Précédent|Prochain

Water identification from the GF-1 satellite image based on the deep convolutional neural networks

  • role： First author第一作者
  • Affiliation：

    School of Geographic Science, Nanjing University of Information Science and Technology, Nanjing 210044, China

  • Email：gwang@nuist.edu.cn
  • Introduction：王国杰， 研究方向为陆面过程遥感与建模。E-mail： gwang@nuist.edu.cn
WANG Guojie1,  
  • Affiliation：

    School of Geographic Science, Nanjing University of Information Science and Technology, Nanjing 210044, China

HU Yifan1,  
  • Affiliation：

    School of Geographic Science, Nanjing University of Information Science and Technology, Nanjing 210044, China

ZHANG Sen1,  
  • Affiliation：

    School of Remote Sensing & Geomatics Engineering, Nanjing University of Information Science and Technology, Nanjing 210044, China

RU Yi2,  
  • Affiliation：

    School of Geographic Science, Nanjing University of Information Science and Technology, Nanjing 210044, China

CHEN Kainan1,  
  • Affiliation：

    School of Geographic Science, Nanjing University of Information Science and Technology, Nanjing 210044, China

WU Mengjuan1

résumé

Rapid and accurate identification of water bodies from remote sensing images is of great significance to water resources management and flood disaster monitoring. At present, traditional methods for identifying water bodies from satellite images still have shortcomings, and sometimes the results are not accurate enough to meet the practical needs. Recently, the Convolutional Neural Network (CNN) methods have emerged and been rapidly developed, providing a new idea for a identifying water bodies from satellite images. In this work, the Densely Connected Deep Convolutional Neural Network (DenseNet) is used to identify water bodies in the Hongze Lake area, together with the ResNet, VGG, HRNet networks, and the traditional method of Normalized Difference Water Index (NDWI). We have added the upsampling process and the skip connection structure to its classical structure to improve the performance of the DenseNet network. These methods are applied to the GF-1 satellite images of the Hongze Lake area to identify the water bodies in different seasons. Experiments are conducted to determine the optimal parameters of DenseNet, ResNet, VGG, and HRNet networks for water body identification. Moreover, the OSTU method is used to determine the optimal threshold of NDWI to reduce the uncertainty of threshold determination. Several indices of precision (P), recall (R), F1 score, and misclassification rate (MRate) are used to evaluate the performance of these methods. The main conclusions we have reached are as follows: (1) All the CNN models of ResNet, VGG, HRNet, and DenseNet have significantly outperformed the traditional NDWI method; for example, the precision (P) of water identification by using the NDWI method is only 0.779 compared with ground truth; however, it is highly improved to >0.922 by utilizing the CNN models. (2) The modified DenseNet model has effectively alleviated the problems of gradient explosion and disappearance, and the water body identification result is much better than the other CNN models, e.g., with the best P (0.960) and MRate (0.041). The training efficiency of the modified DenseNet model also appears far better than that of the other CNN models with the shorted training time, and the lowest loss function. (3) The modified DenseNet model shows also a better capability in identifying the fine features of water bodies, even if their shapes and water colors change largely in different seasons. These results have indicated that the CNN models are good tools for identifying water bodies from satellite images, and the modified DenseNet model appears to be the most promising one among them.

mots-clés

satellite images;Water Identification;normalized difference water index;convolutional neural network

References

  1. 1.
    Bengio Y. 2012. Practical recommendations for gradient-based training of deep architectures//Montavon G, Orr G B, Müller K R eds.Neural Networks: Tricks of the Trade. Berlin, Heidelberg: Springer, 437-478
  2. 2.
    Bi H Y, Wang S Y, Zeng J Y, Zhao Y, Wang H and Yin H. 2012. Comparison and analysis of several common water extraction methods based on TM image. Remote Sensing Information, 27(5): 77-82
  3. 3.
    Cortes C and Vapnik V. 1995. Support-vector networks. Machine Learning, 20(3): 273-297
  4. 4.
    Feyisa G L, Meilby H, Fensholt R and Proud S R. 2014. Automated water extraction index: a new technique for surface water mapping using Landsat imagery. Remote Sensing of Environment, 140(1): 23-35
  5. 5.
    Fu D and Yue J P. 2019. Hongze Lake water surface area based on Landsat image and its change analysis. Journal of Gansu Sciences, 31(2): 35-39
  6. 6.
    He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE: 770-778
  7. 7.
    Hinton G E, Osindero S and Teh Y W. 2006. A fast learning algorithm for deep belief nets. Neural Computation, 18(7): 1527-1554
  8. 8.
    Huang G, Liu Z, Van Der Maaten L and Weinberger K Q. 2017. Densely connected convolutional network//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu: IEEE: 2261-2269
  9. 9.
    Kou D L, Quan J C and Zhang Z W. 2019. Research on progress of object detection framework based on deep learning. Computer Engineering and Applications, 55(11): 25-34
  10. 10.
    Krizhevsky A, Sutskever I and Hinton G E. 2017. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6): 84-90
  11. 11.
    Liu W B, Wang Z D, Liu X H, Zeng N Y, Liu Y R and Alsaadi F E. 2017. A survey of deep neural network architectures and their applications. Neurocomputing, 234: 11-26
  12. 12.
    Lu H T and Zhang Q C. 2016. Applications of Deep Convolutional Neural Network in Computer Vision. Journal of Data Acquisition and Processing, 31(1): 1-17
  13. 13.
    McFeeters S K. 1996. The use of the normalized difference water index (NDWI) in the delineation of open water features. International Journal of Remote Sensing, 17(7): 1425-1432
  14. 14.
    Mei H P, Wang Z L, Liu M, Zhou J M. 2021. Characteristic Water Levels of Hongze Lake in the Past Five Decades:Variation Rules and Influencing Factors. Journal of Yangtze River Scientific Research Institute, 38(1): 35-40
  15. 15.
    Otsu N. 1979. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man, and Cybernetics, 9(1): 62-66
  16. 16.
    Qu J Y, Sun X and Gao X. 2016. Remote sensing image target recognition based on CNN. Foreign Electronic Measurement Technology, 35(8): 45-50
  17. 17.
    Saito S, Yamashita T and Aoki Y. 2016. Multiple object extraction from aerial imagery with convolutional neural networks. Electronic Imaging, 60(1): 1-9
  18. 18.
    Simonyan K and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition//Proceedings of the 3rd International Conference on Learning Representations. San Diego: ICLR: 1-14
  19. 19.
    Sheng Y W, Xiao Q G, Chen W Y. 1994. Application of FY-1B Meteorological Satellite Data to Monitor the Flood Disaster in Huaihe River Basin in Summer, 1991. Journal of Remote Sensing, 9(3): 228-233
  20. 20.
    Stehman S V. 1997. Selecting and interpreting measures of thematic classification accuracy. Remote Sensing of Environment, 62(1): 77-89
  21. 21.
    Wang G J, Wu M J, Wei X K and Song H H. 2020a. Water identification from high-resolution remote sensing images based on multidimensional densely connected convolutional neural networks. Remote Sensing, 12(5): 795
  22. 22.
    Wang J D, Sun K, Cheng T H, Jiang B R, Deng C R, Zhao Y, Liu D, Mu Y D, Tan M K, Wang X G, Liu W Y and Xiao B. 2020b. Deep high-resolution representation learning for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(10): 3349-3364
  23. 23.
    Wang X, Sui L C, Zhong M Q, Li D M and Dang L L. 2018. Fully convolution neural networks for water extraction of remote sensing images. Bulletin of Surveying and Mapping, (6): 41-45
  24. 24.
    Wang Z H. 1992. Application of remote sensing techniques to the study of geological disaster. Journal of Remote Sensing, 7(3): 190-195
  25. 25.
    Xu H Q. 2005. A study on information extraction of water body with the modified normalized difference water index (MNDWI). Journal of Remote Sensing, 9(5): 589-595
  26. 26.
    Xu H Q. 2006. Modification of normalised difference water index (NDWI) to enhance open water features in remotely sensed imagery. International Journal of Remote Sensing, 27(14): 3025-3033
  27. 27.
    Yang W L, Yang M H and Qi H X. 2012. Water body extracting from TM image based on BPNN. Science of Surveying and Mapping, 37(1): 148-150
  28. 28.
    Yin B C, Wang W T and Wang L C. 2015. A review of deep learning. Journal of Beijing University of Technology, 41(1): 48-59
  29. 29.
    Yin Y Q, Li J G, Yu T, Yang H Y and Zhang Y H. 2015. The Study of Object-oriented Water Body Extraction Method Based on High Resolution RS Image. Bulletin of Surveying and Mapping, (1): 81-85
  30. 30.
    Yue Y, Gong J and Wang D. 2010. The extraction of water information based on SPOT5 image using object-oriented method//2010 18th International Conference on Geoinformatics. Beijing: IEEE: 1-5
  31. 31.
    Zhang B, Li J S, Shen Q, Wu Y H, Zhang F F, Wang S L, Yao Y, Guo L N and Yin Z Y. 2021. Recent research progress on long time series and large scale optical remote sensing of inland water. National Remote Sensing Bulletin, 25(1): 37-52
  32. 32.
    Zheng Y P, Li G Y and Li Y. 2019. Survey of application of deep learning in image recognition. Computer Engineering and Applications, 55(12): 20-36
  33. 33.
    Zhou F Y, Jin L P and Dong J. 2017. Review of convolutional neural network. Chinese Journal of Computers, 40(6): 1229-1251
  34. 34.
    Zhu C M, Luo J C, Shen Z F and Li J L. 2013. River linear water adaptive auto-extraction on remote sensing image aided by DEM. Acta Geodaetica et Cartographica Sinica, 42(2): 277-283

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website