TY - GEN
T1 - Adaptive learning algorithm for SVM applied to feature tracking
AU - Garg, Ashutosh
AU - Cohen, Ira
AU - Huang, Thomas S.
N1 - Funding Information:
This work was supported in part by National Science Foundation Grants CDA-96-24396 and IRI-96-34618. The authors will also like to thank the reviewers for their useful comments.
Publisher Copyright:
© 1999 IEEE.
PY - 1999
Y1 - 1999
N2 - The framework of support vector machines (SVM) is becoming extremely popular in the field of statistical pattern classification. In this paper we investigate a technique which couples Kalman filter closely with the SVM. The problem of object tracking can be seen as a pattern recognition problem. However, because of the dynamics, this pattern might experience some changes over time. In order to keep track of the position of the pattern and to make out the desired pattern from the background, we must have some strong continuous time model. We propose an algorithm which combines the Markov property of the Kalman filter with the strong classification capability of SVM. The whole system has been tested on real life problems and we found that with this framework we could track a particular object even in a frame which contains identical objects. The results were compared to that of obtained by color blob tracking which showed the strength of the approach.
AB - The framework of support vector machines (SVM) is becoming extremely popular in the field of statistical pattern classification. In this paper we investigate a technique which couples Kalman filter closely with the SVM. The problem of object tracking can be seen as a pattern recognition problem. However, because of the dynamics, this pattern might experience some changes over time. In order to keep track of the position of the pattern and to make out the desired pattern from the background, we must have some strong continuous time model. We propose an algorithm which combines the Markov property of the Kalman filter with the strong classification capability of SVM. The whole system has been tested on real life problems and we found that with this framework we could track a particular object even in a frame which contains identical objects. The results were compared to that of obtained by color blob tracking which showed the strength of the approach.
UR - http://www.scopus.com/inward/record.url?scp=77953223561&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77953223561&partnerID=8YFLogxK
U2 - 10.1109/ICIIS.1999.810293
DO - 10.1109/ICIIS.1999.810293
M3 - Conference contribution
AN - SCOPUS:77953223561
T3 - Proceedings - 1999 International Conference on Information Intelligence and Systems, ICIIS 1999
SP - 388
EP - 395
BT - Proceedings - 1999 International Conference on Information Intelligence and Systems, ICIIS 1999
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1999 International Conference on Information Intelligence and Systems, ICIIS 1999
Y2 - 31 October 1999 through 3 November 1999
ER -