Multiple People Tracking Using Camera Networks with Overlapping Views

Abstract

We present a novel framework for multiple pedestrian tracking using overlapping cameras in which the problems of object detection and data association are solved alternately. In each round of our algorithm, the people are detected by inference on a factor graph model at each time slice. The outputs of the inference, namely, the probabilistic occupancy maps, are used to define a cost network model. Data association is achieved by solving a min-cost flow problem on the resulting network model. The outputs of the data association, namely, the ground occupancy maps, are used to control the size of factors in graph model in the next round. By alternating between object detection and data association, a desirable compromise between complexity and accuracy is obtained. Experiments results on public datasets demonstrate the competitiveness of our method compared with other state-ofthe-art approaches.

Abnormal Event Detection via Multikernel Learning for Distributed Camera Networks

“…In the literature [2, 3], the framework for multiple pedestrian tracking by using overlapping cameras was presented. In [4], several major challenges in distributed video processing, including robust and computationally efficient inference and opportunistic and parsimonious sensing, were discussed.…”