A coarse-to-fine approach for motion pattern discovery

Bolun Cai; Zhifeng Luo; Kerui Li

doi:10.1109/CyberC.2012.95

A coarse-to-fine approach for motion pattern discovery

Bolun Cai, Zhifeng Luo, Kerui Li

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

Abstract

In this paper, we propose a coarse-to-fine approach to discovery motion patterns. There are two phases in the proposed approach. In the first phase, the proposed median-based GMM achieves coarse clustering. Moreover, the number of clusters can be heuristically found by the proposed algorithm. In the second phase, to refine coarse clustering in the first phase, a Fisher optimal division method is proposed to examine the boundary data points and to detect the change point between motion patterns. The experimental results show that the proposed approach outperforms the existing algorithms.

Original language	English
Title of host publication	Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012
Pages	519-522
Number of pages	4
DOIs	https://doi.org/10.1109/CyberC.2012.95
Publication status	Published - Oct 2012
Externally published	Yes
Event	4th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012 - Sanya, China Duration: 10 Oct 2012 → 12 Oct 2012

Publication series

Name	Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012

Conference

Conference	4th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012
Country/Territory	China
City	Sanya
Period	10/10/12 → 12/10/12

Keywords

GMM
motion pattern discovery
trajectory data clustering

ASJC Scopus subject areas

Software

More information

10.1109/CyberC.2012.95

Cite this

Cai, B., Luo, Z., & Li, K. (2012). A coarse-to-fine approach for motion pattern discovery. In Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012 (pp. 519-522). Article 6385022 (Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012). https://doi.org/10.1109/CyberC.2012.95

@inproceedings{3fd8a8c5d72c4c778ebade25de95d317,

title = "A coarse-to-fine approach for motion pattern discovery",

abstract = "In this paper, we propose a coarse-to-fine approach to discovery motion patterns. There are two phases in the proposed approach. In the first phase, the proposed median-based GMM achieves coarse clustering. Moreover, the number of clusters can be heuristically found by the proposed algorithm. In the second phase, to refine coarse clustering in the first phase, a Fisher optimal division method is proposed to examine the boundary data points and to detect the change point between motion patterns. The experimental results show that the proposed approach outperforms the existing algorithms.",

keywords = "GMM, motion pattern discovery, trajectory data clustering",

author = "Bolun Cai and Zhifeng Luo and Kerui Li",

year = "2012",

month = oct,

doi = "10.1109/CyberC.2012.95",

language = "English",

isbn = "9780769548104",

series = "Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012",

pages = "519--522",

booktitle = "Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012",

note = "4th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012 ; Conference date: 10-10-2012 Through 12-10-2012",

}

Cai, B, Luo, Z & Li, K 2012, A coarse-to-fine approach for motion pattern discovery. in Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012., 6385022, Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012, pp. 519-522, 4th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012, Sanya, China, 10/10/12. https://doi.org/10.1109/CyberC.2012.95

A coarse-to-fine approach for motion pattern discovery. / Cai, Bolun; Luo, Zhifeng; Li, Kerui.
Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012. 2012. p. 519-522 6385022 (Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012).

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - A coarse-to-fine approach for motion pattern discovery

AU - Cai, Bolun

AU - Luo, Zhifeng

AU - Li, Kerui

PY - 2012/10

Y1 - 2012/10

N2 - In this paper, we propose a coarse-to-fine approach to discovery motion patterns. There are two phases in the proposed approach. In the first phase, the proposed median-based GMM achieves coarse clustering. Moreover, the number of clusters can be heuristically found by the proposed algorithm. In the second phase, to refine coarse clustering in the first phase, a Fisher optimal division method is proposed to examine the boundary data points and to detect the change point between motion patterns. The experimental results show that the proposed approach outperforms the existing algorithms.

AB - In this paper, we propose a coarse-to-fine approach to discovery motion patterns. There are two phases in the proposed approach. In the first phase, the proposed median-based GMM achieves coarse clustering. Moreover, the number of clusters can be heuristically found by the proposed algorithm. In the second phase, to refine coarse clustering in the first phase, a Fisher optimal division method is proposed to examine the boundary data points and to detect the change point between motion patterns. The experimental results show that the proposed approach outperforms the existing algorithms.

KW - GMM

KW - motion pattern discovery

KW - trajectory data clustering

UR - http://www.scopus.com/inward/record.url?scp=84872357276&partnerID=8YFLogxK

U2 - 10.1109/CyberC.2012.95

DO - 10.1109/CyberC.2012.95

M3 - Conference article published in proceeding or book

AN - SCOPUS:84872357276

SN - 9780769548104

T3 - Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012

SP - 519

EP - 522

BT - Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012

T2 - 4th International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012

Y2 - 10 October 2012 through 12 October 2012

ER -

Cai B, Luo Z, Li K. A coarse-to-fine approach for motion pattern discovery. In Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012. 2012. p. 519-522. 6385022. (Proceedings of the 2012 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC 2012). doi: 10.1109/CyberC.2012.95

A coarse-to-fine approach for motion pattern discovery

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this