A change detection method based on cosegmentation
Zhenlei Xie, Ruoming Shi, Ling Feng Zhu, Peng Shu, Linyuan Li · 2017
A method based on cosegmentation is applied to change detection to segment image patches belonging to each image. The image patches have the characteristics of spatial correspondence in multi-temporal images and precise boundary in its own image. By construction and optimization of energy function that consists of change feature item and image feature item, both of spectrum and shape change can successfully be given the description between different temporal images. The optimal segment results of multi-temporal images are achieved as the energy function reaches its minimum, in this process, the method of min-cut/max-flow will be used.