Dual View Interactive Network And Viewpoint Error Validation Method For Off-Nadir Images Change Detection

• Published in: IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium pp. 8777 - 8781
• Main Authors: Wei, Jinjiang, Sun, Kaimin, Li, Wenzhuo, Li, Wangbin, Gao, Song, Tan, Yingjiao, Miao, Shunxia, Cui, Wei
• Format: Conference Proceeding
• Language: English
• Published: IEEE 07.07.2024
• Subjects: attention mechanism; Attention mechanisms; Buildings; Change detection; Computational efficiency; Correlation; deep learning; Feature extraction; remote sensing; Semantics; Sensors
• ISSN: 2153-7003
• DOI: 10.1109/IGARSS53475.2024.10642596

Change Detection (CD) in remote sensing imagery is a valuable technique to identify urban expansion and anomalies on the Earth's surface. However, the viewpoint difference between bi-temporal images often leads to significant view-point errors, resulting in false detection. Off-nadir datasets and global attention mechanisms have been commonly used to address this issue, but their effectiveness is challenging to validate. To tackle these challenges, we propose a novel Dual View Interactive Network (DVINet) specifically designed for CD in off-nadir images. Our approach incorporates the Viewpoint Interactive Attention Mechanism (VIM), which computes semantic correlations among dual view features extracted by the encoder to establish feature correspondences. In addition, we pioneer a viewpoint error validation method by evaluating the performance of CD in building facade regions. Experimental results on two off-nadir datasets, BANDON and S2Looking, show that DVINet achieves 70.65% and 66.26% F1, respectively, outperforming six mainstream methods in terms of CD performance.