TY - GEN
T1 - Detector ensemble
AU - Dai, Shengyang
AU - Yang, Ming
AU - Wu, Ying
AU - Katsaggelos, Aggelos
PY - 2007
Y1 - 2007
N2 - Component-based detection methods have demonstrated their promise by integrating a set of part-detectors to deal with large appearance variations of the target. However, an essential and critical issue, i.e., how to handle the imperfectness of part-detectors in the integration, is not well addressed in the literature. This paper proposes a detector ensemble model that consists of a set of substructure-detectors, each of which is composed of several part-detectors. Two important issues are studied both in theory and in practice, (1) finding an optimal detector ensemble, and (2) detecting targets based on an ensemble. Based on some theoretical analysis, a new model selection strategy is proposed to learn an optimal detector ensemble that has a minimum number of false positives and satisfies the design requirement on the capacity of tolerating missing parts. In addition, this paper also links ensemble-based detection to the inference in Markov random field, and shows that the target detection can be done by a max-product belief propagation algorithm.
AB - Component-based detection methods have demonstrated their promise by integrating a set of part-detectors to deal with large appearance variations of the target. However, an essential and critical issue, i.e., how to handle the imperfectness of part-detectors in the integration, is not well addressed in the literature. This paper proposes a detector ensemble model that consists of a set of substructure-detectors, each of which is composed of several part-detectors. Two important issues are studied both in theory and in practice, (1) finding an optimal detector ensemble, and (2) detecting targets based on an ensemble. Based on some theoretical analysis, a new model selection strategy is proposed to learn an optimal detector ensemble that has a minimum number of false positives and satisfies the design requirement on the capacity of tolerating missing parts. In addition, this paper also links ensemble-based detection to the inference in Markov random field, and shows that the target detection can be done by a max-product belief propagation algorithm.
UR - http://www.scopus.com/inward/record.url?scp=35148849153&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=35148849153&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2007.383274
DO - 10.1109/CVPR.2007.383274
M3 - Conference contribution
AN - SCOPUS:35148849153
SN - 1424411807
SN - 9781424411801
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
BT - 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
T2 - 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR'07
Y2 - 17 June 2007 through 22 June 2007
ER -