Visual Object Servo Tracking Based on the Particle Filter Method Using a Pan-Tilt-Zoom Camera

Abstract

We present a servo control model in a particle filter to realize robust visual object tracking using Pan-Tilt-Zoom (PTZ) camera. The particle filter method has attracted much attention due to its robust tracking performance in cluttered environments. However, most methods are in the mode of moving object and stationary camera, as a result, the tracking will end in failure if the object goes out of the field of view of the camera. In this paper, a closed-loop control model based on speed regulation is proposed to drive the PTZ camera to keep the target at the centre of the camera angle. The experiment results show that our system can track the moving object well and can always keep the object in the middle of the field of view. The system is computationally efficient and can run in real-time completely.