Adaptive discriminative generative model for object tracking

Ruei Sung Lin, Ming Hsuan Yang, Stephen E Levinson

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

Abstract

This paper presents an adaptive visual learning algorithm for object tracking. We formulate a novel discriminative generative framework that generalizes the conventional Fisher Linear Discriminant algorithm with a generative model and renders a proper probabilistic interpretation. Within the context of object tracking, we aim to find a discriminative generative model that best separates the target class from the background. We present a computationally efficient algorithm to constantly update this discriminative model as time progresses. While most tracking algorithms operate on the premise that the object appearance or environment lighting condition does not significantly change as time progresses, our method adapts the discriminative generative model to reflect appearance variation of the target and background, thereby facilitating the tracking task in different situations. Numerous experiments show that our method is able to learn a discriminative generative model for tracking target objects undergoing large pose and lighting changes.

Original languageEnglish (US)
Title of host publicationECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings
EditorsRamon Lopez de Mantaras, Lorenza Saitta
PublisherIOS Press
Pages505-509
Number of pages5
ISBN (Electronic)9781586034528
StatePublished - Jan 1 2004
Event16th European Conference on Artificial Intelligence, ECAI 2004 - Valencia, Spain
Duration: Aug 22 2004Aug 27 2004

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume110
ISSN (Print)0922-6389

Other

Other16th European Conference on Artificial Intelligence, ECAI 2004
CountrySpain
CityValencia
Period8/22/048/27/04

Fingerprint

Lighting
Target tracking
Learning algorithms
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Lin, R. S., Yang, M. H., & Levinson, S. E. (2004). Adaptive discriminative generative model for object tracking. In R. L. de Mantaras, & L. Saitta (Eds.), ECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings (pp. 505-509). (Frontiers in Artificial Intelligence and Applications; Vol. 110). IOS Press.

Adaptive discriminative generative model for object tracking. / Lin, Ruei Sung; Yang, Ming Hsuan; Levinson, Stephen E.

ECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings. ed. / Ramon Lopez de Mantaras; Lorenza Saitta. IOS Press, 2004. p. 505-509 (Frontiers in Artificial Intelligence and Applications; Vol. 110).

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

Lin, RS, Yang, MH & Levinson, SE 2004, Adaptive discriminative generative model for object tracking. in RL de Mantaras & L Saitta (eds), ECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings. Frontiers in Artificial Intelligence and Applications, vol. 110, IOS Press, pp. 505-509, 16th European Conference on Artificial Intelligence, ECAI 2004, Valencia, Spain, 8/22/04.
Lin RS, Yang MH, Levinson SE. Adaptive discriminative generative model for object tracking. In de Mantaras RL, Saitta L, editors, ECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings. IOS Press. 2004. p. 505-509. (Frontiers in Artificial Intelligence and Applications).
Lin, Ruei Sung ; Yang, Ming Hsuan ; Levinson, Stephen E. / Adaptive discriminative generative model for object tracking. ECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings. editor / Ramon Lopez de Mantaras ; Lorenza Saitta. IOS Press, 2004. pp. 505-509 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{9f177acc5d204b91bc9996683b715b69,
title = "Adaptive discriminative generative model for object tracking",
abstract = "This paper presents an adaptive visual learning algorithm for object tracking. We formulate a novel discriminative generative framework that generalizes the conventional Fisher Linear Discriminant algorithm with a generative model and renders a proper probabilistic interpretation. Within the context of object tracking, we aim to find a discriminative generative model that best separates the target class from the background. We present a computationally efficient algorithm to constantly update this discriminative model as time progresses. While most tracking algorithms operate on the premise that the object appearance or environment lighting condition does not significantly change as time progresses, our method adapts the discriminative generative model to reflect appearance variation of the target and background, thereby facilitating the tracking task in different situations. Numerous experiments show that our method is able to learn a discriminative generative model for tracking target objects undergoing large pose and lighting changes.",
author = "Lin, {Ruei Sung} and Yang, {Ming Hsuan} and Levinson, {Stephen E}",
year = "2004",
month = "1",
day = "1",
language = "English (US)",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
pages = "505--509",
editor = "{de Mantaras}, {Ramon Lopez} and Lorenza Saitta",
booktitle = "ECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings",
address = "United States",

}

TY - GEN

T1 - Adaptive discriminative generative model for object tracking

AU - Lin, Ruei Sung

AU - Yang, Ming Hsuan

AU - Levinson, Stephen E

PY - 2004/1/1

Y1 - 2004/1/1

N2 - This paper presents an adaptive visual learning algorithm for object tracking. We formulate a novel discriminative generative framework that generalizes the conventional Fisher Linear Discriminant algorithm with a generative model and renders a proper probabilistic interpretation. Within the context of object tracking, we aim to find a discriminative generative model that best separates the target class from the background. We present a computationally efficient algorithm to constantly update this discriminative model as time progresses. While most tracking algorithms operate on the premise that the object appearance or environment lighting condition does not significantly change as time progresses, our method adapts the discriminative generative model to reflect appearance variation of the target and background, thereby facilitating the tracking task in different situations. Numerous experiments show that our method is able to learn a discriminative generative model for tracking target objects undergoing large pose and lighting changes.

AB - This paper presents an adaptive visual learning algorithm for object tracking. We formulate a novel discriminative generative framework that generalizes the conventional Fisher Linear Discriminant algorithm with a generative model and renders a proper probabilistic interpretation. Within the context of object tracking, we aim to find a discriminative generative model that best separates the target class from the background. We present a computationally efficient algorithm to constantly update this discriminative model as time progresses. While most tracking algorithms operate on the premise that the object appearance or environment lighting condition does not significantly change as time progresses, our method adapts the discriminative generative model to reflect appearance variation of the target and background, thereby facilitating the tracking task in different situations. Numerous experiments show that our method is able to learn a discriminative generative model for tracking target objects undergoing large pose and lighting changes.

UR - http://www.scopus.com/inward/record.url?scp=85017347906&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017347906&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85017347906

T3 - Frontiers in Artificial Intelligence and Applications

SP - 505

EP - 509

BT - ECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings

A2 - de Mantaras, Ramon Lopez

A2 - Saitta, Lorenza

PB - IOS Press

ER -