An Experimental Framework for Evaluating PTZ Tracking Algorithms

PTZ (Pan-Tilt-Zoom) cameras are powerful devices in video surveillance applications, because they offer both wide area coverage and highly detailed images in a single device. Tracking with a PTZ camera is a closed loop procedure that involves computer vision algorithms and control strategies, both crucial in developing an effective working system. In this work, we propose a novel experimental framework that allows to evaluate image tracking algorithms in controlled and repeatable scenarios, combining the PTZ camera with a calibrated projector screen on which we can play different tracking situations. We applied such setup to compare two different tracking algorithms, a kernel-based (mean-shift) tracking and a particle filter, opportunely tuned to fit with a PTZ camera. As shown in the experiments, our system allows to finely investigate pros and cons of each algorithm.