Abandoned object detection using multi-layer motion detection
Simon Denman, Sridha Sridharan, Vinod Chandran · QUT ePrints (Queensland University of Technology) · 2008
Abandoned object detection (AOD) systems are re-quired to run in high traffic situations, with high levels of occlusion. Systems rely on background segmentation techniques to locate abandoned objects, by detecting ar-eas of motion that have stopped. This is often achieved by using a medium term motion detection routine to detect long term changes in the background. When AOD systems are integrated into person tracking sys-tem, this often results in two separate motion detectors being used to handle the different requirements. We propose a motion detection system that is capable of de-tecting medium term motion as well as regular motion. Multiple layers of medium term (static) motion can be detected and segmented. We demonstrate the perfor-mance of this motion detection system and as part of an abandoned object detection system. 1