Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.5.2.11

Water Segmentation Based on Morphologic and Edge-enhanced U-Net Using Sentinel-1 SAR Images  

Kim, Hwisong (School of Earth and Environmental Sciences, Seoul National University)
Kim, Duk-jin (School of Earth and Environmental Sciences, Seoul National University)
Kim, Junwoo (Future Innovation Institute, Seoul National University)
Publication Information
Korean Journal of Remote Sensing / v.38, no.5_2, 2022 , pp. 793-810 More about this Journal
Abstract
Synthetic Aperture Radar (SAR) is considered to be suitable for near real-time inundation monitoring. The distinctly different intensity between water and land makes it adequate for waterbody detection, but the intrinsic speckle noise and variable intensity of SAR images decrease the accuracy of waterbody detection. In this study, we suggest two modules, named 'morphology module' and 'edge-enhanced module', which are the combinations of pooling layers and convolutional layers, improving the accuracy of waterbody detection. The morphology module is composed of min-pooling layers and max-pooling layers, which shows the effect of morphological transformation. The edge-enhanced module is composed of convolution layers, which has the fixed weights of the traditional edge detection algorithm. After comparing the accuracy of various versions of each module for U-Net, we found that the optimal combination is the case that the morphology module of min-pooling and successive layers of min-pooling and max-pooling, and the edge-enhanced module of Scharr filter were the inputs of conv9. This morphologic and edge-enhanced U-Net improved the F1-score by 9.81% than the original U-Net. Qualitative inspection showed that our model has capability of detecting small-sized waterbody and detailed edge of water, which are the distinct advancement of the model presented in this research, compared to the original U-Net.
Keywords
Synthetic aperture radar (SAR); Deep learning; Convolutional neural network (CNN); Water detection; Morphology transformation; Edge detection;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Long, J., E. Shelhamer, and T. Darrell, 2015. Fully convolutional networks for semantic segmentation, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, Jun. 7-12, pp. 3431-3440. https://doi.org/10.1109/CVPR.2015.7298965   DOI
2 Miranda, N., P.J. Meadows, D. Type, and T. Note, 2015. Radiometric calibration of S-1 Level-1 products generated by the S-1 IPF, https://sentinel.esa.int/documents/247904/685163/S1-RadiometricCalibr ation-V1.0.Pdf, Accessed on Sep. 26, 2022.
3 Shrivakshan, G.T. and C. Chandrasekar, 2012. A comparison of various edge detection techniques used in image processing, International Journal of Computer Science Issues (IJCSI), 9(5): 269-276. http://dx.doi.org/10.14257/ijsip.2016.9.2.13   DOI
4 Vernon, D., 1991. Machine vision, Prentice Hall, Hoboken, NJ, USA, p. 143.
5 Wu, L., L. Wang, L. Min, W. Hou, Z. Guo, J. Zhao, and N. Li, 2018. Discrimination of algal-bloom using spaceborne SAR observations of Great Lakes in China, Remote Sensing, 10(5): 767. https://doi.org/10.3390/rs10050767   DOI
6 Kim, B., K.H. Choi, and J.S. Won, 1998. Efficient Speckle Noise Filtering of Sar Images, Journal of Astronomy and Space Sciences, 15(1): 175-183 (in Korean with English abstract).
7 Abraham, N. and N.M. Khan, 2019. A novel focal tversky loss function with improved attention unet for lesion segmentation, Proc. of 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italy, Apr. 8-11, pp. 683-687. https://doi.org/10.1109/ISBI.2019.8759329   DOI
8 Bai, Y., W. Wu, Z. Yang, J. Yu, B. Zhao, X. Liu, H. Yang, E. Mas, and S. Koshimura, 2021. Enhancement of detecting permanent water and temporary water in flood disasters by fusing sentinel-1 and sentinel-2 imagery using deep learning algorithms: Demonstration of sen1floods11 benchmark datasets, Remote Sensing, 13(11): 2220. https://doi.org/10.3390/rs13112220   DOI
9 Guo, Z., L. Wu, Y. Huang, Z. Guo, J. Zhao, and N. Li, 2022. Water-Body Segmentation for SAR Images: Past, Current, and Future, Remote Sensing, 14(7):1752. https://doi.org/10.3390/rs14071752   DOI
10 Jadon, S., 2020. A survey of loss functions for semantic segmentation, Proc. of 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Via del Mar, Chile, Oct. 27-29, pp. 1-7. https://doi.org/10.1109/CIBCB48159.2020.9277638   DOI
11 Li, J., C. Wang, L. Xu, F. Wu, H. Zhang, and B. Zhang, 2021. Multitemporal water extraction of dongting lake and poyang lake based on an automatic water extraction and dynamic monitoring framework, Remote Sensing, 13(5): 865. https://doi.org/10.3390/rs13050865   DOI
12 Liu, Y., L. Li, Y. Xie, L. Chen, and Y. Deng, 2015. An optimized water detection algorithm for SAR images utilizing SOPC technologies, Proc. of IET International Radar Conference 2015, Hangzhou, China, Oct. 14-16, pp. 1-4. https://doi.org/10.1049/cp.2015.1396   DOI
13 Kim, J., H. Kim, H. Jeon, S.H. Jeong, J. Song, S.K.P. Vadivel, and D.J. Kim, 2021. Synergistic Use of Geospatial Data for Water Body Extraction from Sentinel-1 Images for Operational Flood Monitoring across Southeast Asia Using Deep Neural Networks, Remote Sensing, 13(23): 4759. https://doi.org/10.3390/rs13234759   DOI
14 Denbina, M., Z.J. Towfic, M. Thill, B. Bue, N. Kasraee, A. Peacock, and Y. Lou, 2020. Flood mapping using UAVSAR and convolutional neural networks, Proc. of IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, Waikoloa, HI, USA, Sep. 26-Oct. 2, pp. 3247-3250. https://doi.org/10.1109/IGARSS39084.2020.9324379   DOI
15 Dong, Z., G. Wang, S.O.Y. Amankwah, X. Wei, Y. Hu, and A. Feng, 2021. Monitoring the summer flooding in the Poyang Lake area of China in 2020 based on Sentinel-1 data and multiple convolutional neural networks, International Journal of Applied Earth Observation and Geoinformation, 102: 102400. https://doi.org/10.1016/j.jag.2021.102400   DOI
16 Hajduch, G. and N. Miranda, 2018. Masking "no-value" pixels on GRD products generated by the Sentinel1 ESA IPF, https://sentinel.esa.int/documents/247 904/2142675/Sentinel-1-masking-no-value-pixelsgrd-products-note.Pdf, Accessed on Sep. 26, 2022.
17 Jahne, B., H. Scharr, and S. Korkel, 1999. Principles of Filter Design, In: Jahne, B., Haussecker, H., Geissler, P. (eds), Handbook of computer vision and applications, Academic Press, New York, NY, USA, pp. 125-151.
18 Kang, W., Y. Xiang, F. Wang, L. Wan, and H. You, 2018. Flood detection in gaofen-3 SAR images via fully convolutional networks, Sensors, 18(9): 2915. https://doi.org/10.3390/s18092915   DOI
19 Klemenjak, S., B. Waske, S. Valero, and J. Chanussot, 2012. Automatic detection of rivers in highresolution SAR data, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(5): 1364-1372. https://doi.org/10.1109/JSTARS.2012.2189099   DOI
20 Liu, H. and K.C. Jezek, 2004. Automated extraction of coastline from satellite imagery by integrating Canny edge detection and locally adaptive thresholding methods, International Journal of Remote Sensing, 25(5): 937-958. https://doi.org/10.1080/0143116031000139890   DOI
21 Maini, R. and H. Aggarwal, 2009. Study and comparison of various image edge detection techniques, International Journal of Image Processing (IJIP), 3(1): 1-11.
22 Hofle, B., M. Vetter, N. Pfeifer, G. Mandlburger, and J. Stotter, 2009. Water surface mapping from airborne laser scanning using signal intensity and elevation data, Earth Surface Processes and Landforms, 34(12): 1635-1649. https://doi.org/10.1002/esp.1853   DOI
23 Pai, M.M.M., V. Mehrotra, S. Aiyar, U. Verma, and R.M. Pai, 2019. Automatic segmentation of river and land in sar images: A deep learning approach, Proc. of 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), Sardinia, Italy, Jun. 3-5, pp. 15-20. https://doi.org/10.1109/AIKE.2019.00011   DOI
24 White, L., B. Brisco, M. Dabboor, A. Schmitt, and A. Pratt, 2015. A collection of SAR methodologies for monitoring wetlands, Remote Sensing, 7(6): 7615-7645. https://doi.org/10.3390/rs70607615   DOI
25 Silveira, M. and S. Heleno, 2009. Classification of water regions in SAR images using level sets and non-parametric density estimation, Proc. of 2009 16th IEEE International Conference on Image Processing (ICIP), Cairo, Egypt, Nov. 7-10, pp. 1685-1688. https://doi.org/10.1109/ICIP.2009.5413391   DOI
26 Ting, K.M., 2011. Confusion Matrix, In: Sammut, C., Webb, G.I. (eds), Encyclopedia of Machine Learning, Springer, Boston, MA, USA. https://doi.org/10.1007/978-0-387-30164-8_157   DOI
27 Wang, J., Y. Feng, R. Wang, X. Tong, S. Chen, Z. Lei, and M. Xi, 2022. Evaluation of typhoon-induced inundation losses associated with LULC using multi-temporal SAR and optical images, Geomatics, Natural Hazards and Risk, 13(1): 2227-2251. https://doi.org/10.1080/19475705.2022.2112624   DOI
28 Ronneberger, O., P. Fischer, and T. Brox, 2015. U-net: Convolutional networks for biomedical image segmentation, Proc. of International Conference on Medical Image Computing and Computerassisted Intervention, Munich, Germany, Oct. 5-9, pp. 234-241. https://doi.org/10.48550/arXiv.1505.04597   DOI
29 Yuan, K., X. Zhuang, G. Schaefer, J. Feng, L. Guan, and H. Fang, 2021. Deep-learning-based multispectral satellite image segmentation for water body detection, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 7422-7434. https://doi.org/10.1109/JSTARS.2021.3098678   DOI
30 Xie, L., H. Zhang, and C. Wang, 2015. Water-body types classification using Radarsat-2 fully polarimetric SAR data, Proc. of 2015 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES), Bali, Indonesia, Dec. 3-5, pp. 1-5. https://doi.org/10.1109/ICARES.2015.7429816   DOI