Multi-target tracking identification system under multi-camera surveillance system

Abstract

Intelligent video surveillance system has an important role in group behavior analysis. In the literature, several multi-tracking identification systems have been proposed to detect the group behavior through determining motion trajectory of the individual pedestrian. In this paper, a matrix based temporal recursive positional identification method is extended to determine and track the trajectory of each person including the person who newly enters into or exits from the observation region. The surveillance area is divided into different observation zones and each zone has one camera which detects the presence of each person. Given the geometrical structure of the observation zone, the topological relation, represented by a matrix, is established. The extended matrix-based algorithm first divides the topological relation into three sub-relations which represent the potential movements of newly entering-into-zone, exiting-from-zone, and moving-between-zones persons. Different methods are used to determine their motion trajectories. Experimental results conclude the effectiveness and correctness of the extended algorithm.