Abstract
Image change detection is one of the important application branches of remote sensing technology in many fields. However, in complex environments, remote sensing image change detection is often subject to various interferences, resulting in low accuracy and poor real-time performance of detection results. The research focuses on the advantages and problems of residual networks and depth-wise separable convolution modules, designs a new remote sensing image change detection model, and finally sets up experiments for verification. The average accuracy of the proposed detection model before and after training convergence was 0.54 and 0.97. The accuracy of repeated detection ranged from 95.82% to 99.68%, and the area under curve of the model was 0.90. However, after removing the integrated residual attention unit and depth-wise separable convolution, the accuracy decreased by 1.91% and the latency increased by 117ms. In addition, the detection efficiency of the model for different elements ranged from 0.91 to 0.94, with high accuracy in detecting changes in spatial and temporal scales and small offsets. The actual accuracy and mean latency time of the model were 92.43% and 260ms, respectively. In summary, the proposed change detection model significantly improves the accuracy and real-time performance of remote sensing image processing, contributing to the expanded application of remote sensing dynamic detection technology in fields such as ocean monitoring and ecological research.