A Unified Hierarchical Appearance Model for People Re-identification Using Multi-view Vision Sensors

Authors:
Jau-Hong Kao;Chih-Yang Lin;Wen-How Wang;Yi-Ta Wu
Affiliations:
Advanced Technology Center, Information and Communications Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan 310;Advanced Technology Center, Information and Communications Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan 310;Advanced Technology Center, Information and Communications Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan 310;Advanced Technology Center, Information and Communications Research Laboratories, Industrial Technology Research Institute, Hsinchu, Taiwan 310
Venue:
PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Year:
2008

Citing 5
Cited 0

Learning Patterns of Activity Using Real-Time Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking Across Multiple Cameras With Disjoint Views

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Application of Principal Component Analysis to Multikey Searching

IEEE Transactions on Software Engineering
Detection of loitering individuals in public transportation areas

IEEE Transactions on Intelligent Transportation Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Surveillance of wide areas requires a system of multiple cameras to keep observing people. In such a multiple view system, the people appearance obtained in one camera is usually different from the ones obtained in other cameras. In order to correctly identify people, the unique appearance model of each specific object should be invariant to such changes. In this paper, our appearance model is represented by a hierarchical structure where each node maintains a color Gaussian mixture model (GMM). The re-identification is performed with Bayesian decision. Experimental results show our unified appearance model is robust to rotation and scaling variations. Furthermore, it achieves high accuracy rate (92.7% in average) and high processing performance (above 30 FPS) without tracking mechanism.