research papers on remote sensing

IEEE Account

• Change Username/Password
• Update Address

Purchase Details

• Payment Options
• Order History
• View Purchased Documents

Profile Information

• Communications Preferences
• Profession and Education
• Technical Interests
• US & Canada: +1 800 678 4333
• Worldwide: +1 732 981 0060
• Contact & Support
• About IEEE Xplore
• Accessibility
• Terms of Use
• Nondiscrimination Policy
• Privacy & Opting Out of Cookies

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

• View all journals
• Explore content
• About the journal
• Publish with us
• Sign up for alerts
• Open access
• Published: 11 November 2023

Features extraction from multi-spectral remote sensing images based on multi-threshold binarization

• Bohdan Rusyn 1 , 2 ,
• Oleksiy Lutsyk 1 ,
• Rostyslav Kosarevych 1 ,
• Taras Maksymyuk 3 &
• Juraj Gazda 4  

Scientific Reports volume  13 , Article number:  19655 ( 2023 ) Cite this article

2030 Accesses

10 Citations

1 Altmetric

Metrics details

• Computational science
• Computer science

In this paper, we propose a solution to resolve the limitation of deep CNN models in real-time applications. The proposed approach uses multi-threshold binarization over the whole multi-spectral remote sensing image to extract the vector of discriminative features for classification. We compare the classification accuracy and the training time of the proposed approach with ResNet and Ensemble CNN models. The proposed approach shows a significant advantage in accuracy for small datasets, while keeping very close recall score to both deep CNN models for larger datasets. On the other hand, regardless of the dataset size, the proposed multi-threshold binarization provides approximately 5 times lower training and inference time than both ResNet and Ensemble CNN models.

Similar content being viewed by others

Local feature acquisition and global context understanding network for very high-resolution land cover classification

Dehazing in hyperspectral images: the GRANHHADA database

A new hyperspectral image classification method based on spatial-spectral features

Introduction.

Remote sensing tasks are currently vital for a wide range of applications in our life. The workflow of remote sensing is typically connected to the analysis of large data flows by expert systems and deriving the corresponding inferences, evaluations and predictions. Naturally, such workflows heavily rely on artificial intelligence (AI) solutions 1 . By using deep learning (DL), modern AI algorithms achieved a significant boost in terms of speed and accuracy of decision making, as well as in terms of the overall volume of the processed data in real time 2 , 3 . Notwithstanding the already terrific abilities of state-of-the-art AI-empowered remote sensing solutions, which are able to process images in quasi-real-time with 15–20 fps, there is still a large subset of tasks that require processing time in the range of milliseconds 4 . The most important aspect of the computational performance of the deep learning algorithm is the feature extraction process, which significantly affects the classification performance 5 . According to the literature, feature extraction typically takes up to 80% of all computational loads 6 . The most widely adopted DL solution for image and video processing is based on convolutional neural networks (CNNs), which use a mix of convolutional and dense (fully connected) layers 7 , 8 . The convolutional layers work as feature extractors, while dense layers are used for classification or regression decisions based on the extracted features. Sometimes, feature extractors can use recurrent layers, which provide generative capabilities to the model. Thus, the internal structure and deepness of the CNN model is usually optimized for the specific task to achieve the best performance in terms of accuracy, precision, sensitivity and inference time 7 , 8 .

By nature, deeper CNNs are typically more powerful and can be used for more complex tasks in remote sensing. However, the size of the CNN, or any other DL model, is directly connected to the computational requirements and processing time, which constrain its practical applicability. Thus, the alternative approach is to use models based on binary neural networks 9 , i.e., neural networks, where all weights are binary, instead of floating or integers. Such an approach allows the use of much simpler hardware and provides much faster inference on segmentation tasks based on the generalization of image features 10 .

Typically, CNNs are very likely to run into overfitting by lacking generalization abilities and being biased to the training data. There are several techniques to avoid overfitting, such as adding additive noise to the training data, using dropout layers and optimizing the ratio between model complexity, number of training samples and target accuracy 11 , 12 , 13 , 14 . Feature extraction is a far more complicated process than classification and requires additional optimization steps for training 15 . The training time for the model depends on the internal number of trainable parameters and the size of the dataset. Therefore, the initial optimization direction is to determine the optimal dataset, which is relatively small but provides the target variability, discriminative ability and statistical completeness 16 .

The distinctive property of the typical remote sensing task compared to conventional computer vision tasks is the multi-spectral image processing 17 . Multi-spectral images are composed of a set of monochrome subimages of the same scene from different sensors (cameras) with different wavelengths. The commonly used RGB images are the particular case of the multi-spectral image composed of subimages of red, green and blue colors. Industrial remote sensing satellites, such as Landsat 5, work with 7 subimages, which cover both the visible and infrared ranges from 450 to 1250 nm.

All known approaches for image processing and recognition can be applied for the multi-spectral images by processing each subimage separately 18 . For example, the multi-spectral image can be considered a combination of monochrome images, which are processed separately to extract the distinctive features and landmarks and combine them within a single image. However, better results can be achieved by multi-spectral processing of the image as a whole. This is especially important for the classification tasks, when we need to extract the feature vectors and create a dataset for deep learning 19 . To fully exploit the additional information from several spectral bands, we need to analyze a multi-spectral image as a whole rather than a combination of multiple grayscale images. Thus, each pixel of a multi-spectral image can be represented in a n-dimensional hyperspace as a vector of length k.

There are specific methods dedicated to the processing of the multi-spectral images. In the segmentation of multi-spectral images 20 , each pixel in a different spectrum band forms a vector of features with different intensities, which represent its position in the k-dimensional feature space. The simplest approach to determine a class is to choose the upper and lower thresholds for each spectrum band to represent an m-dimensional hypercube in a feature space. If the feature vector of the pixel fits into the corresponding class localization in a hypercube, the pixel is classified to that class accordingly. In many tasks, segmentation can be simplified to binarization, which reduces the computational complexity and uncertainty of decisions 21 , 22 .

Usually, the classification of the multi-spectral images by deep learning methods is implemented in the same way for any problem. The key difference is all the time hidden in the feature extraction part, which is implemented by the convolutional neural networks 23 , 24 . As an alternative, multi-level approaches are sometimes used, such as decision trees and approaches based on gradient boosting 25 .

From the perspective of processing and feature extraction of multispectral images, decomposition methods have proven to be effective, as they enable the detailing of potential hidden features 26 . In particular, approaches utilizing processing in the spectral domain 27 and methods based on the use of subpixel data 28 for multispectral images can be distinguished. Feature formation technology based on threshold approaches works well for multichannel images 29 , making it possible to apply it to multispectral images.

In the majority of cases, approaches to feature extraction of multispectral images rely on local descriptor methods that do not account for possible relationships in homogeneous regions. To address this issue, a method is proposed in 30 that is based on the extraction of structural features with multiple characteristics of spectral-spatial structures of different objects. Here, local and global structural features are formed and combined into a general feature vector.

In 31 , it is further suggested to utilize multiscale features, which enable effective representation in the feature space of image regions containing objects of arbitrary size or varying scales, thereby enhancing the ability to analyze multispectral images at different levels of detail. This approach allows for the efficient handling of multispectral images, catering to the diverse requirements of various applications in the realm of remote sensing, pattern recognition, and image processing.

The main problem, that occurs during the recognition of multi-spectral images, is that the overall data volume for processing is significantly higher, which negatively affects the processing time and memory consumption. In many tasks, it results in significant constraints for real-time computer vision applications. Recently, we observe numerous developments of smaller and faster CNN architectures such as MobileNet, SqueezeNet, ShuffleNet, etc, which are suitable for resource-constrained environments, such as microcontrollers and mobile devices. However, the main limitation of those models is that they still use convolutional layers for the feature extraction, but their number is significantly reduced and some layers may be simplified by replacing regular convolutions with depthwise convolutions. With depthwise convolution we separate all channels of the image, perform independent convolutions for each channel, and stack the result afterwards. This approach has been proven to be effective for many tasks on RGB images, where number of channels is limited to 3. Typically, those models are just 1–5% below their much larger counterparts in the key performance metrics 32 . However, multi-spectral images sometimes can exceed 100 contiguous spectral bands (channels), which makes depthwise convolutions less favourable in this context. Moreover, a variable number of channels in multi-spectral images does not align well with highly determined architecture of any CNN, where even small change of image resolution has large impact on the overall network performance. Thus, such architectures are not yet suitable for the remote sensing applications.

Therefore, further research on feature extraction approaches for multi-spectral images to address real-time requirements is timely and relevant to the overall field of deep learning-based computer vision and remote sensing applications in particular.

To address the aforementioned problem, in this paper we propose a new approach for the features extraction from multi-spectral images. Proposed approach is aimed to decrease the complexity of the computer vision applications in remote sensing. In particular, we assess the training complexity of the deep learning models on multi-spectral images due to the convolutional layers. We also prove that employing preliminary feature extraction, based on multi-threshold binarization, allows to speed-up the model training process. In addition, the proposed approach is considerably faster and requires a smaller training set compared to conventional training of the convolutional neural networks. The main contribution of the paper are the following:

We develop a new feature extraction algorithm from multi-spectral remote sensing images based on the multi-threshold binarization.

We derive a mathematical model for calculation of an arbitrary number of thresholds for image binarization.

We conduct an experimental evaluation and comparison between proposed approach and commonly used CNN models.

The remainder of this paper is organized as follows. In section “ Introduction ”, we explain in detail the proposed approach for feature extraction from multi-spectral images based on the multi-threshold binarization. In section “ Multi-threshold binarization for feature extraction from multi-spectral images ”, we provide an experimental evaluation and performance analysis. Finally, we conclude this article in section “ Experimental evaluations and performance analysis ”.

Multi-threshold binarization for feature extraction from multi-spectral images

Remote sensing images often contain noise and artifacts. To remove or mitigate this noise, we propose to use a multi-threshold image binarization, as it allows for the filtering of pixels that do not meet specified threshold values. Multi-threshold binarization is a powerful technique, that performs an adaptation of thresholds for each image or for distinct regions within an image, thereby facilitating enhanced feature extraction under various conditions. If it is necessary to highlight objects or features in an image that possess varying contrast or brightness relative to the background, multi-threshold binarization can aid in enhancing extraction accuracy by utilizing different thresholds for different parts of the image.

Thus, the design of the feature extraction algorithm should satisfy the following requirements:

distinguish foreground objects under different lighting and brightness conditions;

support smooth and sharp contours;

be robust to the additive noise;

be invariant to affine transformation;

be invariant to nonlinear distortions;

be compliant with real-time operation.

The conventional way of binarization of grayscale and color images is to use a global threshold to simply obtain a map of the binary features:

where B ( x ,  y ) is a binary representation, f ( x ,  y ) is a grayscale image, T is binarization threshold.

However, considering that deep dense neural network (DNN) is used as a classificator in modern computer vision applications, the number of features, that are extracted with the global threshold binarization is not sufficient for the accurate classification of multi-spectral remote sensing images. Therefore, in this paper we propose a multi-threshold binarization, which allows to transform each subimage into multiple binary representations based on different thresholds. The corresponding set of binary representations is treated as an informative tensor of features for each subimage. The key advantages of the proposed approach are that it allows to extract more features, and also provides a flexibility of feature extraction by using variable number of thresholds.

Let us describe the workflow of the proposed approach. Initially, the multi-spectral image is analyzed pixelwise, considering all spectrum bands, which are represented as a set of matrices. Then, we determine the global threshold, which can be calculated as an average of all values:

where \({{P}_{i}}\) is the value of the pixel intensity, \({{n}_{G}}=x\times y\times m\) is a total number of all pixels, considering all spectrum bands m. Then, the upper and lower thresholds are determined from the maximal and minimal values of pixels intensity:

where \({{T}_{U}}\) —upper threshold, \({{T}_{D}}\) —lower threshold.

To determine the best trade-off between computational complexity and accuracy, we have conducted an experimental evaluation to assess the effective number of thresholds for each image. According to our observations on the studied datasets, the equilibrium is achieved at 7 local equidistant thresholds in combination with one global threshold:

The further increasing of the number of threshold does not provide significant advantage comparing to the added computational complexity.

Let us generalize it to an arbitrary number of thresholds:

where V is a threshold index, r is a number of thresholds.

Multi-threshold binarization allows to represent each spectrum band of the multi-spectral image I as a set of binary matrices L (Fig.  1 ). Note that size of matrices \({{L}_{m}}\left( x,y \right)\) is the same as the size of the input sub-image \(I\left( x,y \right)\) .

Depending on the number of subimages m we will obtain a different number of matrices \(L_{m}\) .

To combine a large number of matrices, we use elementwise XOR and OR operations as follows:

where L is a resulting binary matrix, which indicates the changes in particular elements of all matrices.

Representation of a separate subimage as a set of 9 matrices after multi-threshold binarization.

For the cases in which the invariance to rotations is not mandatory, matrix L is directly used as an input to the classifier, which can be either a classic one or based on the dense neural network. Whenever invariance to rotations is needed, we can use data augmentation to obtain a larger dataset with arbitrary image rotations.

A state-of-the-art remote sensing system consists of many sensors, which can determine an altitude, GPS coordinates and spatial orientation, represented as a quaternion:

where a ,  b ,  c ,  d —real numbers, i ,  j ,  k —imaginary numbers.

A quaternion can be represented into Eulers angles according to the following equations:

where \(\phi ,\theta ,\psi\) —rotation angles from the x ,  y ,  z axes, respectively.

The obtained angles \(\phi ,\theta ,\psi\) can be used for the rotation of the feature matrix \(L_{m}\) and perspective alignment. Thus, each sub-image \(L_{m}(x,y)\) is rotated by the angle \(\phi\) . If the rotation is performed around the origin (0, 0), the corresponding transformation is represented according to the following equations:

where \(\left( {{x}_{2}},{{y}_{2}} \right)\) —coordinates after rotation. Considering that images can be obtained at different angles to the normal, we should also take into account a perspective transformation. This can be achieved by using rotations along the y and z axes:

where \({\textbf{R}}_{\varvec{\theta }},{\textbf{R}}_{\varvec{\psi }}\) —rotation matrices along y and z axes.

By preprocessing the feature matrix \(L_{m}\) , we achieve invariance to the rotation and projection alignment. Such an approach provides faster training because it eliminates the need to train the model on an excessive dataset with additional rotated samples.

Experimental evaluations and performance analysis

The comparison of the proposed approach with existing ResNet and Ensemble CNN was conducted in terms of performance metrics and computational complexity during model training. Computational complexity significantly correlates with the training and inference time of the models. For this, ResNet, Ensemble CNN, and the proposed approach were trained from scratch on various sizes of training sets and with the same dense neural network head for all models. For each case, an assessment of validation accuracy and training time was conducted. The results showed that for some training set sizes, the proposed approach demonstrates the best classification accuracy results, while the performance of the proposed approach is almost 5 times higher. The experimental workflow is as follows. From each subimage of the multi-spectral image, we obtain the target number of binary representations for different binarization thresholds. The obtained representations are combined to create a vector of image features, which can be fed to the dense neural network classifier (Fig.  2 ). The invariance to rotations and affine transformations is ensured by the corresponding rotation operators and robust training. It is worth noting that dense neural network classifier, could have been replaced by other solutions, such as naive Bayesian classifier, support vector machines, random forest, k-nearest neighbors, etc. However, since our main aim is to compete with larger CNN architectures which all use dense neural network classifier, we also use it throughout this particular research to understand the exact impact of the proposed approach.

The optimal number of thresholds for each subimage of multi-spectral image is determined experimentally by looking at the classification accuracy. However, each additional threshold results in an increase in computational complexity and a longer inference time.

The workflow of the feature extraction from multi-spectral images.

Classification accuracy vs number of thresholds for the Zurich dataset.

Classification accuracy vs dataset size for the TipJul1 database.

Classification accuracy vs dataset size for the Zurich database.

Accuracy vs training time for the Zurich database.

From the results in Fig.  3 , we can conclude that the case with 7 thresholds satisfies most of the conditions, and further increasing of the threshold number does not necessarily improve the classification accuracy. To evaluate the performance of the proposed approach, we compare it with two reference architectures, namely, ResNet and Ensemble CNN. The dataset for the experiment is created based on the multi-spectral images obtained from remote sensing of the Earth’s surface. The whole dataset is split into 60%, 20% and 20% parts for training, validation and testing, respectively. The class labels are obtained from the homepage of the University of Valencia:

The TipJul1 dataset based on Landsat data has 7 bands and 5 classes, with a resolution of 169x169 pixels;

The Zurich dataset based on QuickBird data has 4 bands and 4 classes, with a resolution of 828 \(\times\) 889 pixels.

The ensemble of CNNs is based on the use of multiple CNN models, which are combined to create a single prediction. Ensemble learning is employed to enhance the performance of machine learning models by combining several models trained on the same training dataset. In this case, the ensemble is achieved by training multiple CNN models with the same architecture and parameters but with different initial weights. Predictions made by each of these models are combined based on the majority class with the highest number of votes. This combination of multiple models reduces the variance and increases the stability of predictions, leading to an improvement in classification accuracy.

From the results presented in Figs.  4 and 5 , we can conclude that for small datasets, the proposed approach outperforms the ResNet and Ensemble CNN in terms of classification accuracy. This can be explained by the fact that both ResNet and Ensemble CNN extract features from the deep cascade of convolutional layers, which require large datasets for training. Thus, the key advantage of the proposed feature extraction approach is that it is able to work with a small training dataset, e.g. 200–800 images. Moreover, the proposed model still provides decent performance for large datasets (e.g. more than 1800 images), despite being outperformed with a small margin by deep CNN architectures in terms of classification accuracy. We further investigate the other performance metrics to compare the the proposed approach with two other models. In the Table  1 we depict the highest achieved values of accuracy, precision, recall and F1-score regardless of the training time and dataset size. All metrics have been measured for both TipJul1 and Zurich datasets. Obtained results correlate with those displayed on Figs.  4 , 5 and 6 , and we observe that multi-threshold binarization has noticeably lower scores in accuracy , precision and F1-score , while being very close to the more complex CNN models in recall . This can be explained by the difference between underlying meaning of those metrics. Whereas, accuracy and F1-score are the balanced metrics that reflect the models ability to classify true positive and true negative samples, the precision is biased towards minimizing false positive samples, and recall is biased towards minimizing false negative samples. In most computer vision tasks, we seek for a trade-off between precision and recall , reflected by the F1-score . However, in the context of many remote sensing applications, we often look for environmental anomalies such as large forest fires, erupting volcanoes, etc. Minimizing false negative samples allows to identify the problems earlier and save more time for a corresponding reaction. In this context, recall metric is the most important, which proves a suitability of the proposed approach specifically to the remote sensing computer vision applications. For a more comprehensive understanding, we also compare the training time for all studied models. To evaluate the training time of the models, standard tools contained in the TensorFlow deep learning library were used. In this case, for evaluating the ResNet and Ensemble CNN models, model training profiling tools were employed. The profiling log contains information about the execution time of the model operations; by analyzing it, one can determine how much time the training process takes. Assessing the training time of the proposed model was somewhat more complex since it involves the preliminary application of multi-threshold binarization. In this instance, checkpoint markers were used, and measuring the time between checkpoints allow to determine the training time. As observed from the results in the Table  2 , the computational complexity of the multi-threshold binarization is much lower than those of ResNet and Ensemble CNN architectures, due to the absence of convolutional layers.

As shown in Table  2 , the training times for ResNet and Ensemble CNN are similar and approximately 5 times larger than for the proposed multi-threshold binarization. The same difference is observed for the inference time, where the proposed approach is able to classify the image for 0.08 s using 3.6 GHz Intel Core i5 CPU and Nvidia GTX 1060 GPU.

Finally, we compare the accuracy of the studied models with respect to the training time, which is required to achieve it. According to the results in Fig.  6 , we can observe that with the short training time, multi-threshold binarization has up to 19% higher classification accuracy compared to ResNet and Ensemble CNN models. Both CNN-based models are able to show decent results after a significantly longer training time. Note that within the current experimental setup, we do not have the results for multi-threshold binarization for the longer training time, but even with a short training time, it seems to lose only 3–5% compared to the well-trained CNN counterparts. Thus, the proposed multi-threshold binarization can be considered a good alternative to the complex and deep CNN architectures for real-time remote sensing applications.

In this paper, we have proposed a new solution to tackle the real-time image classification problem for remote sensing applications. In the proposed approach the typical deep CNN feature extractor is replaced by the multi-threshold binarization, which allows us to obtain highly discriminative features with much lower computational complexity. Experimental results on the TipJul1 and Zurich datasets show that the proposed multi-threshold binarization provides better classification accuracy after training on small datasets, while being outperformed by ResNet and Ensemble CNN on larger datasets. Nevertheless, in terms of complexity, the proposed approach provides 5 times lower training and inference time compared to ResNet and Ensemble CNN while maintaining the classification accuracy. In our future research, we will compare how the MobileNet, ShuffleNet and proposed approach perform on the highly complex multi-spectral images with very large number of channels, and also much higher number of classes and samples.

Data availability

The datasets generated and analysed during the current study are available in the Landsat Collections repository, available at https://www.usgs.gov/landsat-missions/landsat-collections , and the HYPERLABELME repository, available at https://hyperlabelme.uv.es/ .

Ma, L. et al. Deep learning in remote sensing applications: A meta-analysis and review. ISPRS J. Photogramm. Remote Sens. 152 , 166–177. https://doi.org/10.1016/j.isprsjprs.2019.04.015 (2019).

Article   ADS   Google Scholar  

Cheng, G., Xie, X., Han, J., Guo, L. & Xia, G.-S. Remote sensing image scene classification meets deep learning: Challenges, methods, benchmarks, and opportunities. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 13 , 3735–3756. https://doi.org/10.1109/JSTARS.2020.3005403 (2020).

Khosravi, M. R. & Tavallali, P. Real-time statistical image and video processing for remote sensing and surveillance applications. J. Real-Time Image Process. 18 , 1435–1439 (2021).

Article   Google Scholar  

Huang, X. et al. Machine learning based video processing for real-time near-miss detection. In VEHITS , 169–179 (2020).

Mutlag, W. K., Ali, S. K., Aydam, Z. M. & Taher, B. H. Feature extraction methods: A review. J. Phys. Conf. Ser. 1591 , 012028. https://doi.org/10.1088/1742-6596/1591/1/012028 (2020).

Chou, K.-P. et al. Robust feature-based automated multi-view human action recognition system. IEEE Access 6 , 15283–15296 (2018).

Xiao, Y. et al. Action recognition for depth video using multi-view dynamic images. Inf. Sci. 480 , 287–304. https://doi.org/10.1016/j.ins.2018.12.050 (2019).

Han, Y., Zhang, P., Zhuo, T., Huang, W. & Zhang, Y. Going deeper with two-stream convnets for action recognition in video surveillance. Pattern Recognit. Lett. 107 , 83–90. https://doi.org/10.1016/j.patrec.2017.08.015 (2018). Video Surveillance-oriented Biometrics.

Zhuang, B. et al. Structured binary neural networks for image recognition. Int. J. Comput. Vis. 130 , 2081–2102 (2022).

Ding, R., Liu, H. & Zhou, X. IE-Net: Information-enhanced binary neural networks for accurate classification. Electronics 11 , 937 (2022).

Madaeni, F. et al. Convolutional neural network and long short-term memory models for ice-jam predictions. Cryosphere 16 , 1447–1468 (2022).

Rusyn, B., Korniy, V., Lutsyk, O. & Kosarevych, R. Deep learning for atmospheric cloud image segmentation. In 2019 XIth International Scientific and Practical Conference on Electronics and Information Technologies (ELIT) , 188–191. https://doi.org/10.1109/ELIT.2019.8892285 (2019).

Chen, Y., Lin, Z., Zhao, X., Wang, G. & Gu, Y. Deep learning-based classification of hyperspectral data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 7 , 2094–2107. https://doi.org/10.1109/JSTARS.2014.2329330 (2014).

Ma, L. et al. Deep learning in remote sensing applications: A meta-analysis and review. ISPRS J. Photogramm. Remote Sens. 152 , 166–177 (2019).

Freire, P. J. et al. Performance versus complexity study of neural network equalizers in coherent optical systems. J. Lightw. Technol. 39 , 6085–6096 (2021).

Rusyn, B., Lutsyk, O. & Kosarevych, R. Evaluating the informativity of a training sample for image classification by deep learning methods. Cybern. Syst. Anal. 57 , 853–863 (2021).

Article   MATH   Google Scholar  

Feng, X., He, L., Cheng, Q., Long, X. & Yuan, Y. Hyperspectral and multispectral remote sensing image fusion based on endmember spatial information. Remote Sens. 12 , 1009 (2020).

Nalepa, J. Recent advances in multi-and hyperspectral image analysis. Sensors 21 , 6002 (2021).

Article   ADS   PubMed   PubMed Central   Google Scholar  

Su, T., Zhang, S. & Liu, T. Multi-spectral image classification based on an object-based active learning approach. Remote Sens. 12 , 504 (2020).

Article   ADS   CAS   Google Scholar  

Yuan, X., Shi, J. & Gu, L. A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Syst. Appl. 169 , 114417 (2021).

Rahkar Farshi, T. & Demirci, R. Multilevel image thresholding with multimodal optimization. Multimed. Tools Appl. 80 , 15273–15289 (2021).

Ashir, A. M. Multilevel thresholding for image segmentation using mean gradient. J. Electr. Comput. Eng. 2022 (2022).

Wei, L. et al. Crops fine classification in airborne hyperspectral imagery based on multi-feature fusion and deep learning. Remote Sens. 13 , 2917 (2021).

Yang, S., Gu, L., Li, X., Jiang, T. & Ren, R. Crop classification method based on optimal feature selection and hybrid CNN-RF networks for multi-temporal remote sensing imagery. Remote Sens. 12 , 3119 (2020).

Taherkhani, A., Cosma, G. & McGinnity, T. M. AdaBoost-CNN: An adaptive boosting algorithm for convolutional neural networks to classify multi-class imbalanced datasets using transfer learning. Neurocomputing 404 , 351–366 (2020).

Duan, P. et al. Component decomposition-based hyperspectral resolution enhancement for mineral mapping. Remote Sens. 12 , 2903 (2020).

Li, Q., Zheng, B. & Yang, Y. Spectral-spatial active learning with structure density for hyperspectral classification. IEEE Access 9 , 61793–61806. https://doi.org/10.1109/ACCESS.2021.3074405 (2021).

Sellars, P., Aviles-Rivero, A. I. & Schönlieb, C.-B. Superpixel contracted graph-based learning for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 58 , 4180–4193. https://doi.org/10.1109/TGRS.2019.2961599 (2020).

Thepade, S., Das, R. & Ghosh, S. A novel feature extraction technique using binarization of bit planes for content based image classification. J. Eng. 2014 (2014).

Liang, N., Duan, P., Xu, H. & Cui, L. Multi-view structural feature extraction for hyperspectral image classification. Remote Sens. 14 , 1971 (2022).

Huang, S., Lu, Y., Wang, W. & Sun, K. Multi-scale guided feature extraction and classification algorithm for hyperspectral images. Sci. Rep. 11 , 18396 (2021).

Article   ADS   CAS   PubMed   PubMed Central   Google Scholar  

Yu, K. et al. MobileNet-YOLO v5s: An improved lightweight method for real-time detection of sugarcane stem nodes in complex natural environments. IEEE Access 11 , 104070–104083. https://doi.org/10.1109/ACCESS.2023.3317951 (2023).

Download references

Acknowledgements

This research was supported by a project #0117U000519 of the National Academy of Science of Ukraine, by the project #0120U102193 of the Ministry of Education and Science of Ukraine (No. 0123U100232), and by the Slovak Research and Development Agency, project number APVV-18-0214 and VEGA 1/0685/23.

Author information

Authors and affiliations.

Department of Remote Sensing Information Technologies, Karpenko Physico-Mechanical Institute, NAS of Ukraine, Lviv, Ukraine

Bohdan Rusyn, Oleksiy Lutsyk & Rostyslav Kosarevych

Department of Informatics and Teleinformatics, Kazimierz Pulaski University of Technology and Humanities, Radom, Poland

Bohdan Rusyn

Department of Telecommunications, Lviv Polytechnic National University, Lviv, Ukraine

Taras Maksymyuk

Department of Computers and Informatics, Technical University of Kosice, Kosice, Slovakia

Juraj Gazda

You can also search for this author in PubMed   Google Scholar

Contributions

The contribution of each of the authors in this research articles can be divided as follows: conceptualization—O.L. and R.K.; methodology—O.L.; software—O.L.; validation—R.K. and B.R.; formal analysis—T.M. and J.G.; investigation—R.K., O.L.; data curation—R.K.; writing—original draft preparation—O.L.; editing—B.R. and T.M.; supervision—B.R.; proofreading and funding acquisition—J.G. All authors have read and agreed to the published version of the manuscript.

Corresponding authors

Correspondence to Oleksiy Lutsyk or Taras Maksymyuk .

Ethics declarations

Competing interests.

The authors declare no competing interests.

Additional information

Publisher's note.

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ .

Reprints and permissions

About this article

Cite this article.

Rusyn, B., Lutsyk, O., Kosarevych, R. et al. Features extraction from multi-spectral remote sensing images based on multi-threshold binarization. Sci Rep 13 , 19655 (2023). https://doi.org/10.1038/s41598-023-46785-7

Download citation

Received : 11 July 2023

Accepted : 05 November 2023

Published : 11 November 2023

DOI : https://doi.org/10.1038/s41598-023-46785-7

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

This article is cited by

Deep learning assisted xrf spectra classification.

• Velibor Andric
• Goran Kvascev
• Maja Gajic-Kvascev

Scientific Reports (2024)

By submitting a comment you agree to abide by our Terms and Community Guidelines . If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

Quick links

• Explore articles by subject
• Guide to authors
• Editorial policies

Sign up for the Nature Briefing: Anthropocene newsletter — what matters in anthropocene research, free to your inbox weekly.

Information

• Author Services

Initiatives

You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.

All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .

Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.

Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.

Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.

Original Submission Date Received: .

• Active Journals
• Find a Journal
• Proceedings Series
• For Authors
• For Reviewers
• For Editors
• For Librarians
• For Publishers
• For Societies
• For Conference Organizers
• Open Access Policy
• Institutional Open Access Program
• Special Issues Guidelines
• Editorial Process
• Research and Publication Ethics
• Article Processing Charges
• Testimonials
• Preprints.org
• SciProfiles
• Encyclopedia

Article Menu

• Subscribe SciFeed
• Recommended Articles
• Google Scholar
• on Google Scholar
• Table of Contents

Find support for a specific problem in the support section of our website.

Please let us know what you think of our products and services.

Visit our dedicated information section to learn more about MDPI.

JSmol Viewer

Challenges facing the use of remote sensing technologies in the construction industry: a review.

1. Introduction

• The primary goal of categorizing and classifying remote sensing technologies is to categorize and classify the diverse types of remote sensing technologies (such as satellite, airborne, and ground-based systems) employed within the construction industry, developing a comprehensive understanding of diverse remote sensing methodologies through categorization and classification.
• The paper aims to identify and analyze the specific challenges associated with each type of remote sensing technology utilized in construction. By scrutinizing the obstacles and limitations faced by satellite, airborne, and ground-based remote sensing technologies, this review intends to illuminate the practical difficulties construction professionals encounter when integrating these technologies into their projects.
• To propose solutions and future research directions, another objective is to propose potential solutions and suggest future research directions to tackle the challenges identified for each type of remote sensing technology by offering actionable insights to empower construction professionals to enhance the utilization and efficacy of remote sensing technologies in their projects.

2. Background

2.1. remote sensing imaging mechanism, 2.2. remote sensing platform, 2.3. remote sensing techniques applied for construction industry, 3. data collection, 3.1. method of collection, 3.2. bibliographic metadata, 4.1. overview, 4.2. merits and limitations of each remote sensing type, 4.3. challenge of using remote sensing in construction management, 4.3.1. temporal resolutions, 4.3.2. spatial resolution, 4.3.3. spatiotemporal resolution, 4.3.4. weather issues, 4.3.5. atmospheric and cloud covering, 4.3.6. shadow issues.

• Obstruction by tall trees: Tall trees can obstruct buildings in the images, leading to incomplete or inaccurate data.
• Sensor observation angle: The observation angle of the sensor can cause anomalies in the shape of buildings, making it challenging to extract accurate information.
• Diversity of building materials and structures: The wide variety of exterior building materials and structures makes it difficult to develop consistent building extraction models.

4.3.7. Logistical and Regulation Issues

4.3.8. cost issues, 4.3.9. technical issues, 4.3.10. standardization issues, 4.3.11. safety issues, 5. practical implications, 6. recommendation for future research, 7. conclusions, data availability statement, conflicts of interest.

• Zhang, S.; Bogus, S.M.; Lippitt, C.D.; Kamat, V.; Lee, S. Implementing Remote-Sensing Methodologies for Construction Research: An Unoccupied Airborne System Perspective. J. Constr. Eng. Manag. 2022 , 148 , 03122005. [ Google Scholar ] [ CrossRef ]
• Sun, B. Application of satellite remote sensing in the construction and comprehensive management of smart cities. In Advances in Civil Engineering and Environmental Engineering ; CRC Press: Boca Raton, FL, USA, 2023. [ Google Scholar ]
• Moselhi, O.; Bardareh, H.; Zhu, Z. Automated data acquisition in construction with remote sensing technologies. Appl. Sci. 2020 , 10 , 2846. [ Google Scholar ] [ CrossRef ]
• Kushwaha, P.; Dubey, S. Application of remote sensing in civil engineering. Southeast Asian J. Case Rep. Rev. 2023 , 9 , 74–76. [ Google Scholar ] [ CrossRef ]
• Liang, H.; Cho, J.; Seo, S. Construction Site Multi-Category Target Detection System Based on UAV Low-Altitude Remote Sensing. Remote Sens. 2023 , 15 , 1560. [ Google Scholar ] [ CrossRef ]
• Beevi, L.S.; Muthusundari, S.; Sakthi, D.V.; Subhashini, G. Blockchain-Based Remote Construction Monitoring Using UAV in SITL Simulation. In Proceedings of Third International Conference on Sustainable Expert Systems: ICSES 2022 ; Lecture Notes in Networks and Systems; Springer Nature Singapore: Singapore, 2022. [ Google Scholar ]
• Vu, T.-T.; Wickramasinghe, D.; Ahmed, M.; Maul, T. Remote Sensing Monitoring Large-Scale Repetitive Construction Projects. In Proceedings of the 35th EARSeL Symposium—European Remote Sensing: Progress, Challenges and Opportunities, Stockholm, Sweden, 15–18 June 2015. [ Google Scholar ]
• Wickramasinghe, D.C.; Vu, T.T.; Maul, T. Satellite remote-sensing monitoring of a railway construction project. Int. J. Remote Sens. 2018 , 39 , 1754–1769. [ Google Scholar ] [ CrossRef ]
• Aricak, B. Using remote sensing data to predict road fill areas and areas affected by fill erosion with planned forest road construction: A case study in Kastamonu Regional Forest Directorate (Turkey). Environ. Monit. Assess 2015 , 187 , 7. [ Google Scholar ] [ CrossRef ]
• Behnam, A.; Wickramasinghe, D.C.; Ghaffar, M.A.A.; Vu, T.T.; Tang, Y.H.; Isa, H.B.M. Automated progress monitoring system for linear infrastructure projects using satellite remote sensing. Autom. Constr. 2016 , 68 , 114–127. [ Google Scholar ] [ CrossRef ]
• Schnebele, E.; Tanyu, B.F.; Cervone, G.; Waters, N. Review of remote sensing methodologies for pavement management and assessment. Eur. Transp. Res. Rev. 2015 , 7 , 2. [ Google Scholar ] [ CrossRef ]
• Zhang, H.; Zhang, Y.; Gao, T.; Lan, S.; Tong, F.; Li, M. Landsat 8 and Sentinel-2 Fused Dataset for High Spatial-Temporal Resolution Monitoring of Farmland in China’s Diverse Latitudes. Remote. Sens. 2023 , 15 , 2951. [ Google Scholar ] [ CrossRef ]
• Drusch, M.; Del Bello, U.; Carlier, S.; Colin, O.; Fernandez, V.; Gascon, F.; Hoersch, B.; Isola, C.; Laberinti, P.; Martimort, P.; et al. Sentinel-2: ESA’s Optical High-Resolution Mission for GMES Operational Services. Remote Sens. Environ. 2012 , 120 , 25–36. [ Google Scholar ] [ CrossRef ]
• Claverie, M.; Ju, J.; Masek, J.G.; Dungan, J.L.; Vermote, E.F.; Roger, J.-C.; Skakun, S.V.; Justice, C. The Harmonized Landsat and Sentinel-2 surface reflectance data set. Remote. Sens. Environ. 2018 , 219 , 145–161. [ Google Scholar ] [ CrossRef ]
• Mandanici, E.; Bitelli, G. Preliminary comparison of sentinel-2 and landsat 8 imagery for a combined use. Remote. Sens. 2016 , 8 , 1014. [ Google Scholar ] [ CrossRef ]
• Chastain, R.; Housman, I.; Goldstein, J.; Finco, M.; Tenneson, K. Empirical cross sensor comparison of Sentinel-2A and 2B MSI, Landsat-8 OLI, and Landsat-7 ETM+ top of atmosphere spectral characteristics over the conterminous United States. Remote Sens. Environ. 2019 , 221 , 274–285. [ Google Scholar ] [ CrossRef ]
• Ferrero, A.M.; Forlani, G.; Roncella, R.; Voyat, H.I. Advanced geostructural survey methods applied to rock mass characterization. Rock Mech. Rock Eng. 2009 , 42 , 631–665. [ Google Scholar ] [ CrossRef ]
• Kennedy, R.E.; Townsend, P.A.; Gross, J.E.; Cohen, W.B.; Bolstad, P.; Wang, Y.; Adams, P. Remote sensing change detection tools for natural resource managers: Understanding concepts and tradeoffs in the design of landscape monitoring projects. Remote Sens. Environ. 2009 , 113 , 1382–1396. [ Google Scholar ] [ CrossRef ]
• Jianzhong, S.; Zhimo, C.; Zhixiang, J.; Jing, R. Urban Construction Planning and Aerial Remote Sensing Information System of Shanghai. In Geosciences and Human Survival, Environment, Natural Hazards, Global Change ; CRC Press: Boca Raton, FL, USA, 2023. [ Google Scholar ]
• Kaamin, M.; Fahmizam, M.A.F.; Jefri, A.S.; Sharom, M.H.; Kadir, M.A.A.; Nor, A.H.M.; Supar, K. Progress Monitoring at Construction Sites Using UAV Technology. IOP Conf. Ser. Earth Environ. Sci. 2023 , 1140 , 012025. [ Google Scholar ] [ CrossRef ]
• Hasan, A.; Qadir, A.; Nordeng, I.; Neubert, J. Construction Inspection through Spatial Database. In Proceedings of the 34th International Symposium on Automation and Robotics in Construction and Mining (ISARC 2017), Taipei, Taiwan, 28 June–1 July 2017. [ Google Scholar ]
• Vincke, S.; Bassier, M.; Hernandez, R.d.L.; Dejaeghere, I.; Carbonez, K.; Vergauwen, M. Remote sensing data as basis for the modelling and reassembly of dismantled heritage structures. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. —ISPRS Arch. 2019 , 42 , 1187–1194. [ Google Scholar ] [ CrossRef ]
• Zhang, S.; Lippitt, C.D.; Bogus, S.M.; Neville, P.R.H. Characterizing pavement surface distress conditions with hyper-spatial resolution natural color aerial photography. Remote Sens. 2016 , 8 , 392. [ Google Scholar ] [ CrossRef ]
• Zhang, S.; Lippitt, C.D.; Bogus, S.M.; Loerch, A.C.; Sturm, J.O. The accuracy of aerial triangulation products automatically generated from hyper-spatial resolution digital aerial photography. Remote. Sens. Lett. 2016 , 7 , 160–169. [ Google Scholar ] [ CrossRef ]
• Yao, S.; Li, L.; Cheng, G.; Zhang, B. Analyzing Long-Term High-Rise Building Areas Changes Using Deep Learning and Multisource Satellite Images. Remote. Sens. 2023 , 15 , 2427. [ Google Scholar ] [ CrossRef ]
• Wang, X.; Xing, Q.; An, D.; Meng, L.; Zheng, X.; Jiang, B.; Liu, H. Effects of spatial resolution on the satellite observation of floating macroalgae blooms. Water 2021 , 13 , 1761. [ Google Scholar ] [ CrossRef ]
• Roy, S.; Chakraborty, A. Single Image Super-resolution with a Switch Guided Hybrid Network for Satellite Images. arXiv 2020 , arXiv:2011.14380. [ Google Scholar ]
• Liu, S.; Hodgson, M.E. Satellite image collection modeling for large area hazard emergency response. ISPRS J. Photogramm. Remote. Sens. 2016 , 118 , 13–21. [ Google Scholar ] [ CrossRef ]
• Sehgal, S.; Ahuja, L.; Hima Bindu, M. High Resolution Satellite Image Compression using DCT and EZW. In Proceedings of the International Conference on Sustainable Computing in Science, Technology and Management (SUSCOM), Amity University Rajasthan, Jaipur, India, 26–28 February 2019. Available online: https://ssrn.com/abstract=3350914 (accessed on 5 April 2024).
• Huang, C.-L.C.; Munasinghe, T. Exploring Various Applicable Techniques to Detect Smoke on the Satellite Images. In Proceedings of the 2020 IEEE International Conference on Big Data, Big Data 2020, Institute of Electrical and Electronics Engineers Inc., Virtual Conference, 10–13 December 2020; pp. 5703–5705. [ Google Scholar ] [ CrossRef ]
• Liu, S.; Hodgson, M.E. Optimizing large area coverage from multiple satellite-sensors. GIScience Remote Sens. 2013 , 50 , 652–666. [ Google Scholar ] [ CrossRef ]
• Reddy, G. Satellite Remote Sensing Sensors: Principles and Applications. In Geospatial Technologies in Land Resources Mapping, Monitoring and Management: An Overview ; Springer: Berlin/Heidelberg, Germany, 2018. [ Google Scholar ]
• Singh, K.D.; Nansen, C. Advanced calibration to improve robustness of drone-acquired hyperspectral remote sensing data. In Proceedings of the 6th International Conference on Agro-Geoinformatics, Fairfax, VA, USA, 7–10 August 2017. [ Google Scholar ]
• Bolt, M.; Prather, J.C.; Horton, T.; Adams, M. Massively Deployable, Low-Cost Airborne Sensor Motes for Atmospheric Characterization. Wirel. Sens. Netw. 2020 , 12 , 99869. [ Google Scholar ] [ CrossRef ]
• Na Dong, L.; Tong, J.; Wang, C.Y. The Application of airborne remote sensing technology in land and resources. Appl. Mech. Mater. 2014 , 644–650 , 4360–4363. [ Google Scholar ] [ CrossRef ]
• Lee, K.; Noh, H.; Lim, J. Airborne relay-based regional positioning system. Sensors 2015 , 15 , 12682–12699. [ Google Scholar ] [ CrossRef ]
• Li, N.; Zhang, Y.; Shi, K.; Zhang, Y.; Sun, X.; Wang, W.; Qian, H.; Yang, H.; Niu, Y. Real-Timeand Continuous Tracking of Total Phosphorus Using a Ground-Based Hyperspectral Proximal Sensing System. Remote Sens. 2023 , 15 , 507. [ Google Scholar ] [ CrossRef ]
• Wu, P.; Shan, C.; Liu, C.; Xie, Y.; Wang, W.; Zhu, Q.; Zeng, X.; Liang, B. Ground-Based Remote Sensing of Atmospheric Water Vapor Using High-Resolution FTIR Spectrometry. Remote. Sens. 2023 , 15 , 3484. [ Google Scholar ] [ CrossRef ]
• Hoshiba, M. Real-Time Prediction of Impending Ground Shaking: Review of Wavefield-Based (Ground-Motion-Based) Method for Earthquake Early Warning. Front. Earth Sci. 2021 , 9 , 722784. [ Google Scholar ] [ CrossRef ]
• Sousa, D.; Small, C. WhichVegetation Index? Benchmarking Multispectral Metrics to Hyperspectral Mixture Models in Diverse Cropland. Remote. Sens. 2023 , 15 , 971. [ Google Scholar ] [ CrossRef ]
• Gu, L.; Shuai, Y.; Shao, C.; Xie, D.; Zhang, Q.; Li, Y.; Yang, J. Angle effect on typical optical remote sensing indices in vegetation monitoring. Remote. Sens. 2021 , 13 , 1699. [ Google Scholar ] [ CrossRef ]
• Silva, T.M.d.A.; Valente, D.S.M.; Pinto, F.d.A.d.C.; de Queiroz, D.M.; Santos, N.T. Sensor system for acquisition of vegetation indexes. Rev. Bras. Eng. Agric. Ambient. 2021 , 25 , 264–269. [ Google Scholar ] [ CrossRef ]
• O’sullivan, A.M.; Kurylyk, B.L. Limiting External Absorptivity of UAV-Based Uncooled Thermal Infrared Sensors Increases Water Temperature Measurement Accuracy. Remote. Sens. 2022 , 14 , 6356. [ Google Scholar ] [ CrossRef ]
• Marcq, S.; Delogu, E.; Chapelier, M.; Vidal, T.H.G. DirecTES: A Direct Method for Land and Sea Surface Temperature and Emissivity Separation for Thermal Infrared Sensors—Application to TRISHNA and ECOSTRESS. Remote. Sens. 2023 , 15 , 517. [ Google Scholar ] [ CrossRef ]
• Khan, Y.; Butt, M.A.; Khonina, S.N.; Kazanskiy, N.L. Thermal Sensor Based on Polydimethylsiloxane Polymer Deposited on Low-Index-Contrast Dielectric Photonic Crystal Structure. Photonics 2022 , 9 , 770. [ Google Scholar ] [ CrossRef ]
• Ren, H.; Ye, X.; Nie, J.; Meng, J.; Fan, W.; Qin, Q.; Liang, Y.; Liu, H. Retrieval of Land Surface Temperature, Emissivity, and Atmospheric Parameters from Hyperspectral Thermal Infrared Image Using a Feature-Band Linear-Format Hybrid Algorithm. IEEE Trans. Geosci. Remote Sens. 2021 , 60 , 4401015. [ Google Scholar ] [ CrossRef ]
• Michler, F.; Scheiner, B.; Reissland, T.; Weigel, R.; Koelpin, A. Micrometer Sensing with Microwaves: Precise Radar Systems for Innovative Measurement Applications. IEEE J. Microwaves 2021 , 1 , 202–217. [ Google Scholar ] [ CrossRef ]
• Berthold, P.; Michaelis, M.; Luettel, T.; Meissner, D.; Wuensche, H.-J. A Radar measurement model for extended object tracking in dynamic scenarios. In Proceedings of the 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France, 9–12 June 2019. [ Google Scholar ]
• Fioranelli, F.D.; Shah, S.A.D.; Li, H.; Shrestha, A.; Yang, S.D.; Le Kernec, D.J.L. Radar sensing for healthcare. Electron. Lett. 2019 , 55 , 1022–1024. [ Google Scholar ] [ CrossRef ]
• Rane, V.; Poojari, H.; Sharma, P.; Phansekar, S.; Pawar, P. LiDAR Based Self-Driving Car. Int. J. Res. Appl. Sci. Eng. 2022 , 10 , 261–270. [ Google Scholar ] [ CrossRef ]
• Dreissig, M.; Scheuble, D.; Piewak, F.; Boedecker, J. Survey on LiDAR Perception in Adverse Weather Conditions. In Proceedings of the 2023 IEEE Intelligent Vehicles Symposium (IV), Anchorage, AK, USA, 4–7 June 2023. [ Google Scholar ] [ CrossRef ]
• Vivek, C.; Kareti, V.; Atmuri, P.; Venkateshwarlu, S.C. Design and Implementation of LIDAR System for Distance Measurements. Int. J. Sci. Res. Eng. Manag. 2022 , 6 , 6060–6063. [ Google Scholar ] [ CrossRef ]
• van Veen, M.; Hutchinson, D.J.; Kromer, R.; Lato, M.; Edwards, T. Effects of of sampling interval on the frequency—Magnitude relationship of rockfalls detected from terrestrial laser scanning using semi-automated methods. Landslides 2017 , 14 , 1579–1592. [ Google Scholar ] [ CrossRef ]
• D’Amato, J.; Hantz, D.; Guerin, A.; Jaboyedoff, M.; Baillet, L.; Mariscal, A. Influence of meteorological factors on rockfall occurrence in a middle mountain limestone cliff. Nat. Hazards Earth Syst. Sci. 2016 , 16 , 719–735. [ Google Scholar ] [ CrossRef ]
• Williams, J.G.; Rosser, N.J.; Hardy, R.J.; Brain, M.J. The Importance of Monitoring Interval for Rockfall Magnitude-Frequency Estimation. J. Geophys. Res. Earth Surf. 2019 , 124 , 2841–2853. [ Google Scholar ] [ CrossRef ]
• Giacomini, A.; Thoeni, K.; Santise, M.; Diotri, F.; Booth, S.; Fityus, S.; Roncella, R. Temporal-spatial frequency rockfall data from open-pit highwalls using a low-cost monitoring system. Remote Sens. 2020 , 12 , 2459. [ Google Scholar ] [ CrossRef ]
• Corbari, C.; Ravazzani, G.; Mancini, M. A distributed thermodynamic model for energy and mass balance computation: FEST-EWB. Hydrol. Process. 2011 , 25 , 1443–1452. [ Google Scholar ] [ CrossRef ]
• van Duynhoven, A.; Dragićević, S. Analyzing the effects of temporal resolution and classification confidence for modeling land cover change with long short-term memory networks. Remote Sens. 2019 , 11 , 2784. [ Google Scholar ] [ CrossRef ]
• Feng, S.; Liu, S.; Jing, L.; Zhu, Y.; Yan, W.; Jiang, B.; Liu, M.; Lu, W.; Ning, Y.; Wang, Z.; et al. Quantification of the environmental impacts of highway construction using remote sensing approach. Remote. Sens. 2021 , 13 , 1340. [ Google Scholar ] [ CrossRef ]
• Hartmeyer, I.; Delleske, R.; Keuschnig, M.; Krautblatter, M.; Lang, A.; Schrott, L.; Otto, J.-C. Current glacier recession causes significant rockfall increase: The immediate paraglacial response of deglaciating cirque walls. Earth Surf. Dyn. 2020 , 8 , 729–751. [ Google Scholar ] [ CrossRef ]
• Kustas, W.P.; Norman, J.M.; Anderson, M.C.; French, A.N. Estimating subpixel surface temperatures and energy fluxes from the vegetation index-radiometric temperature relationship. Remote. Sens. Environ. 2003 , 85 , 429–440. [ Google Scholar ] [ CrossRef ]
• Merlin, O.; Al Bitar, A.; Walker, J.P.; Kerr, Y. An improved algorithm for disaggregating microwave-derived soil moisture based on red, near-infrared and thermal-infrared data. Remote. Sens. Environ. 2010 , 114 , 2305–2316. [ Google Scholar ] [ CrossRef ]
• Merlin, O.; Rudiger, C.; Al Bitar, A.; Richaume, P.; Walker, J.P.; Kerr, Y.H. Disaggregation of SMOS soil moisture in Southeastern Australia. IEEE Trans. Geosci. Remote. Sens. 2012 , 50 , 1556–1571. [ Google Scholar ] [ CrossRef ]
• Chen, Q.; Cheng, Q.; Wang, J.; Du, M.; Zhou, L.; Liu, Y. Identification and evaluation of urban construction waste with vhr remote sensing using multi-feature analysis and a hierarchical segmentation method. Remote. Sens. 2021 , 13 , 158. [ Google Scholar ] [ CrossRef ]
• Elamin, A.; El-Rabbany, A. UAV-Based Multi-Sensor Data Fusion for Urban Land Cover Mapping Using a Deep Convolutional Neural Network. Remote. Sens. 2022 , 14 , 4298. [ Google Scholar ] [ CrossRef ]
• Niu, L.; Xu, G.; Kaufmann, H.; Li, X. An advanced algorithm for fusing Gaofen multispectral satellite data with drone imagery. Int. J. Remote. Sens. 2022 , 43 , 3163–3189. [ Google Scholar ] [ CrossRef ]
• Bouguettaya, A.; Zarzour, H.; Kechida, A.; Taberkit, A.M. Deep learning techniques to classify agricultural crops through UAV imagery: A review. Neural Comput. Appl. 2022 , 34 , 9511–9536. [ Google Scholar ] [ CrossRef ]
• Althobaiti, A.; Alotaibi, A.A.; Abdel-Khalek, S.; Alsuhibany, S.A.; Mansour, R.F. Intelligent Deep Data Analytics Based Remote Sensing Scene Classification Model. Comput. Mater. Contin. 2022 , 72 , 1921–1938. [ Google Scholar ] [ CrossRef ]
• de Barros, B.M.; Barbosa, D.G.; Hackmann, C.L. Spectral Analysis of Marine Debris in Simulated and Observed Sentinel-2/MSI Images using Unsupervised Classification. arXiv 2023 , arXiv:2306.15008. [ Google Scholar ]
• Papale, L.G.; Guerrisi, G.; De Santis, D.; Schiavon, G.; Del Frate, F. Satellite Data Potentialities in Solid Waste Landfill Monitoring: Review and Case Studies. Sensors 2023 , 23 , 3917. [ Google Scholar ] [ CrossRef ]
• Gao, S.; Liu, Y.; Cao, S.; Chen, Q.; Du, M.; Zhang, D.; Jia, J.; Zou, W. IUNet-IF: Identification of construction waste using unmanned aerial vehicle remote sensing and multi-layer deep learning methods. Int. J. Remote. Sens. 2022 , 43 , 7181–7212. [ Google Scholar ] [ CrossRef ]
• Park, Y.; Guldmann, J.-M.; Liu, D. Impacts of tree and building shades on the urban heat island: Combining remote sensing, 3D digital city and spatial regression approaches. Comput. Environ. Urban Syst. 2021 , 88 , 101655. [ Google Scholar ] [ CrossRef ]
• Butcher, B.; Walton, G.; Kromer, R.; Gonzales, E.; Ticona, J.; Minaya, A. High-Temporal-Resolution Rock Slope Monitoring Using Terrestrial Structure-from-Motion Photogrammetry in an Application with Spatial Resolution Limitations. Remote. Sens. 2023 , 16 , 66. [ Google Scholar ] [ CrossRef ]
• le Maire, G.; Dupuy, S.; Nouvellon, Y.; Loos, R.A.; Hakamada, R. Mapping t-rotation plantations at regional scale using MODIS time series: Case of eucalypt plantations in Brazil. Remote. Sens. Environ. 2014 , 152 , 136–149. [ Google Scholar ] [ CrossRef ]
• Sun, R.; Chen, S.; Su, H.; Mi, C.; Jin, N. The Effect of NDVI Time Series Density Derived from Spatiotemporal Fusion of Multisource Remote Sensing Data on Crop Classification Accuracy. ISPRS Int. J. Geo-Inf. 2019 , 8 , 502. [ Google Scholar ] [ CrossRef ]
• Zhang, X.; Zhang, J.; Tian, Y.; Li, Z.; Zhang, Y.; Xu, L.; Wang, S. Urban geological 3d modeling based on papery borehole log. ISPRS Int. J. Geo-Inf. 2020 , 9 , 389. [ Google Scholar ] [ CrossRef ]
• Kadhim, N.; Mourshed, M. A shadow-overlapping algorithm for estimating building heights from VHR satellite images. IEEE Geosci. Remote Sens. Lett. 2018 , 15 , 8–12. [ Google Scholar ] [ CrossRef ]
• Prabhakar, D.; Garg, P.K. Automatic shadow detection for high-resolution remote sensing data. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci.—ISPRS Arch. 2022 , XLVIII-4/W5-2022 , 143–150. [ Google Scholar ] [ CrossRef ]
• Han, H.; Han, C.; Lan, T.; Huang, L.; Hu, C.; Xue, X. Automatic shadow detection for multispectral satellite remote sensing images in invariant color spaces. Appl. Sci. 2020 , 10 , 6467. [ Google Scholar ] [ CrossRef ]
• Mostafa, Y.; Nady, B. Study on shadow detection from high-resolution satellite images using color model. Sohag Eng. J. 2021 , 1 , 85–95. [ Google Scholar ] [ CrossRef ]
• Selvaraju, S.; Jancy, P.L.; Kumar, D.V.; Prabha, R.; Karthikeyan, C.; Babu, D.V. Support Vector Machine based Remote Sensing using Satellite Data Image. In Proceedings of the 2021 2nd International Conference on Smart Electronics and Communication, Trichy, India, 7–9 October 2021; IEEE: Piscataway, NJ, USA, 2021. [ Google Scholar ]
• Liasis, G.; Stavrou, S. Satellite images analysis for shadow detection and building height estimation. ISPRS J. Photogramm. Remote Sens. 2016 , 119 , 437–450. [ Google Scholar ] [ CrossRef ]
• Liu, X.; Yang, F.; Wei, H.; Gao, M. Shadow Removal from UAV Images Based on Color and Texture Equalization Compensation of Local Homogeneous Regions. Remote. Sens. 2022 , 14 , 2616. [ Google Scholar ] [ CrossRef ]
• Xie, Y.; Feng, D.; Xiong, S.; Zhu, J.; Liu, Y. Multi-scene building height estimation method based on shadow in high resolution imagery. Remote. Sens. 2021 , 13 , 2862. [ Google Scholar ] [ CrossRef ]
• Yu, K.; Chen, Y.; Wang, D.; Chen, Z.; Gong, A.; Li, J. Study of the seasonal effect of building shadows on urban land surface temperatures based on remote sensing data. Remote. Sens. 2019 , 11 , 497. [ Google Scholar ] [ CrossRef ]
• Dong, X.; Cao, J.; Zhao, W. A review of research on remote sensing images shadow detection and application to building extraction. Eur. J. Remote. Sens. 2023 , 57 , 2293163. [ Google Scholar ] [ CrossRef ]
• He, Y.; Ma, W.; Ma, Z.; Fu, W.; Chen, C.; Yang, C.-F.; Liu, Z. Using Unmanned aerial vehicle remote sensing and a monitoring information system to enhance the management of unauthorized structures. Appl. Sci. 2019 , 9 , 4954. [ Google Scholar ] [ CrossRef ]
• Bassier, M.; Vermandere, J.; De Winter, H. Linked building data for construction site monitoring: A test CASE. ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci. 2022 , V-2-2022 , 159–165. [ Google Scholar ] [ CrossRef ]
• Liang, H.; Lee, S.-C.; Bae, W.; Kim, J.; Seo, S. Towards UAVs in Construction: Advancements, Challenges, and Future Directions for Monitoring and Inspection. Drones 2023 , 7 , 20. [ Google Scholar ] [ CrossRef ]
• Guan, S.; Zhu, Z.; Wang, G. A Review on UAV-Based Remote Sensing Technologies for Construction and Civil Applications. Drones 2022 , 6 , 117. [ Google Scholar ] [ CrossRef ]
• Albeaino, G.; Gheisari, M. Trends, benefits, and barriers of unmanned aerial systems in the construction industry: A survey study in the United States. J. Inf. Technol. Constr. 2021 , 26 , 84–111. [ Google Scholar ] [ CrossRef ]
• Ashrapov, I.; Malakhov, D.; Marchenkov, A.; Lulin, A.; El-Ayyass, D. Automatic satellite building construction monitoring. arXiv 2022 , arXiv:2209.15084. [ Google Scholar ] [ CrossRef ]
• Zhang, S. Assessing the Utility of Nighttime Light Satellite Imagery for Adjusting Cost Estimate by Project Location. Master’s Thesis, The University of New Mexico, Albuquerque, NM, USA, 2016. Available online: https://digitalrepository.unm.edu/geog_etds/30/ (accessed on 10 May 2024).
• olde Scholtenhuis, L.L.; Doree, A.; Hartmann, T. Challenges for Construction IT adoption on Project Level. In Proceedings of the 27th Annual ARCOM Conference 2011, Bristol, UK, 5–7 September 2011; Association of Researchers in Construction Management (ARCOM): Bristol, UK, 2011; pp. 443–452. [ Google Scholar ]
• Hammad, A.W.A.; da Costa, B.B.F.; Soares, C.A.P.; Haddad, A.N. The use of unmanned aerial vehicles for dynamic site layout planning in large-scale construction projects. Buildings 2021 , 11 , 602. [ Google Scholar ] [ CrossRef ]
• Zhou, S.; Gheisari, M. Unmanned aerial system applications in construction: A systematic review. Constr. Innov. 2018 , 18 , 453–468. [ Google Scholar ] [ CrossRef ]
• Tahar, K.N. Efficiency and cost comparison of UAV/Field survey. In Proceedings of the 2015 International Conference on Space Science and Communication (IconSpace), Langkawi, Malaysia, 10–12 August 2015. [ Google Scholar ]
• Venkatachalam, K.; Manoharan, H.; Kumar, J.S.; Reddy, P.; Sugumaran, R.; Raja, M. An effective construction monitoring system using sensor centered technologies. Int. J. Syst. Assur. Eng. Manag. 2021 . [ Google Scholar ] [ CrossRef ]
• Cheng, J.X. Application of Remote Sensing Technology in Ecological Engineering—A Case Study of Phase I Tao River Water Diversion Project. E3S Web Conf. 2021 , 276 , 01033. [ Google Scholar ] [ CrossRef ]
• Qiu, T.; Lu, F.C.; Zhang, J.J.; Wang, R. Monitoring of soil erosion caused by construction projects using remote sensing images. IOP Conf. Ser. Earth Environ. Sci. 2021 , 626 , 012023. [ Google Scholar ] [ CrossRef ]
• Wang, C.; Shi, W.; Lv, H. Construction of Remote Sensing Indices Knowledge Graph (RSIKG) Based on Semantic Hierarchical Graph. Remote. Sens. 2024 , 16 , 158. [ Google Scholar ] [ CrossRef ]
• Kang, S.; Park, M.-W.; Suh, W. Feasibility study of the unmanned-aerial-vehicle radio-frequency identification system for localizing construction materials on large-scale open sites. Sens. Mater. 2019 , 31 , 1449–1465. [ Google Scholar ] [ CrossRef ]
• Won, D.; Chi, S.; Park, M.-W. UAV-RFID Integration for Construction Resource Localization. KSCE J. Civ. Eng. 2020 , 24 , 1683–1695. [ Google Scholar ] [ CrossRef ]
• Yu, M. Standardization Construction of Fire Information Communication Operation and Management Based on Remote Communication. J. Phys. Conf. Ser. 2020 , 1570 , 012048. [ Google Scholar ] [ CrossRef ]
• Mehata, K.M.; Shankar, S.K.; Karthikeyan, N.; Nandhinee, K.; Hedwig, P.R. IoT Based Safety and Health Monitoring for Construction Workers. In Proceedings of the 2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT), Chennai, India, 25–26 April 2019. [ Google Scholar ]
• Rey-Merchán, M.D.C.; Delgado-Fernández, V.J.; López-Arquillos, A. Barriers to the Integration of IoT Safety Devices in Construction Environments. In Proceedings of the International Conference on Industrial Engineering and Industrial Management, Toledo, Spain, 7–8 July 2022; Springer International Publishing: Cham, Switzerland; pp. 191–196. [ Google Scholar ]
• Okonkwo, C.; Awolusi, I.; Nnaji, C. Privacy and security in the use of wearable internet of things for construction safety and health monitoring. IOP Conf. Ser. Earth Environ. Sci. 2022 , 1101 , 092004. [ Google Scholar ] [ CrossRef ]
• IJeelani, I.; Gheisari, M. Safety challenges of UAV integration in construction: Conceptual analysis and future research roadmap. Saf. Sci. 2021 , 144 , 105473. [ Google Scholar ] [ CrossRef ]

Click here to enlarge figure

Share and Cite

Almohsen, A.S. Challenges Facing the Use of Remote Sensing Technologies in the Construction Industry: A Review. Buildings 2024 , 14 , 2861. https://doi.org/10.3390/buildings14092861

Almohsen AS. Challenges Facing the Use of Remote Sensing Technologies in the Construction Industry: A Review. Buildings . 2024; 14(9):2861. https://doi.org/10.3390/buildings14092861

Almohsen, Abdulmohsen S. 2024. "Challenges Facing the Use of Remote Sensing Technologies in the Construction Industry: A Review" Buildings 14, no. 9: 2861. https://doi.org/10.3390/buildings14092861

Article Metrics

Article access statistics, further information, mdpi initiatives, follow mdpi.

Subscribe to receive issue release notifications and newsletters from MDPI journals

• How to reach us

Select Page

Joint Urban Remote Sensing Event 2025 – Second call for papers

presentation

September 9, 2024.

JURSE 2025, the 17th International Conference on Joint Urban Remote Sensing, organized by Higher School of Communication of Tunis (SUP’COM), invites to explore the future of sustainable development. Marking the first JURSE conference held in Africa, this event brings together leading researchers, practitioners, and policymakers from around the world to exchange ideas, showcase groundbreaking advancements, and navigate the challenges facing our cities.

JURSE 2025 focuses on exploring innovative applications of Joint Urban Remote Sensing and Earth Observation in building resilient and thriving urban centers. The conference delves into cutting-edge research and explores how these technologies can contribute to achieving the UN Sustainable Development Goals (SDGs).

Our Earth Observation Research Cluster (EORC) as well as the Earth Observation Center (EOC) of DLR have contributed to this conference for a long time – with papers, presentations as well as organization. Together with Prof. Kuffer from ITC Enschede, Dr. Stokes from NASA, Dr. Clement Mallet from IGN our professor Hannes Taubenböck is chair of this conference.

Please find more details here:  https://2025.ieee-jurse.org/

you may also like:

Master Defense: Comparing the suitability of remote sensing and wildlife camera time series for deriving phenological metrics of understory vegetation in temperate forests of Upper Franconia, Bavaria

On September 18, Sarah Schneider will present her master thesis "Comparing the suitability of remote sensing and wildlife camera time series for deriving phenological metrics of understory vegetation in temperate forests of Upper Franconia, Bavaria" at 14:00 in...

Master Defense: Regionalisation and Characterisation of Grasslands in the EU based on Remote Sensing Data

On September 17, Daniel Gruschwitz will present his master thesis " Detection of hedgerows and copses in the agricultural landscape of Lower Franconia (Germany) using earth observation data" at 13:30 in seminar room 3, John-Skilton-Str. 4a. From the abstract: In the...

New publication on “A road map for future data-driven urban planning and environmental health research”

New publication on “A road map for future data-driven urban planning and environmental health research”   On 24 and 25 October, 2023 the Urban Burden of Disease Policy workshop on Cities, form, environmental exposures and health impacts took place in Sitges,...

EORC contributions to a RiskKAN webinar

The RiskKAN Network on Emergent Risks and Extreme Events of the Future Earth, IRDR, WCRP, and WWRP programs, is having a webinar on 26th of Sept, 13-15:00 CET/Berlin time. The webinar is titled "Integrating critical infrastructure and social vulnerability...

Master Defense: Detection of hedgerows and copses in the agricultural landscape of Lower Franconia (Germany) using earth observation data

On September 17, Verena Stegmaier will presenter her master thesis " Detection of hedgerows and copses in the agricultural landscape of Lower Franconia (Germany) using earth observation data" at 12:30 in seminar room 3, John-Skilton-Str. 4a. From the abstract:...

Visiting scientist Dr. Ji Zhao

  Dr. Ji Zhao is joining the Earth Observation Research Cluster as a visiting scientist for one year.   After obtaining his PhD in Photogrammetry and Remote Sensing from Wuhan University, China, he worked as an associate professor at China University of...

A new approach for estimating plant growth and determining water requirement using remote sensing

• Original Paper
• Published: 10 September 2024

Cite this article

• A. A. Baradaran   ORCID: orcid.org/0000-0003-2472-3732 1 &
• M. S. Tavazoei 1  

Due to different climatic conditions and the high cost of devices, monitoring plant growth is complex and costly. Remote sensing of agricultural lands on a large scale using satellite imagery is more appropriate than hardware equipment such as sensors. One of the main challenges in plant growth is the rate of plant evapotranspiration discussed in the FAO-56 paper. The rate of plant evapotranspiration in the initial, development, and late growth stages is an important issue. Factors such as irrigation method, surface albedo, height above sea level, aerodynamic conditions, leaf and stomata, and soil texture are main to review plant growth from placement to harvest. In this research using Landsat 8 satellite imagery and vegetation indices, we present an approach in which exist several important indicators for sensing plant growth, determining soil texture and moisture, land slope, and improving cloud effects. The water required by the plant at different stages of growth and the equations in the FAO-56 paper estimate and improve using these indices. We have used cubic spline interpolation, Pearson correlation coefficient, explanation coefficient (R 2 ), Root Mean Square Error (RMSE), Mean Absolute Deviation (MAD), and the Mean Standard Error (MSE) to evaluate and compare the accuracy of each index. Finally, the correlation equation of each index is calculated with its actual values. We have also used hypothesis and regression analysis testing to prove efficiency and predict crop behavior.

The results show that the proposed approach by evaluating spatial and temporal data in different climates leads to greater efficiency and crop. The study can consider important parameters in precision agriculture to achieve efficiency, productivity, quality, profitability, and sustainability of crops.

Graphical Abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save.

• Get 10 units per month
• Download Article/Chapter or eBook
• 1 Unit = 1 Article or 1 Chapter
• Cancel anytime

Price includes VAT (Russian Federation)

Instant access to the full article PDF.

Rent this article via DeepDyve

Institutional subscriptions

Similar content being viewed by others

Retrieval of Crop Biophysical Parameters Using Remote Sensing

Assessing how irrigation practices and soil moisture affect crop growth through monitoring Sentinel-1 and Sentinel-2 data

Analysis of vegetation dynamics using remote sensing and GIS: a case study of Madhya Pradesh, India

Explore related subjects.

• Environmental Chemistry

Data availability

The datasets generated during and/or analyzed during the current study are available from the corresponding author on reasonable request.

Abu El-Magd S et al (2023) Environmental hazard assessment and monitoring for air pollution using machine learning and remote sensing. Int J Environ Sci Technol 20(6):6103–6116

Article   Google Scholar  

Adjei F et al (2023) Evaluation of potential evapotranspiration assessment methods for hydrological modelling with SWAT in the Densu river basin in Ghana. Int J Environ Sci Technol 20(1):921–930

Article   CAS   Google Scholar  

Allen RG et al (1998) Crop evapotranspiration-Guidelines for computing crop water requirements. FAO Irrigation Drainage Paper 56:D05109

Google Scholar  

Allen RG et al (1998) Rome: food and agriculture organization of the united national. FAO Irrigation Drainage Paper 56(97):e156

Bajwa AA et al (2020) Impact of climate change on biology and management of wheat pests. Crop Protect 137:105304

Baltas EA (2007) Impact of climate change on the hydrological regime and water resources in the basin of Siatista. Water Resour Develop 23(3):501–518

Campos I et al (2018) Remote sensing-based crop biomass with water or light-driven crop growth models in wheat commercial fields. Field Crop Res 216:175–188

Chen L et al (2021) Disclosing the future food security risk of China based on crop production and water scarcity under diverse socioeconomic and climate scenarios. Sci Total Environ 790:148110

Chikwanha OC et al (2021) Impact of water scarcity on dryland sheep meat production and quality: key recovery and resilience strategies. J Arid Environ 190:104511

Darvishzadeh R et al (2008) Estimation of vegetation LAI from hyperspectral reflectance data: effects of soil type and plant architecture. Int J Appl Earth Obs Geoinf 10(3):358–373

Dingre S, Gorantiwar S (2021) Soil moisture based deficit irrigation management for sugarcane (Saccharum officinarum L.) in semiarid environment. Agri Water Manage 245:106549

Fabre S et al (2015) Estimation of soil moisture content from the spectral reflectance of bare soils in the 0.4–2.5 µm domain. Sensors 15(2):3262–3281

Fernandes FHS et al (2018) Degradation trends based on MODIS-derived estimates of productivity and water use efficiency: a case study for the cultivated pastures in the Brazilian Cerrado. Remote Sensing Appli: Society Environ 11:30–40

Gao Z et al (2013) A method of estimating soil moisture based on the linear decomposition of mixture pixels. Math Comput Model 58(3–4):606–613

Hong M et al (2021) Application of high-resolution meteorological data from NCAM-WRF to characterize agricultural drought in small-scale farmlands based on soil moisture deficit. Agric Water Manag 243:106494

Hristov J et al (2021) Reuse of treated water in European agriculture: potential to address water scarcity under climate change. Agric Water Manag 251:106872

Idso SB (1981) A set of equations for full spectrum and 8-to 14-μm and 10.5-to 12.5 μm thermal radiation from cloudless skies. Water Resour Res 17(2):295–304

Kumar A et al (2021) Salt-tolerant plant growth-promoting Bacillus pumilus strain JPVS11 to enhance plant growth attributes of rice and improve soil health under salinity stress. Microbiol Res 242:126616

Lee R (1978) Forest microclimatology. Columbia University Press

Li Z, Tan D (2013) The second modified perpendicular drought index (mpdi1): a combined drought monitoring method with soil moisture and vegetation index. J Indian Society Remote Sensing 41(4):873–881

Li B et al (2016) Estimating soil moisture with Landsat data and its application in extracting the spatial distribution of winter flooded paddies. Remote Sensing 8(1):38

Li B-B et al (2021) Deep soil moisture limits the sustainable vegetation restoration in arid and semi-arid Loess Plateau. Geoderma 399:115122

Luo S et al (2019) Combining hyperspectral imagery and LiDAR pseudo-waveform for predicting crop LAI, canopy height and above-ground biomass. Ecol Ind 102:801–812

Ma Y et al (2018) Estimation of daily evapotranspiration and irrigation water efficiency at a Landsat-like scale for an arid irrigation area using multi-source remote sensing data. Remote Sens Environ 216:715–734

Macfarlane C et al (2017) A standardised Landsat time series (1973–2016) of forest leaf area index using pseudoinvariant features and spectral vegetation index isolines and a catchment hydrology application. Remote Sensing Appli: Society Environ 6:1–14

Matsuda M et al (2001) Estimation of plant growth in rice field based on remote sensing. IFAC Proceed Volumes 34(28):95–100

Matthias A et al (1990) Aerodynamic parameters for a sparsely roughened surface composed of small cotton plants and ridged soil. Remote Sens Environ 32(2–3):143–153

Mika J et al (2001) Impact of documented land use changes on the surface albedo and evapotranspiration in a plain watershed. Phys Chem Earth Part B 26(7–8):601–606

Oke TR (2002) Boundary layer climates. Routledge

Book   Google Scholar  

Petitcolin F, Vermote E (2002) Land surface reflectance, emissivity and temperature from MODIS middle and thermal infrared data. Remote Sens Environ 83(1–2):112–134

Rane N, Jayaraj G (2022) Enhancing SWAT model predictivity using multi-objective calibration: effects of integrating remotely sensed evapotranspiration and leaf area index. Int J Environ Sci Technol 20:1–20

Riihelä A et al (2013) CLARA-SAL: a global 28 yr timeseries of earth’s black-sky surface albedo. Atmos Chem Phys 13(7):3743–3762

Robinson P (2009) Sellers, WD 1965: physical climatology. Chicago: University of Chicago Press, 272 pp. Prog Phys Geogr 33(1):130–132

Rosenberg NJ et al (1983) Microclimate: the biological environment. John Wiley & Sons

Rosenburg N et al (1974) Microclimate: the biological environment. John Wiley and Sons, New York

Schwager P, Berg C (2021) Remote sensing variables improve species distribution models for alpine plant species. Basic Appl Ecol 54:1–13

Tasumi, M. (2003). Progress in operational estimation of regional evapotranspiration using satellite imagery, University of Idaho.

Taylor P et al (1996) RE (Ted) Munn: Founding editor; a mini-biography. Bound-Layer Meteorol 78(1):3–8

Van Wijk WR (1964) Physics of plant environment. Soil Sci 98(1):69

Wang Q et al (2018) Sediment control and fodder yield increase in alfalfa (Medicago sativa L) production with tied-ridge-furrow rainwater harvesting on sloping land. Field Crop Res 225:55–63

Wang Y et al (2020) Alfalfa canopy water interception under low-pressure sprinklers. Agric Water Manag 230:105919

Wang, J. (2000). Relations between productivity, climate, and Normalized Difference Vegetation Index in the central Great Plains, University of Kansas.

Weiss M et al (2020) Remote sensing for agricultural applications: a meta-review. Remote Sens Environ 236:111402

Xiao Y et al (2015) Effects of alternate furrow irrigation on the biomass and quality of alfalfa (Medicago sativa). Agric Water Manag 161:147–154

Xu, M., et al. (2014). Automatic cloud removal for Landsat 8 OLI images using cirrus band. 2014 IEEE Geoscience and Remote Sensing Symposium, IEEE.

Zohdi E, Abbaspour M (2019) Harmful algal blooms (red tide): a review of causes, impacts and approaches to monitoring and prediction. Int J Environ Sci TeChnol 16:1789–1806

Download references

Acknowledgements

We acknowledge the technical and financial support provided by the Iran National Science Foundation (INSF) for project No.99021526.

Author information

Authors and affiliations.

Department of Electrical Engineering, Sharif University of Technology, Tehran, Iran

A. A. Baradaran & M. S. Tavazoei

You can also search for this author in PubMed   Google Scholar

Contributions

Amir Abbas Baradaran: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Resources, Data Curation, Writing—Original Draft, Visualization, Project administration, Mohammad Saleh Tavazoei: Supervision, Writing—Original Draft, Writing—Review & Editing, Project administration, Resources, Data Curation, Methodology, analysis.

Corresponding author

Correspondence to A. A. Baradaran .

Ethics declarations

Conflicts of interest.

All authors declare that they have no conflict of interest or financial conflicts to disclose in the outcome of this study.

Ethical approval

This chapter does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Editorial responsibility: S.Mirkia.

Appendix A: Range of variables (R and NIR values are in micrometers)

NDVI index in Landsat 8 satellite is between − 1 and 1. This index is less than 1 for water and wet regions, between 0 and 0.3 for dry or barren lands, and greater than 0.3 for agricultural lands with suitable vegetation. This index is one or close to one for lands with high vegetation cover. Therefore:

If \(NDVI \le 1\) :

If \(NDVI \ge 1\) :

For non-agricultural land:

According to the above relationship, the minimum and maximum NIR are R and 0.18R , respectively.

According to Eqs. ( 4 ) to ( 6 ):

By setting the minimum value of NIR in \({\text{L}}_{{{\text{SAVI}}}}\) :

By setting the maximum value of NIR in \({\text{L}}_{{{\text{SAVI}}}}\) :

Factor s is the slope of the soil line. With the change of vegetation, the value of s also changes. In other words, the s factor changes over time. Therefore, by deriving the above equation and solving the derivative equation, and inserting it into the first equation, the maximum value of \(L_{SAVI}\) is obtained:

Therefore, the range of L is equal to:

Based on the range of L , NSAVI and NLAI are as follows:

Appendix B: Modifying and updating parameters according to cloudy days for pixel 16.

Table 18 shows all observed farmland values for Pixel 16 that cloudy days marked in red. The values have been collected at 16-day intervals according to Landsat 8 satellite imagery (first line).

The first step of the update is performed on day 17. Because it is the first overcast day, and the observed values should be converted to actual values by cubic spline interpolation (Table  19 ).

Tables 20 , 21 , 22 , 23 , 24 , 25 , 26 and 27 show the continuation of the update steps, respectively.

In the tenth step, the LAI value is more than 7. So, the algorithm stops (see Lemma 1 ).

Appendix C: Z-table

Appendix D: t-student table

Appendix E: CDI values for the overcast area in Fig.  12

Appendix F: CDI values for the partly cloudy area in Fig.  14

Appendix G: Research flowchart and graphical abstract

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Baradaran, A.A., Tavazoei, M.S. A new approach for estimating plant growth and determining water requirement using remote sensing. Int. J. Environ. Sci. Technol. (2024). https://doi.org/10.1007/s13762-024-06020-w

Download citation

Received : 09 August 2022

Revised : 06 June 2024

Accepted : 19 August 2024

Published : 10 September 2024

DOI : https://doi.org/10.1007/s13762-024-06020-w

Share this article

Anyone you share the following link with will be able to read this content:

Sorry, a shareable link is not currently available for this article.

Provided by the Springer Nature SharedIt content-sharing initiative

• Remote sensing
• Leaf area index
• Plant growth
• Find a journal
• Publish with us
• Track your research