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 language | English (US) |
|---|---|
| Title of host publication | ECAI 2004 - 16th European Conference on Artificial Intelligence, including Prestigious Applications of Intelligent Systems, PAIS 2004 - Proceedings |
| Editors | Ramon Lopez de Mantaras, Lorenza Saitta |
| Publisher | IOS Press |
| Pages | 505-509 |
| Number of pages | 5 |
| ISBN (Electronic) | 9781586034528 |
| State | Published - Jan 1 2004 |
| Event | 16th European Conference on Artificial Intelligence, ECAI 2004 - Valencia, Spain Duration: Aug 22 2004 → Aug 27 2004 |
Publication series
| Name | Frontiers in Artificial Intelligence and Applications |
|---|---|
| Volume | 110 |
| ISSN (Print) | 0922-6389 |
Other
| Other | 16th European Conference on Artificial Intelligence, ECAI 2004 |
|---|---|
| Country | Spain |
| City | Valencia |
| Period | 8/22/04 → 8/27/04 |
Fingerprint
ASJC Scopus subject areas
- Artificial Intelligence
Cite this
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 proceeding › Conference contribution
}
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 -