Image Change Detection Method based on RPCA and Low-rank Decomposition

Detecting changes in images of the same scene at different stages is of widespread interest in diverse disciplines, including medical diagnosis, remote sensing and so on. This paper presents a new change detection method based on robust Principle Component Analysis (RPCA). The considered couple of temporal images is expanded into an image serial through linear interpolation. The illumination variations are reduced by combining the local and global illumination correction method together. The image serial is concatenated into a low-rank image matrix and the change part is given by the sparse component through decomposing the image matrix. The proposed method is of lower complexity and higher effectiveness compared to the conventional image differecing, and it is more robust to noise and the registration error. Extensive experimental results are made from synthetic data, clinical medical and remote sensing data.