587
Electronic Engineering and Information Science – Wang (Ed.)
© 2015 Taylor & Francis Group, London, ISBN: 978-1-138-02772-5
Robust online multi-object identifying and tracking
J. Su, G.S. Yin & Z.Y. Luo
Department College of Computer Science and Technology, Harbin Engineering University, China
ABSTRACT: In order to realize multiple target identifying and tracking in complex scenes, a robust online
identifying and tracking method is proposed, which is implemented on a novel Bayesian tracking model by
using the ability of managing multi-modal distributions. The association between tracked targets and detections
need not to be explicitly computed in this model. First, accurately identify multi-targets whose number is com-
pletely unknown by using ...