Tracking objects in video using motion and appearance models

Aswin C. Sankaranarayanan; Rama Chellappa; Qinfen Zheng

doi:10.1109/ICIP.2005.1530075

Tracking objects in video using motion and appearance models

Aswin C. Sankaranarayanan
, Rama Chellappa
, Qinfen Zheng

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

Abstract

This paper proposes a visual tracking algorithm that combines motion and appearance in a statistical framework. It is assumed that image observations are generated simultaneously from a background model and a target appearance model. This is different from conventional appearance-based tracking, that does not use motion information. The proposed algorithm attempts to maximize the likelihood ratio of the tracked region, derived from appearance and back-ground models. Incorporation of motion in appearance based tracking provides robust tracking, even when the target violates the appearance model. We show that the proposed algorithm performs well in tracking targets efficiently over long time intervals.

Original language	English (US)
Title of host publication	IEEE International Conference on Image Processing 2005, ICIP 2005
Pages	394-397
Number of pages	4
DOIs	https://doi.org/10.1109/ICIP.2005.1530075
State	Published - 2005
Externally published	Yes
Event	IEEE International Conference on Image Processing 2005, ICIP 2005 - Genova, Italy Duration: Sep 11 2005 → Sep 14 2005

Publication series

Name	Proceedings - International Conference on Image Processing, ICIP
Volume	2
ISSN (Print)	1522-4880

Other

Other	IEEE International Conference on Image Processing 2005, ICIP 2005
Country/Territory	Italy
City	Genova
Period	9/11/05 → 9/14/05

ASJC Scopus subject areas

General Engineering

Access to Document

10.1109/ICIP.2005.1530075

Cite this

Tracking objects in video using motion and appearance models. / Sankaranarayanan, Aswin C.; Chellappa, Rama; Zheng, Qinfen.
IEEE International Conference on Image Processing 2005, ICIP 2005. 2005. p. 394-397 1530075 (Proceedings - International Conference on Image Processing, ICIP; Vol. 2).

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

Sankaranarayanan, AC, Chellappa, R & Zheng, Q 2005, Tracking objects in video using motion and appearance models. in IEEE International Conference on Image Processing 2005, ICIP 2005., 1530075, Proceedings - International Conference on Image Processing, ICIP, vol. 2, pp. 394-397, IEEE International Conference on Image Processing 2005, ICIP 2005, Genova, Italy, 9/11/05. https://doi.org/10.1109/ICIP.2005.1530075

@inproceedings{03fc44fbea0449f3a23eb78c1ba5a3b7,

title = "Tracking objects in video using motion and appearance models",

abstract = "This paper proposes a visual tracking algorithm that combines motion and appearance in a statistical framework. It is assumed that image observations are generated simultaneously from a background model and a target appearance model. This is different from conventional appearance-based tracking, that does not use motion information. The proposed algorithm attempts to maximize the likelihood ratio of the tracked region, derived from appearance and back-ground models. Incorporation of motion in appearance based tracking provides robust tracking, even when the target violates the appearance model. We show that the proposed algorithm performs well in tracking targets efficiently over long time intervals.",

author = "Sankaranarayanan, \{Aswin C.\} and Rama Chellappa and Qinfen Zheng",

year = "2005",

doi = "10.1109/ICIP.2005.1530075",

language = "English (US)",

isbn = "0780391349",

series = "Proceedings - International Conference on Image Processing, ICIP",

pages = "394--397",

booktitle = "IEEE International Conference on Image Processing 2005, ICIP 2005",

note = "IEEE International Conference on Image Processing 2005, ICIP 2005 ; Conference date: 11-09-2005 Through 14-09-2005",

}

TY - GEN

T1 - Tracking objects in video using motion and appearance models

AU - Sankaranarayanan, Aswin C.

AU - Chellappa, Rama

AU - Zheng, Qinfen

PY - 2005

Y1 - 2005

N2 - This paper proposes a visual tracking algorithm that combines motion and appearance in a statistical framework. It is assumed that image observations are generated simultaneously from a background model and a target appearance model. This is different from conventional appearance-based tracking, that does not use motion information. The proposed algorithm attempts to maximize the likelihood ratio of the tracked region, derived from appearance and back-ground models. Incorporation of motion in appearance based tracking provides robust tracking, even when the target violates the appearance model. We show that the proposed algorithm performs well in tracking targets efficiently over long time intervals.

AB - This paper proposes a visual tracking algorithm that combines motion and appearance in a statistical framework. It is assumed that image observations are generated simultaneously from a background model and a target appearance model. This is different from conventional appearance-based tracking, that does not use motion information. The proposed algorithm attempts to maximize the likelihood ratio of the tracked region, derived from appearance and back-ground models. Incorporation of motion in appearance based tracking provides robust tracking, even when the target violates the appearance model. We show that the proposed algorithm performs well in tracking targets efficiently over long time intervals.

UR - https://www.scopus.com/pages/publications/33749594729

UR - https://www.scopus.com/pages/publications/33749594729#tab=citedBy

U2 - 10.1109/ICIP.2005.1530075

DO - 10.1109/ICIP.2005.1530075

M3 - Conference contribution

AN - SCOPUS:33749594729

SN - 0780391349

SN - 9780780391345

T3 - Proceedings - International Conference on Image Processing, ICIP

SP - 394

EP - 397

BT - IEEE International Conference on Image Processing 2005, ICIP 2005

T2 - IEEE International Conference on Image Processing 2005, ICIP 2005

Y2 - 11 September 2005 through 14 September 2005

ER -

Tracking objects in video using motion and appearance models

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this