Carrying object detection using adaptive centroid star skeleton

Abstract

Detecting a carried object is a primary step for surveillance applications which is useful to recognize and monitor threats, and prevent criminal activity in order to maintain social control. Thus, this thesis aims to detect a carried object seen from a stationary camera using human body silhouette feature information. Star skeletonization technique with the adaptive centroid point is used to extract human feature. The carried object is classified using time series of motions of the extracted skeleton limbs. The boundary of the carried object is figured from carried objects track points and adjacent sink curves of contour. The method is able to detect and track carried object such as a luggage and a backpack. Moreover, the detection of leaving luggage event could be achieved. In the research, some data from TRECVID dataset and manually captured data are used to perform experiments.