Persistent People Tracking and Face Capture Over a Wide Area

Gerard Medioni, Yinghao Cai; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2014, pp. 700-701

Persistent people tracking over a wide area is important for many applications and has received much attention in recent years. For real-time and forensic applications, it is very helpful to capture the facial images of people tracked. In this paper, we address the problem of people tracking and face capture over a wide area. First, we propose a people tracking and face capture system using a single PTZ camera. The availability of high resolution facial images opens up new opportunities for further biometric analysis. Then, we present a new solution to persistent people tracking across multiple cameras with non-overlapping fields of view. The development of these methods should provide new insights into long-term people tracking over a wide area.