Iterative Edge Enhancing Framework for Building Change Detection

Shuai Song, Yuanlin Zhang, Yuan Yuan

Abstract: The building change detection (BCD) task serves urban planning by monitoring land use. However, due to the complexity of remote-sensing images and high foreground–background similarity, it leads to inaccurate detection of building edge regions. Existing methods deal with this problem by fusing features of different layers. But the fusing operation cannot separate details information from the overall information of buildings, resulting in inaccurate detection of building edge area. To address the above challenges, we propose an iterative edge-enhancing framework (IEEF). The IEEF alleviates the building edge detection difficulty by densely implementing a detail semantic enhancement module (DSEM) in the decoding part. This module takes differential features between adjacent scales to explicitly represent the building edge information. Simultaneously, to deal with the class imbalance problem, a Density-Guided Sampling method dedicated to change detection is proposed to increase the proportion of positive samples during training. Our proposed method achieves state-of-the-art performance on the LEarning, VIsion and Remote sensing laboratory building Change Detection (LEVIR-CD) dataset and the Wuhan University (WHU) dataset and obtains accurate changed building edges.

External IDs:doi:10.1109/lgrs.2023.3247882