Improvement of Person Tracking Accuracy in Camera Network by Fusing WiFi and Visual Information
Person tracking in camera network is still an open subject nowadays. The main challenge for this problem is how to link exactly individual trajectories when people move in a camera FOV (Field of View) or switch to other ones. This refers to solve the problem of person re-identication (Re-ID) in tracking process. A popular method for this is assigning the current position with the previous one based on the minimum distance between them. This is called as person identication by tracking. In this work, we approach tracking by identication, which means the trajectory assignment is done by the person identity (ID) determined at each video frame. In order to improve the accuracy of vision-based person tracking, we focus on accuracy enhancement for person identication by adding ID of the WiFi-enable device held by each person. A fusion scheme of WiFi and visual signals is proposed in this work for person tracking. An optimal assignment and Kalman lter are used in this combination to assign the position observations and predicted states from camera and WiFi systems. The correction step of Kalman lter is then applied for each tracker to give out state estimations of locations. The fusion method allows tracking by identication in non-overlapping cameras, with clear iden tity information taken from WiFi adapter. The experiments on a multi-model dataset show outperforming tracking results of the proposed fusion method in comparison with vision-based only method.
This work is licensed under a Creative Commons Attribution 3.0 License.