Asymmetric totally-corrective boosting for real-time object detection
Date
2011
Authors
Wang, P.
Shen, C.
Barnes, N.
Zheng, H.
Ren, Z.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Computer Vision - ACCV 2010: Proceedings of 10th Asian Conference on Computer Vision, held in Queenstown, New Zealand, Nov 8-12 2010, revised selected papers, part 1 / R. Kimmel, R. Klette and A. Sugimoto (eds.): pp.176-188
Statement of Responsibility
Peng Wang, Chunhua Shen, Nick Barnes, Hong Zheng, and Zhang Ren
Conference Name
Asian Conference on Computer Vision (10th : 2010 : Queenstown, New Zealand)
Abstract
Real-time object detection is one of the core problems in computer vision. The cascade boosting framework proposed by Viola and Jones has become the standard for this problem. In this framework, the learning goal for each node is asymmetric, which is required to achieve a high detection rate and a moderate false positive rate. We develop new boosting algorithms to address this asymmetric learning problem. We show that our methods explicitly optimize asymmetric loss objectives in a totally corrective fashion. The methods are totally corrective in the sense that the coefficients of all selected weak classifiers are updated at each iteration. In contract, conventional boosting like AdaBoost is stage-wise in that only the current weak classifier’s coefficient is updated. At the heart of the totally corrective boosting is the column generation technique. Experiments on face detection show that our methods outperform the state-of-the-art asymmetric boosting methods.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© Springer-Verlag Berlin Heidelberg 2011