Remote sensing image change detection method based on space selection and time sequence evolution

The invention belongs to the technical field of image processing, and discloses a remote sensing image change detection method based on space selection and time sequence evolution, a space and time sequence double-branch encoder structure is constructed, the first branch accurately explores the space positioning of a change area in a double-time image pair, and the second branch accurately explores the space positioning of the change area in the double-time image pair; and the other branch generates a virtual video from the dual-time image through a specific data enhancement method to supplement local details of the change area. According to the method, excellent performance is achieved through a small number of parameters and calculation amount. 本发明属于图像处理技术领域，公开了一种基于空间选择和时序演变的遥感图像变化检测方法，构建了一个空间和时序双分支编码器结构，第一个分支精确地探索了双时图像对中变化区域的空间定位，而另一个分支通过特定的数据增强方法从双时图像生成虚拟视频来补充变化区域的局部细节。本发明方法通过少量的参数和计算量实现了优异性能。