Information theoretic sensor management for multi-target tracking with a single pan-tilt-zoom camera

• Published in: IEEE Winter Conference on Applications of Computer Vision pp. 893 - 900
• Main Authors: Salvagnini, Pietro, Pernici, Federico, Cristani, Marco, Lisanti, Giuseppe, Masi, Iacopo, Del Bimbo, Alberto, Murino, Vittorio
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-03-2014
• Subjects: Cameras; Computational modeling; Detectors; Entropy; Estimation; Gaussian distribution; Target tracking
• ISSN: 1550-5790; 2642-9381
• DOI: 10.1109/WACV.2014.6836009

Automatic multiple target tracking with pan-tilt-zoom (PTZ) cameras is a hard task, with few approaches in the literature, most of them proposing simplistic scenarios. In this paper, we present a PTZ camera management framework which lies on information theoretic principles: at each time step, the next camera pose (pan, tilt, focal length) is chosen, according to a policy which ensures maximum information gain. The formulation takes into account occlusions, physical extension of targets, realistic pedestrian detectors and the mechanical constraints of the camera. Convincing comparative results on synthetic data, realistic simulations and the implementation on a real video surveillance camera validate the effectiveness of the proposed method.