Spatial-temporal consistent labeling of tracked pedestrians across non-overlapping camera views

Abstract

Tracking people across multiple cameras with non-overlapping views is a challenging task, since their observations are separated in time and space and their appearances may vary significantly. This paper proposes a Bayesian model to solve the consistent labeling problem across multiple non-overlapping camera views. Significantly different from related… (More)
DOI: 10.1016/j.patcog.2010.11.011

Topics

27 Figures and Tables

Cite this paper

@article{Lian2011SpatialtemporalCL, title={Spatial-temporal consistent labeling of tracked pedestrians across non-overlapping camera views}, author={Guoyun Lian and Jian-Huang Lai and Wei-Shi Zheng}, journal={Pattern Recognition}, year={2011}, volume={44}, pages={1121-1136} }