Journals Information
Computer Science and Information Technology Vol. 3(5), pp. 159 - 170
DOI: 10.13189/csit.2015.030502
Reprint (PDF) (1341Kb)
Particle-filter Multi-target Tracking Algorithm Based on Dynamic Salient Features
Zhang Yan *, Shi Zhi-guang , LI Ji-Cheng , Yang Wei-ping
ATR lab, National University of Defense Technology, Changsha, China
ABSTRACT
In order to address the problem of tracking different moving targets in image sequence against a complicated background, this paper presents a particle-filter multi-target tracking algorithm based on their dynamic salient features. By making use of the research findings on visual attention, the algorithm adopts the robust dynamic salient features as a result of combining the gray-scale and details with the motion characteristics of such targets as the state vector of particle filter. The algorithm is highly robust as it contains salient features originating from the low-level features of the targets. Meanwhile the particle filter allows optimized estimation of non-linear and non-Gaussian models. As a consequence, the algorithm is capable of managing traces in tracking different targets and dealing with their appearance, disappearance, mergence, splitting and sheltering by obstacles. Experiments show that this new algorithm enables tracking of multiple targets in complicated image sequence.
KEYWORDS
Salience, Target Feature, Particle-filter, Multi-target Tracking
Cite This Paper in IEEE or APA Citation Styles
(a). IEEE Format:
[1] Zhang Yan , Shi Zhi-guang , LI Ji-Cheng , Yang Wei-ping , "Particle-filter Multi-target Tracking Algorithm Based on Dynamic Salient Features," Computer Science and Information Technology, Vol. 3, No. 5, pp. 159 - 170, 2015. DOI: 10.13189/csit.2015.030502.
(b). APA Format:
Zhang Yan , Shi Zhi-guang , LI Ji-Cheng , Yang Wei-ping (2015). Particle-filter Multi-target Tracking Algorithm Based on Dynamic Salient Features. Computer Science and Information Technology, 3(5), 159 - 170. DOI: 10.13189/csit.2015.030502.