Residual Unet for Urban Building Change Detection with Sentinel-1 SAR Data

Urban building change detection is one of the most important parts of remote sensing applications. Researching change detection method based on deep learning is an effective solution to monitor the urban expansion and recognize the specific change classes. In this paper, we propose a novel urban building change detection method based on the revised residual Unet with Sentinel-1 SAR intensity images. Firstly, we present a new difference image by combing both the original intensity image and the enhanced log-ratio difference image using a non-linear function. Then, the combined difference image is sent to a revised residual Unet network to detect the building changes. By the proposed combined difference image and the revised network, our method is able to focus on the building’s change while ignoring other land type changes in a large area. A pair of real bitemporal SAR images is used to test the proposed approach and the obtained experimental results confirm its effectiveness.

[1]  Yafei Wang,et al.  Spatiotemporal Fuzzy Clustering Strategy for Urban Expansion Monitoring Based on Time Series of Pixel-Level Optical and SAR Images , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[2]  Avik Bhattacharya,et al.  Urban classification using PolSAR data and deep learning , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[3]  Yu Cao,et al.  A Neighborhood-Based Ratio Approach for Change Detection in SAR Images , 2012, IEEE Geoscience and Remote Sensing Letters.

[4]  Maoguo Gong,et al.  Feature learning and change feature classification based on deep learning for ternary change detection in SAR images , 2017 .

[5]  Hong Zhang,et al.  Urban Building Change Detection in SAR Images Using Combined Differential Image and Residual U-Net Network , 2019, Remote. Sens..

[6]  Yuanwei Jin,et al.  Change detection by deep neural networks for synthetic aperture radar images , 2017, 2017 International Conference on Computing, Networking and Communications (ICNC).

[7]  Qingjie Liu,et al.  Road Extraction by Deep Residual U-Net , 2017, IEEE Geoscience and Remote Sensing Letters.

[8]  Francesca Bovolo,et al.  A novel change detection framework based on deep learning for the analysis of multi-temporal polarimetric SAR images , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[9]  Yang Yu,et al.  An improved neighborhood-based ratio approach for change detection in SAR images , 2018 .