Salient points for tracking moving objects in video

Detectionandtrackingofmovingobjectsisimportantintheanalysisofvideodata. Oneapproachistomaintain abackgroundmodelofthesceneandsubtractitfromeachframetodetectthemovingobjectswhichcanthenbe trackedusingKalman orparticlefllters. Inthispaper,weconsidersimpletechniquesbasedonsalientpointsto identifymovingobjectswhicharetrackedusingmotioncorrespondence. Wefocusonvideowithalargefleldof view, such as a tra-c intersection with several buildings nearby. Such scenes can contain several salient points, not all of which move between frames. Using public domain video and two types of salient points, we consider how to make these techniques computationally e-cient for detection and tracking. Our early results indicate that salient regions obtained using the Lowe keypoints algorithm and the Scale-Saliency algorithm can be used successfully to track vehicles in moderate resolution video.