Marker-less stereo-vision human motion tracking using hybrid filter in unconstrained environment

Bunseng Chan; King Hann Lim; Lenin Gopal; A. A. Gopalai; W. C. Chia; W. J. Chew

doi:10.1109/TENCON.2018.8650462

Marker-less stereo-vision human motion tracking using hybrid filter in unconstrained environment

Bunseng Chan
, King Hann Lim
, Lenin Gopal
, A. A. Gopalai
, W. C. Chia
, W. J. Chew

Malaysia School of Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other

1 Citation (Scopus)

Abstract

Stereo-vision technology has shown its advantages to overcome the occlusion and realistic information. However, marker-less human motion detection and tracking in the unconstrained environment were led to the difficulty of features extraction. In this paper, we proposed a hybrid technique of Gaussian and median filter to improve the shadow and sudden change of the illumination problems. The skeleton model of the detected human was constructed using the sequential mathematical morphology. Based on the results, the skeleton model produced was not affected by the shadow and the illumination issue. Proposed approach and the normalized filter approach produces up to 86% and 71% of the average accuracy tracking respectively in the real-time tracking. Hence, the proposed approach could improve the performance of the human detection in the unconstrained environment.

Original language	English
Title of host publication	Proceedings of TENCON 2018 - 2018 IEEE Region 10 Conference
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1818-1823
Number of pages	6
ISBN (Electronic)	9781538654576
DOIs	https://doi.org/10.1109/TENCON.2018.8650462
Publication status	Published - 2019
Event	IEEE Tencon (IEEE Region 10 Conference) 2018 - Jeju, Korea, South Duration: 28 Oct 2018 → 31 Oct 2018 https://ieeexplore.ieee.org/xpl/conhome/8643125/proceeding (Proceedings)

Publication series

Name	IEEE Region 10 Annual International Conference, Proceedings/TENCON
Volume	2018-October
ISSN (Print)	2159-3442
ISSN (Electronic)	2159-3450

Conference

Conference	IEEE Tencon (IEEE Region 10 Conference) 2018
Abbreviated title	TENCON 2018
Country/Territory	Korea, South
City	Jeju
Period	28/10/18 → 31/10/18
Internet address	https://ieeexplore.ieee.org/xpl/conhome/8643125/proceeding (Proceedings)

Keywords

Human Motion Detection and Tracking
Segmentation
Sequential Morphology
Skeleton Model
Stereo Vision

Access to Document

10.1109/TENCON.2018.8650462

Cite this

Chan, B., Lim, K. H., Gopal, L., Gopalai, A. A., Chia, W. C., & Chew, W. J. (2019). Marker-less stereo-vision human motion tracking using hybrid filter in unconstrained environment. In Proceedings of TENCON 2018 - 2018 IEEE Region 10 Conference (pp. 1818-1823). (IEEE Region 10 Annual International Conference, Proceedings/TENCON; Vol. 2018-October). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/TENCON.2018.8650462

@inproceedings{ffe120e884764639bc441fc8eba646cd,

title = "Marker-less stereo-vision human motion tracking using hybrid filter in unconstrained environment",

abstract = "Stereo-vision technology has shown its advantages to overcome the occlusion and realistic information. However, marker-less human motion detection and tracking in the unconstrained environment were led to the difficulty of features extraction. In this paper, we proposed a hybrid technique of Gaussian and median filter to improve the shadow and sudden change of the illumination problems. The skeleton model of the detected human was constructed using the sequential mathematical morphology. Based on the results, the skeleton model produced was not affected by the shadow and the illumination issue. Proposed approach and the normalized filter approach produces up to 86\% and 71\% of the average accuracy tracking respectively in the real-time tracking. Hence, the proposed approach could improve the performance of the human detection in the unconstrained environment.",

keywords = "Human Motion Detection and Tracking, Segmentation, Sequential Morphology, Skeleton Model, Stereo Vision",

author = "Bunseng Chan and Lim, \{King Hann\} and Lenin Gopal and Gopalai, \{A. A.\} and Chia, \{W. C.\} and Chew, \{W. J.\}",

note = "Funding Information: ACKNOWLEDGMENT The authors would like to acknowledge the financial support from E-Science-Fund (03-02-07-SF0035) of MOSTI Malaysia. We gratefully acknowledge the support of NVIDIA Corporation with the contribution of the TITAN X used for this research. Publisher Copyright: {\textcopyright} 2018 IEEE. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; IEEE Tencon (IEEE Region 10 Conference) 2018, TENCON 2018 ; Conference date: 28-10-2018 Through 31-10-2018",

year = "2019",

doi = "10.1109/TENCON.2018.8650462",

language = "English",

series = "IEEE Region 10 Annual International Conference, Proceedings/TENCON",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "1818--1823",

booktitle = "Proceedings of TENCON 2018 - 2018 IEEE Region 10 Conference",

address = "United States of America",

url = "https://ieeexplore.ieee.org/xpl/conhome/8643125/proceeding",

}

Chan, B, Lim, KH, Gopal, L, Gopalai, AA, Chia, WC & Chew, WJ 2019, Marker-less stereo-vision human motion tracking using hybrid filter in unconstrained environment. in Proceedings of TENCON 2018 - 2018 IEEE Region 10 Conference. IEEE Region 10 Annual International Conference, Proceedings/TENCON, vol. 2018-October, IEEE, Institute of Electrical and Electronics Engineers, pp. 1818-1823, IEEE Tencon (IEEE Region 10 Conference) 2018, Jeju, Korea, South, 28/10/18. https://doi.org/10.1109/TENCON.2018.8650462

Marker-less stereo-vision human motion tracking using hybrid filter in unconstrained environment. / Chan, Bunseng; Lim, King Hann; Gopal, Lenin et al.
Proceedings of TENCON 2018 - 2018 IEEE Region 10 Conference. IEEE, Institute of Electrical and Electronics Engineers, 2019. p. 1818-1823 (IEEE Region 10 Annual International Conference, Proceedings/TENCON; Vol. 2018-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other

TY - GEN

T1 - Marker-less stereo-vision human motion tracking using hybrid filter in unconstrained environment

AU - Chan, Bunseng

AU - Lim, King Hann

AU - Gopal, Lenin

AU - Gopalai, A. A.

AU - Chia, W. C.

AU - Chew, W. J.

N1 - Funding Information: ACKNOWLEDGMENT The authors would like to acknowledge the financial support from E-Science-Fund (03-02-07-SF0035) of MOSTI Malaysia. We gratefully acknowledge the support of NVIDIA Corporation with the contribution of the TITAN X used for this research. Publisher Copyright: © 2018 IEEE. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.

PY - 2019

Y1 - 2019

N2 - Stereo-vision technology has shown its advantages to overcome the occlusion and realistic information. However, marker-less human motion detection and tracking in the unconstrained environment were led to the difficulty of features extraction. In this paper, we proposed a hybrid technique of Gaussian and median filter to improve the shadow and sudden change of the illumination problems. The skeleton model of the detected human was constructed using the sequential mathematical morphology. Based on the results, the skeleton model produced was not affected by the shadow and the illumination issue. Proposed approach and the normalized filter approach produces up to 86% and 71% of the average accuracy tracking respectively in the real-time tracking. Hence, the proposed approach could improve the performance of the human detection in the unconstrained environment.

AB - Stereo-vision technology has shown its advantages to overcome the occlusion and realistic information. However, marker-less human motion detection and tracking in the unconstrained environment were led to the difficulty of features extraction. In this paper, we proposed a hybrid technique of Gaussian and median filter to improve the shadow and sudden change of the illumination problems. The skeleton model of the detected human was constructed using the sequential mathematical morphology. Based on the results, the skeleton model produced was not affected by the shadow and the illumination issue. Proposed approach and the normalized filter approach produces up to 86% and 71% of the average accuracy tracking respectively in the real-time tracking. Hence, the proposed approach could improve the performance of the human detection in the unconstrained environment.

KW - Human Motion Detection and Tracking

KW - Segmentation

KW - Sequential Morphology

KW - Skeleton Model

KW - Stereo Vision

UR - https://www.scopus.com/pages/publications/85063210335

U2 - 10.1109/TENCON.2018.8650462

DO - 10.1109/TENCON.2018.8650462

M3 - Conference Paper

AN - SCOPUS:85063210335

T3 - IEEE Region 10 Annual International Conference, Proceedings/TENCON

SP - 1818

EP - 1823

BT - Proceedings of TENCON 2018 - 2018 IEEE Region 10 Conference

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - IEEE Tencon (IEEE Region 10 Conference) 2018

Y2 - 28 October 2018 through 31 October 2018

ER -

Chan B, Lim KH, Gopal L, Gopalai AA, Chia WC, Chew WJ. Marker-less stereo-vision human motion tracking using hybrid filter in unconstrained environment. In Proceedings of TENCON 2018 - 2018 IEEE Region 10 Conference. IEEE, Institute of Electrical and Electronics Engineers. 2019. p. 1818-1823. (IEEE Region 10 Annual International Conference, Proceedings/TENCON). doi: 10.1109/TENCON.2018.8650462

Marker-less stereo-vision human motion tracking using hybrid filter in unconstrained environment

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this