A Robust Visual Surveillance System Based on an Omnidirectional Vision Sensor

Abstract

Visual surveillance, object tracking and activity monitoring are some of the important issues for homecare systems. In this work, an omnidirectional video camera is adopted to provide a 360 degree view angle of the indoor scene with a single image sequence. Some basic functions for smart living and elderly care, such as motion detection, object tracking and target behavior analysis, are implemented. For the motion detection, a foreground object model is first detected and the CamShift algorithm is used for object tracking by extracting color information of the target. To make the motion detection and object tracking fully auto-matic and robust under different illumination conditions, an optical flow approach is cooperated to detect small changes of the mobile object. In addition, the camera is calibrated to obtain the one-to-one correspon-dences between the image pixels and the locations on the ground. The information is then combined with the object model for fall detection and abnormal behavior analysis. Experimental results are presented for the real scene images.