Activity perception for smart video surveillance systems

This paper presents a novel framework for activities perception in video surveillance scenarios. Firstly, moving objects are detected by modeling the background using Gaussian Mixture Model (GMM). Secondly, a novel adaptive particle filter (APF) is introduced. The proposed APF has time-varying dimensions and can track multiple moving objects entering or leaving the field of view effectively. Finally, object trajectories are classified by predefined rules for activity analysis. Experimental results demonstrate the robustness and effectiveness of our method.