Discriminant random field and patch-based redundancy analysis for image change detection

To develop better image change detection algorithms, new models able to capture all the spatio-temporal regularities and geometries seen in an image pair are needed. In contrast to the usual pixel-wise methods, we propose a patch-based formulation for modeling semi-local interactions and detecting occlusions and other local or regional changes in an image pair. To this end, the image redundancy property is exploited to detect unusual spatio-temporal patterns in the scene. We first define adaptive detectors of changes between two given image patches and combine locally in space and scale such detectors. The resulting score at a given location is exploited within a discriminant Markov random field (DRF) whose global optimization flags out changes with no optical flow computation. Experimental results on several applications demonstrate that the method performs well at detecting occlusions and meaningful regional changes and is especially robust in the case of low signal-to-noise ratios.