Development of a visual compressive trackng system enhanced by adaptive boosting

Yau Zen Chang; Ming Hsi Hsu; Chieh Tsai Wu; Shih Tseng Lee

doi:10.1109/IECON.2015.7392673

Development of a visual compressive trackng system enhanced by adaptive boosting

Yau Zen Chang
, Ming Hsi Hsu
, Chieh Tsai Wu
, Shih Tseng Lee

Department of Mechanical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

This paper presents the development of a dynamic optical tracking system based on a PTZ camera platform to stably track any selected object and keep the targeted object image in the center of video images. The system is based on the Compressive Tracking algorithm which provides dimensionality reduction to achieve real-time tracking. To enhance reliability and avoid failure due to morphological variation, disappearing and blocking of the targeted objects on image frames, the developed tracking algorithm is enhanced with an Adaptive Boosting (Ada-Boost) evaluation strategy to improve the reliability of the weak Naive Bayes classifier. Besides, a heuristic threshold is applied to select and update object templates to avoid drifting of the templates. Furthermore, potential locations of target patches are searched evenly for based on the Halton sequence. Experiments on practical scenarios demonstrate the robustness and effectiveness of the proposed scheme.

Original language	English
Title of host publication	IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	3678-3682
Number of pages	5
ISBN (Electronic)	9781479917624
DOIs	https://doi.org/10.1109/IECON.2015.7392673
State	Published - 2015
Event	41st Annual Conference of the IEEE Industrial Electronics Society, IECON 2015 - Yokohama, Japan Duration: 09 11 2015 → 12 11 2015

Publication series

Name	IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society

Conference

Conference	41st Annual Conference of the IEEE Industrial Electronics Society, IECON 2015
Country/Territory	Japan
City	Yokohama
Period	09/11/15 → 12/11/15

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Keywords

Active vision
Ada-Boost
Boosting
Classification algorithms
Compressive Tracking
Naive Bayes classifier
Object tracking
PTZ camera
Pattern analysis

Access to Document

10.1109/IECON.2015.7392673

Cite this

Chang, Y. Z., Hsu, M. H., Wu, C. T., & Lee, S. T. (2015). Development of a visual compressive trackng system enhanced by adaptive boosting. In IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society (pp. 3678-3682). Article 7392673 (IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IECON.2015.7392673

Chang, Yau Zen ; Hsu, Ming Hsi ; Wu, Chieh Tsai et al. / Development of a visual compressive trackng system enhanced by adaptive boosting. IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 3678-3682 (IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society).

@inproceedings{1c2218eaa2e14c27aa66caaa022ca316,

title = "Development of a visual compressive trackng system enhanced by adaptive boosting",

abstract = "This paper presents the development of a dynamic optical tracking system based on a PTZ camera platform to stably track any selected object and keep the targeted object image in the center of video images. The system is based on the Compressive Tracking algorithm which provides dimensionality reduction to achieve real-time tracking. To enhance reliability and avoid failure due to morphological variation, disappearing and blocking of the targeted objects on image frames, the developed tracking algorithm is enhanced with an Adaptive Boosting (Ada-Boost) evaluation strategy to improve the reliability of the weak Naive Bayes classifier. Besides, a heuristic threshold is applied to select and update object templates to avoid drifting of the templates. Furthermore, potential locations of target patches are searched evenly for based on the Halton sequence. Experiments on practical scenarios demonstrate the robustness and effectiveness of the proposed scheme.",

keywords = "Active vision, Ada-Boost, Boosting, Classification algorithms, Compressive Tracking, Naive Bayes classifier, Object tracking, PTZ camera, Pattern analysis",

author = "Chang, \{Yau Zen\} and Hsu, \{Ming Hsi\} and Wu, \{Chieh Tsai\} and Lee, \{Shih Tseng\}",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 41st Annual Conference of the IEEE Industrial Electronics Society, IECON 2015 ; Conference date: 09-11-2015 Through 12-11-2015",

year = "2015",

doi = "10.1109/IECON.2015.7392673",

language = "英语",

series = "IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "3678--3682",

booktitle = "IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society",

address = "美国",

}

Chang, YZ, Hsu, MH, Wu, CT & Lee, ST 2015, Development of a visual compressive trackng system enhanced by adaptive boosting. in IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society., 7392673, IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society, Institute of Electrical and Electronics Engineers Inc., pp. 3678-3682, 41st Annual Conference of the IEEE Industrial Electronics Society, IECON 2015, Yokohama, Japan, 09/11/15. https://doi.org/10.1109/IECON.2015.7392673

Development of a visual compressive trackng system enhanced by adaptive boosting. / Chang, Yau Zen; Hsu, Ming Hsi; Wu, Chieh Tsai et al.
IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society. Institute of Electrical and Electronics Engineers Inc., 2015. p. 3678-3682 7392673 (IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Development of a visual compressive trackng system enhanced by adaptive boosting

AU - Chang, Yau Zen

AU - Hsu, Ming Hsi

AU - Wu, Chieh Tsai

AU - Lee, Shih Tseng

PY - 2015

Y1 - 2015

N2 - This paper presents the development of a dynamic optical tracking system based on a PTZ camera platform to stably track any selected object and keep the targeted object image in the center of video images. The system is based on the Compressive Tracking algorithm which provides dimensionality reduction to achieve real-time tracking. To enhance reliability and avoid failure due to morphological variation, disappearing and blocking of the targeted objects on image frames, the developed tracking algorithm is enhanced with an Adaptive Boosting (Ada-Boost) evaluation strategy to improve the reliability of the weak Naive Bayes classifier. Besides, a heuristic threshold is applied to select and update object templates to avoid drifting of the templates. Furthermore, potential locations of target patches are searched evenly for based on the Halton sequence. Experiments on practical scenarios demonstrate the robustness and effectiveness of the proposed scheme.

AB - This paper presents the development of a dynamic optical tracking system based on a PTZ camera platform to stably track any selected object and keep the targeted object image in the center of video images. The system is based on the Compressive Tracking algorithm which provides dimensionality reduction to achieve real-time tracking. To enhance reliability and avoid failure due to morphological variation, disappearing and blocking of the targeted objects on image frames, the developed tracking algorithm is enhanced with an Adaptive Boosting (Ada-Boost) evaluation strategy to improve the reliability of the weak Naive Bayes classifier. Besides, a heuristic threshold is applied to select and update object templates to avoid drifting of the templates. Furthermore, potential locations of target patches are searched evenly for based on the Halton sequence. Experiments on practical scenarios demonstrate the robustness and effectiveness of the proposed scheme.

KW - Active vision

KW - Ada-Boost

KW - Boosting

KW - Classification algorithms

KW - Compressive Tracking

KW - Naive Bayes classifier

KW - Object tracking

KW - PTZ camera

KW - Pattern analysis

UR - https://www.scopus.com/pages/publications/84973176456

U2 - 10.1109/IECON.2015.7392673

DO - 10.1109/IECON.2015.7392673

M3 - 会议稿件

AN - SCOPUS:84973176456

T3 - IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society

SP - 3678

EP - 3682

BT - IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 41st Annual Conference of the IEEE Industrial Electronics Society, IECON 2015

Y2 - 9 November 2015 through 12 November 2015

ER -

Chang YZ, Hsu MH, Wu CT, Lee ST. Development of a visual compressive trackng system enhanced by adaptive boosting. In IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society. Institute of Electrical and Electronics Engineers Inc. 2015. p. 3678-3682. 7392673. (IECON 2015 - 41st Annual Conference of the IEEE Industrial Electronics Society). doi: 10.1109/IECON.2015.7392673

Development of a visual compressive trackng system enhanced by adaptive boosting

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this