A PROBABILISTIC FRAMEWORK FOR SEGMENTATION AND TRACKING OF MULTIPLE NON RIGID OBJECTS FOR VIDEO SURVEILLANCE (MA-P4)

Author(s) : Aleksandar Ivanovic (Beckman Institute for Advanced Science and Technology, University of Illinois, USA) Thomas S. Huang (Beckman Institute for Advanced Science and Technology, University of Illinois, USA)

Abstract : This paper presents a probabilistic framework for segmenting and tracking foreground objects for video surveillance, using a static monocular camera. The algorithm combines information in a probabilistic sense and poses the problem of matching the segmented foreground objects with blobs in the next frame as a non bipartite matching problem. To solve the problem, we assign a probability to each possible matching. A way to improve the detection of new objects is briefly described. The new framework is shown to be able to handle a greater set of difficult situations and to signifi- cantly improve performance.

Menu