Moving Obstacle Removal via Low Rank Decomposition

Obstacle removal is a classic problem in image processing. Because the content behind obstacle can't be deduced only from one image, we introduce a motion obstacle removal problem from an image sequence. It is regarded as a sparse problem with the obstacles as noise. First we match the images with image features to transform the images to the same camera coordinate system. The features of motion objects are not included, which are detected by the big offset of matching features in neighbor images. Then a matrix is constructed with each matched image as column. Without obstacles, each column should be the same. So we decompose the matrix into a low rank matrix and a sparse matrix. According to the low rank we can get the background image without obstacles. Compared to previous methods, the method can restore the background image correctly without any interaction. The experiments show the results are ideal.