Multi-target tracking of time-varying spatial patterns

Jingchen Liu, Yanxi Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Time-varying spatial patterns are common, but few computational tools exist for discovering and tracking multiple, sometimes overlapping, spatial structures of targets. We propose a multi-target tracking framework that takes advantage of spatial patterns inside the targets even though the number, the form and the regularity of such patterns vary with time. RANSAC-based model fitting algorithms are developed to automatically recognize (or dismiss) (il)legitimate patterns. Patterns are represented using a mixture of Markov Random Fields (MRF) with constraints (local and global) and preferences encoded into pairwise potential functions. To handle pattern variations continuously, we introduce a posterior probability for each spatial pattern modeled as a Bernoulli distribution. Tracking is achieved by inferring the optimal state configurations of the targets using belief propagation on a mixture of MRFs. We have evaluated our formulation on real video data with multiple targets containing time-varying lattice patterns and/or reflection symmetry patterns. Experimental results of our proposed algorithm show superior tracking performance over existing methods.

Original languageEnglish (US)
Title of host publication2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
Pages1839-1846
Number of pages8
DOIs
StatePublished - Aug 31 2010
Event2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 - San Francisco, CA, United States
Duration: Jun 13 2010Jun 18 2010

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Other

Other2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010
CountryUnited States
CitySan Francisco, CA
Period6/13/106/18/10

Fingerprint

Target tracking

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Liu, J., & Liu, Y. (2010). Multi-target tracking of time-varying spatial patterns. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010 (pp. 1839-1846). [5539855] (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2010.5539855
Liu, Jingchen ; Liu, Yanxi. / Multi-target tracking of time-varying spatial patterns. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010. 2010. pp. 1839-1846 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
@inproceedings{a5b7b7bbbcfc4663aabe96870049726a,
title = "Multi-target tracking of time-varying spatial patterns",
abstract = "Time-varying spatial patterns are common, but few computational tools exist for discovering and tracking multiple, sometimes overlapping, spatial structures of targets. We propose a multi-target tracking framework that takes advantage of spatial patterns inside the targets even though the number, the form and the regularity of such patterns vary with time. RANSAC-based model fitting algorithms are developed to automatically recognize (or dismiss) (il)legitimate patterns. Patterns are represented using a mixture of Markov Random Fields (MRF) with constraints (local and global) and preferences encoded into pairwise potential functions. To handle pattern variations continuously, we introduce a posterior probability for each spatial pattern modeled as a Bernoulli distribution. Tracking is achieved by inferring the optimal state configurations of the targets using belief propagation on a mixture of MRFs. We have evaluated our formulation on real video data with multiple targets containing time-varying lattice patterns and/or reflection symmetry patterns. Experimental results of our proposed algorithm show superior tracking performance over existing methods.",
author = "Jingchen Liu and Yanxi Liu",
year = "2010",
month = "8",
day = "31",
doi = "10.1109/CVPR.2010.5539855",
language = "English (US)",
isbn = "9781424469840",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
pages = "1839--1846",
booktitle = "2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010",

}

Liu, J & Liu, Y 2010, Multi-target tracking of time-varying spatial patterns. in 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010., 5539855, Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1839-1846, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, CA, United States, 6/13/10. https://doi.org/10.1109/CVPR.2010.5539855

Multi-target tracking of time-varying spatial patterns. / Liu, Jingchen; Liu, Yanxi.

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010. 2010. p. 1839-1846 5539855 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Multi-target tracking of time-varying spatial patterns

AU - Liu, Jingchen

AU - Liu, Yanxi

PY - 2010/8/31

Y1 - 2010/8/31

N2 - Time-varying spatial patterns are common, but few computational tools exist for discovering and tracking multiple, sometimes overlapping, spatial structures of targets. We propose a multi-target tracking framework that takes advantage of spatial patterns inside the targets even though the number, the form and the regularity of such patterns vary with time. RANSAC-based model fitting algorithms are developed to automatically recognize (or dismiss) (il)legitimate patterns. Patterns are represented using a mixture of Markov Random Fields (MRF) with constraints (local and global) and preferences encoded into pairwise potential functions. To handle pattern variations continuously, we introduce a posterior probability for each spatial pattern modeled as a Bernoulli distribution. Tracking is achieved by inferring the optimal state configurations of the targets using belief propagation on a mixture of MRFs. We have evaluated our formulation on real video data with multiple targets containing time-varying lattice patterns and/or reflection symmetry patterns. Experimental results of our proposed algorithm show superior tracking performance over existing methods.

AB - Time-varying spatial patterns are common, but few computational tools exist for discovering and tracking multiple, sometimes overlapping, spatial structures of targets. We propose a multi-target tracking framework that takes advantage of spatial patterns inside the targets even though the number, the form and the regularity of such patterns vary with time. RANSAC-based model fitting algorithms are developed to automatically recognize (or dismiss) (il)legitimate patterns. Patterns are represented using a mixture of Markov Random Fields (MRF) with constraints (local and global) and preferences encoded into pairwise potential functions. To handle pattern variations continuously, we introduce a posterior probability for each spatial pattern modeled as a Bernoulli distribution. Tracking is achieved by inferring the optimal state configurations of the targets using belief propagation on a mixture of MRFs. We have evaluated our formulation on real video data with multiple targets containing time-varying lattice patterns and/or reflection symmetry patterns. Experimental results of our proposed algorithm show superior tracking performance over existing methods.

UR - http://www.scopus.com/inward/record.url?scp=77956000654&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77956000654&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2010.5539855

DO - 10.1109/CVPR.2010.5539855

M3 - Conference contribution

SN - 9781424469840

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1839

EP - 1846

BT - 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010

ER -

Liu J, Liu Y. Multi-target tracking of time-varying spatial patterns. In 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2010. 2010. p. 1839-1846. 5539855. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). https://doi.org/10.1109/CVPR.2010.5539855