Cross-Perception and Hierarchical Similarity Metric Network for Remote Sensing Image Change Detection

Change detection (CD) is a fundamental operation in remote sensing image interpretation. This process employs a range of image processing and recognition techniques to identify semantic alterations in the same geographical region across different temporal phases. However, most of existing CD methods rarely utilize the relationship between dual-time phase features. In addition, they tend to overlook the potential benefits of integrating spatial and channel information, which impairs their ability to discern fine details and address pseudochanges. To address these limitations, we propose a cross-perception and hierarchical similarity metric network (CPHSM-Net). The features are first captured using a feature extractor that adds an adaptive spatial channel enhancement (ASCE) strategy to adaptively obtain a more meaningful representation of the features. Then, the relationships between the features of each layer are captured by the cross-perception (CP) module. Finally, the variation feature description is further enhanced by the hierarchical similarity metric (HSM) module, which is designed to capture the variations and differences in the images. The F1 scores obtained by CPHSM-Net in experimental tests on three publicly available datasets (LEVIR-CD, WHU-CD, and DSIFN-CD) were 91.07%, 92.56%, and 65.75%, respectively, which is superior to the state-of-the-art comparison methods.