Poster: WiFi sensors meet visual tracking for an accurate positioning system

In this poster abstract, we propose a new positioning technique that can localize people by combining WiFi information from their mobile devices with visual tracking. We show that the proposed approach can improve visual tracking by resolving motion and appearance ambiguities while at the same time can uniquely identify each person with their device ID.

[1]  Wen Hu,et al.  Efficient background subtraction for real-time tracking in embedded camera networks , 2012, SenSys '12.

[2]  David A. McAllester,et al.  Object Detection with Discriminatively Trained Part Based Models , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).