Image based object recognition
Image registration has been long used as a basis for the detection of moving objects. In this method spatial information is often ignored, and different motions from multiple moving objects cannot be efficiently modeled. Moreover, image registration is not well suited to handle occlusion that can result in potential object misses. Here proposes a new approach to address these issues. Video frames are first segmented into uniform regions, followed by the construction of RAGs to represent each frame.