A Method for Monitoring Activities of Multiple Objects by Using Stochastic Model

We present a method for estimating activities of multiple objects which are detected in video surveillance systems. In most existing video surveillance systems , the objects detection and classification sometimes cause inaccurate results. In addition to this, we want to monitor activities of objects including interactions between them for long term image sequence. To solve this problem, we newly introduce pre-defined knowledge that each blob has attributes set which consists of object's type, action, and interaction. Using probabilistic relations introduced by a specific Markov model of these attributes sets , the activity descriptions are estimated accurately .