Journal Home > Volume 21 , Issue 2
Tsinghua Science and Technology 2016, 21(2): 221-230 https://doi.org/10.1109/TST.2016.7442504
Open Access | Issue | Published: 31 March 2016

Optimization of the Occlusion Strategy in Visual Tracking

Show Author's Information Jinghuan Wen,  Huimin Ma( ),  Xiaoqin Zhang
Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.
Keywords:
particle swarm optimization, virtual tracking, occlusion interference, death process, statistical fitness function
Cite this article:
Wen J, Ma H, Zhang X. Optimization of the Occlusion Strategy in Visual Tracking. Tsinghua Science and Technology, 2016, 21(2): 221-230. https://doi.org/10.1109/TST.2016.7442504
Download citation
EndNote(RIS)
BibTeX

463

Views

13

Downloads

Citations

20

Crossref

N/A

WoS

15

Scopus

0

CSCD

Abstract Full text About this article

Interference and anti-interference are two opposite and important issues in visual tracking. Occlusion interference can disguise the features of a target and can also be used as an effective benchmark to determine whether a tracking algorithm is reliable. In this paper, we proposed an inner Particle Swarm Optimization (PSO) algorithm to locate the optimal occlusion strategy under different tracking conditions and to identify the most effective occlusion positions and direction of movement to allow a target to evade tracking. This algorithm improved the standard PSO process in three ways. First, it introduced a death process, which greatly reduced the time cost of optimization. Second, it used statistical data to determine the fitness value of the particles so that the fitness more accurately described the tracking. Third, the algorithm could avoid being trapped in local optima, as the fitness changes with time. Experimental results showed that this algorithm was able to identify a global optimal occlusion strategy that can disturb the tracking machine with 86.8% probability over more than 10 000 tracking processes. In addition, it reduced the time cost by approximately 80%, compared with conventional PSO algorithms.


menu
Abstract
Full text
Outline
About this article

Optimization of the Occlusion Strategy in Visual Tracking

Show Author's information Jinghuan Wen, Huimin Ma( ), Xiaoqin Zhang
Department of Electronic Engineering, Tsinghua University, Beijing 100084, China.

Abstract

Interference and anti-interference are two opposite and important issues in visual tracking. Occlusion interference can disguise the features of a target and can also be used as an effective benchmark to determine whether a tracking algorithm is reliable. In this paper, we proposed an inner Particle Swarm Optimization (PSO) algorithm to locate the optimal occlusion strategy under different tracking conditions and to identify the most effective occlusion positions and direction of movement to allow a target to evade tracking. This algorithm improved the standard PSO process in three ways. First, it introduced a death process, which greatly reduced the time cost of optimization. Second, it used statistical data to determine the fitness value of the particles so that the fitness more accurately described the tracking. Third, the algorithm could avoid being trapped in local optima, as the fitness changes with time. Experimental results showed that this algorithm was able to identify a global optimal occlusion strategy that can disturb the tracking machine with 86.8% probability over more than 10 000 tracking processes. In addition, it reduced the time cost by approximately 80%, compared with conventional PSO algorithms.

Keywords: particle swarm optimization, virtual tracking, occlusion interference, death process, statistical fitness function

References(16)

[1]
Störmer V. S., Li S. C., Heekeren H. R., and Lindenberger U., Feature-based interference from unattended visual field during attentional tracking in younger and older adults, Journal of Vision, vol. 11, no. 2, pp. 1–12, 2011.
DOI Google Scholar
[2]
Ablavsky V. and Sclaroff S., Layered graphical models for tracking partially-occluded objects, in Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2008, pp. 1758-1775.
DOI
[3]
Vezzani R. and Cucchiara R., Ad-hoc: Appearance driven human tracking with occlusion handling, in First Internat. Workshop Tracking Humans for the Evaluation of Their Motion in Image Sequences (THEMIS’ 2008), 2008, pp. 9-18.
[4]
Greenhill D., Renno J., Orwell J., and Jones G. A., Occlusion analysis: Learning and utilising depth maps in object tracking, Image and Vision Computing, vol. 26, no. 3, pp. 430–441, 2008.
DOI Google Scholar
[5]
Nguyen H. T. and Smeulders A. W. M., Fast occluded object tracking by a robust appearance filter, Transactions on Pattern Analysis and Machine Intelligence, vol. 26, no. 8, pp. 1099–1104, 2004.
DOI Google Scholar
[6]
Liu H., Research of particle swarm optimization algorithm and its application in ship engineering, (in Chinese), PhD dissertation, Harbin Engineering University, China, 2008.
[7]
Soudan B. and Saad M., An evolutionary dynamic population size PSO implementation, in Information and Communication Technologies: From Theory to Applications, 2008, pp. 1-5.
[8]
Kennedy J. and Eberhart R. C., Particle swarm optimization, in Proceedings of IEEE International Conference on Neural Networks, 1995, pp. 1942-1948. .
DOI
[9]
Heppner F. and Grenander U., A stochastic nonlinear model for coordinated bird flocks, in The Ubiquity of Chaos, S. Krasner, Ed. American Association for the Advancement of Science, 1990, pp. 233-238.
[10]
Shi Y. and Eberhart R., A modified particle swarm optimizer, in Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence, The 1998 IEEE International Conference on, 1998, pp. 69-73.
DOI
[11]
Zhu K., Li J., and Baoyin H., Trajectory optimization of the exploration of asteroids using swarm intelligent algorithms, Tsinghua Science and Technology, vol. 14, no. S2, pp. 7–11, 2009.
DOI Google Scholar
[12]
Hu J., Song J., Zhang M., and Kang X., Topology optimization for urban traffic sensor network, Tsinghua Science and Technology, vol. 13, no. 2, pp. 229–236, 2008.
DOI Google Scholar
[13]
Fan J., Shen X., and Wu Y., Closed-loop adaptation for robust tracking, in Computer Vision- ECCV 2010, 2010, pp. 411-424.
DOI
[14]
Xie X., Hybrid particle swarm optimizer with mass extinction, in Proceedings of the International Conference on Communication, Circuits and Systems, Chengdu, China, 2002, pp. 1170-1173.
[15]
Jin X., Ma L., Wu T., and Qian J., Convergence analysis of the particle swarm optimization based on stochastic processes, Acta Automatica Sinica, vol. 33, no. 12, pp. 1263–1268, 2007.
Google Scholar
[16]
Su G., Ma H., and Hou Y., A robust approach for anti-jamming target tracking in forward looking infrared imagery, in International Conference on Image and Graphics (ICIG), 2011, pp. 636-641.
Publication history
Copyright
Rights and permissions

Publication history

Received: 15 April 2015
Revised: 17 August 2015
Accepted: 24 August 2015
Published: 31 March 2016
Issue date: April 2016

Copyright

© The author(s) 2016

Rights and permissions

Return