Browse > Article
http://dx.doi.org/10.9717/kmms.2022.25.2.206

Comparative Study of Deep Learning Model for Semantic Segmentation of Water System in SAR Images of KOMPSAT-5  

Kim, Min-Ji (Major of AI, Dept. of Information Convergence Engineering, Pusan National University)
Kim, Seung Kyu (Major of AI, Dept. of Information Convergence Engineering, Pusan National University)
Lee, DoHoon (School of Computer Science and Engineering, Pusan National University)
Gahm, Jin Kyu (School of Computer Science and Engineering, Pusan National University)
Publication Information
Journal of Korea Multimedia Society / v.25, no.2, 2022 , pp. 206-214 More about this Journal
Abstract
The way to measure the extent of damage from floods and droughts is to identify changes in the extent of water systems. In order to effectively grasp this at a glance, satellite images are used. KOMPSAT-5 uses Synthetic Aperture Radar (SAR) to capture images regardless of weather conditions such as clouds and rain. In this paper, various deep learning models are applied to perform semantic segmentation of the water system in this SAR image and the performance is compared. The models used are U-net, V-Net, U2-Net, UNet 3+, PSPNet, Deeplab-V3, Deeplab-V3+ and PAN. In addition, performance comparison was performed when the data was augmented by applying elastic deformation to the existing SAR image dataset. As a result, without data augmentation, U-Net was the best with IoU of 97.25% and pixel accuracy of 98.53%. In case of data augmentation, Deeplab-V3 showed IoU of 95.15% and V-Net showed the best pixel accuracy of 96.86%.
Keywords
Semantic Segmentation; Deep Learning Model; Water System; Synthetic Aperture Radar; KOMPSAT-5;
Citations & Related Records
연도 인용수 순위
  • Reference
1 S. Kwon, Y. Kim, and G. Kim, "An Automatic Breast Mass Segmentation based on Deep Learning on Mammogram," Journal of Korea Multimedia Society, Vol. 21, No. 12, pp. 1363-1369, 2018.   DOI
2 M.A. Rahman and Y. Wang, "Optimizing Intersection-Over-Union in Deep Neural Netwoirks for Image Segmentation," International Symposium on Visual Computing, pp. 234-244, 2016.
3 L. Chen, G. Papandreou, F. Schroff, and H. Ada, "Rethinking Atrous Convolution for Semantic Image Segmentation," arXiv P reprint, arXiv:1706.05587, 2017.
4 J. Wang, K. Sun, T. Cheng, B. Jiang, C. Deng, and Y. Zhao et al., "Deep High-Resolution Representation Learning for Visual Recognition," IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 43, No. 10, pp. 3349-3364, 2021.   DOI
5 H. Lee, H. Yoon, and H. Han, "A Study on the Determination of Indicator for the Rist Assesment of Ground Depression Using SAR Image," Journal of the Korean Geo-Environmental Society, Vol. 22, No. 7, pp. 13-20, 2021.
6 O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," International Conference on Medical Image Computing and Computer-Assisted Invervention, pp. 234-241, 2015.
7 F. Milletari, N. Navab, and S.A. Ahmadi. "V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation," Fourth International Conference on 3D Vision, pp. 565-571, 2016.
8 X. Qin, Z. Zhang, C. Huang, M. Dehghan, O. R. Zaiane, and M. Jagersand, "U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection," Pattern Recognition, Vol 106, p. 107404, 2020.   DOI
9 L.C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, "Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation," Proceedings of the European Conference on Computer Vision, pp 801-818, 2018.
10 H. Li, P. Xiong, J. An, and L. Wang, "Pyramid Attention Network for Semantic Segmentation," arXiv P reprint, arXiv:1805. 10180, 2018.
11 H. Zhao, J. Shi, X. Qi, X. Wang, and J. Jia, "Pyramid Scene Parsing Network," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881- 2890, 2017.
12 D.P. Kingma and J.L. Ba, "Adam: A Method for Stochastic Optimization," arXiv P reprint, arXiv:1412.6980, 2014.
13 G. Wang, M. Wu, X. Wei, and H. Song, "Water Identfication from High-Resolution Remote Sensing Images Based on Multidimensional Densely Connected Convolutional Neural Networks," Remote Sensing, Vol. 12, No. 5, pp. 795, 2020.   DOI
14 H. Huimin, L. Lin, R. Tong, H. Hu, Q. Zhang, and Y. Iwamoto et al., "Unet 3+: A Full-Scale Connected Unet for Medical Image Segmentation," IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1055-1059, 2020.
15 E. Castro, J.S. Cardoso, and J.C. Pereira, "Elastic Deformations for Data Augmentation in Breast Cancer Mass Detection," IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), pp. 230-234, 2018.
16 H. Kwon, S. Jeong, S. Kim, J. Lee, and K. Sohm, "Deep-Learning based SAR Ship Detection with Generative Data Augmentation," Journal of Korea Multimedia Society, Vol. 25, No. 1, pp. 1-9, 2022.   DOI
17 M.Y. Kim, C.Y. Choi, S.H. Han, S.J. Lee, and O. Han, "Deep Learning based Water Segmentation of KOMPSAT-5 SAR Images," The Korean Society for Aeronautical and Space Sciences, pp. 131-132, 2020.
18 NDMI, "Prospects of Future Disasters in Our Country through Scenarios," Future Safety Issue, Vol. 18, pp. 1-41, 2021.