Active people tracking by a PTZ camera in IP surveillance system

In this paper, we propose a fuzzy feature-based method for online body tracking using an IP PTZ camera. Because the camera uses a built-in Web server, camera control entails response time and network delays, and thus, the frame rate is irregular and generally low (3-7 fps). Our method has been designed specifically to perform in such conditions. It detects in every frame, candidate targets by extracting moving targets using optical flow, a sampling method, and appearance. The target is detected among samples using a fuzzy classifier. Results show that our system has a good target detection precision (> 93%), and low track fragmentation.