Towards a practical PTZ face detection and tracking system

• Published in: 2013 IEEE Workshop on Applications of Computer Vision (WACV) pp. 31 - 38
• Main Authors: Yinghao Cai, Medioni, G., Thang Ba Dinh
• Format: Conference Proceeding Journal Article
• Language: English
• Published: IEEE 01.01.2013
• Subjects: Automation; Cameras; Computer vision; Dynamical systems; Dynamics; Face; Face detection; Face recognition; Image color analysis; Networks; Real-time systems; Target tracking; Trajectory; Workshops
• ISBN: 9781467350532; 1467350532
• ISSN: 1550-5790; 2642-9381; 1550-5790
• DOI: 10.1109/WACV.2013.6474996

We address the problem of automatic face detection and tracking in uncontrolled scenarios using a pan-tilt-zoom (PTZ) network camera, which could prove most helpful in forensic applications. The detected faces are associated with the corresponding people and trajectories. The dynamic nature of real-world scenarios and real-time restrictions complicate our task. Different from previous work which use a mixture of wide angle cameras and PTZ cameras, we explore the limits to what can be expected from a single PTZ camera. The system first detects and tracks pedestrians in zoomed-out mode, then selects, using a scheduler, a person to zoom in to. After zoom in, we come back to wide area mode, and solve the person-to-person, face-to-person and face-to-face data association problems. Extensive experiments in challenging indoor and outdoor uncontrolled conditions demonstrate the effectiveness of the proposed system.