Browse > Article
http://dx.doi.org/10.7780/kjrs.2020.36.5.2.7

Analysis of Change Detection Results by UNet++ Models According to the Characteristics of Loss Function  

Jeong, Mila (Department of Civil Engineering, Chungbuk National University)
Choi, Hoseong (Department of Civil Engineering, Chungbuk National University)
Choi, Jaewan (Department of Civil Engineering, Chungbuk National University)
Publication Information
Korean Journal of Remote Sensing / v.36, no.5_2, 2020 , pp. 929-937 More about this Journal
Abstract
In this manuscript, the UNet++ model, which is one of the representative deep learning techniques for semantic segmentation, was used to detect changes in temporal satellite images. To analyze the learning results according to various loss functions, we evaluated the change detection results using trained UNet++ models by binary cross entropy and the Jaccard coefficient. In addition, the learning results of the deep learning model were analyzed compared to existing pixel-based change detection algorithms by using WorldView-3 images. In the experiment, it was confirmed that the performance of the deep learning model could be determined depending on the characteristics of the loss function, but it showed better results compared to the existing techniques.
Keywords
Deep learning; Change detection; UNet++; Loss function; Training data;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Badrinarayanan, V., A. Kendall, and R. Cipolla, 2017. SegNet: A deep convolutional encoder-decoder architecture for image segmentation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12): 2481-2495.   DOI
2 Fang, B., L. Pan, and R. Kou, 2019. Dual learningbased siamese framework for change detection using bi-temporal VHR optical remote sensing image, Remote Sensing, 11(11): 1292.   DOI
3 Hou, B., Q. Liu, H. Wang, and Y. Wang, 2020. From W-Net to CDGAN: Bitemporal change detection vis deep learning techniques, IEEE Transactions on Geoscience and Remote Sensing, 58(3): 1790-1802.   DOI
4 Lee, S., H. Yoo, and M. Kim, 2011. Requirements analysis on the acquisition and sharing of land-monitoring data, Seoul Studies, 12(3): 185-201.
5 Zhan, Y., K. Fu, M. Yan, X. Sun, H .Wang, and X. Qiu, 2017. Change detection based on deep siamese convolutional network for optical aerial images, IEEE Geoscience and Remote Sensing Letters, 14(10): 1845-1849.   DOI
6 Li, L., C. Wang, H. Zhang, B. Zhang, and F. Wu, 2019. Urban building change detection in SAR images using combined differential image and residual U-Net network, Remote Sensing, 11(9): 1091.   DOI
7 Liu, J., K. Chen, G. Xu, X. Sun, M. Yan, W. Diao, and H. Han, 2020. Convolutional neural network-based transfer learning for optical aerial images change detection, IEEE Geoscience and Remote Sensing Letters, 17(1): 127-131.   DOI
8 Lu, D., P. Mausel, E. Brondizio, and E. Moran, 2004. Change detection techniques, International Journal of Remote Sensing, 25(12): 2365-2401.   DOI
9 Lu, D., G. Li, and E. Moran, 2014. Current situation and needs of change detection techniques, International Journal of Image and Data Fusion, 5(1): 13-38.   DOI
10 Peng, D., Y. Zhang, and H. Guan, 2019. End-to-end change detection for high resolution satellite images using improved UNet++, Remote Sensing, 11(11): 1382.   DOI
11 Zhang, W. and X. Lu, 2019. The spectral-spatial joint learning for change detection in multispectral imagery, Remote Sensing, 11(3): 240.   DOI
12 Zhou, Z., M.M.R. Siddiquee, N. Tajbakhsh, and J. Liang, 2018. Unet++: A nested u-net architecture for medical image segmentation. In Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer, Cham, pp. 3-11.