Abstract：To solve the problem of feature misalignment appearing in object detection, a multi-configuration feature bag is put forward and used to describe variant misalignments for the same feature. By boosting algorithm, the most discriminative feature bags, which consist of single features and their corresponding misalignment cases, are selected in the phase of classifier training. Based on those best feature bags, weak classifiers are generated and combined into the final ensemble classifier. Moreover, multiple instance learning is introduced to efficiently evaluate the discriminative ability of feature bags and train feature bag classifiers. The experimental results on public face dataset demonstrate that the proposed algorithm is more robust than the traditional method when the problem of feature misalignment is considered. Furthermore, compared to the feature bag with fixed size, the proposed multi-configuration feature bag models the feature misalignment better, gets smaller detector size while improving the detection accuracy.
李秋洁，茅耀斌，王执铨. 基于多配置特征包的目标检测[J]. 模式识别与人工智能, 2011, 24(6): 869-874.
LI Qiu-Jie, MAO Yao-Bin, WANG Zhi-Quan. Object Detection Based on Multi-Configuration Feature Bag. , 2011, 24(6): 869-874.
[1] Zhang Cha, Zhang Zhengyou. A Survey of Recent Advances in Face Detection. Technical Report, MSR-TR-2010-66. Redmond, USA: Microsoft Research, 2010 [2] Viola P, Jones M. Rapid Object Detection Using a Boosted Cascade of Simple Features // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Kauai, USA, 2001, I: 511-518 [3] Dalal N, Triggs B. Histograms of Oriented Gradients for Human Detection // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005, I: 886-893 [4] Viola P, Platt J C, Zhang C. Multiple Instance Boosting for Object Detection // Weiss Y, Schlkopf B, Platt J, eds. Advances in Neural Information Processing Systems. Cambridge, USA: MIT Press, 2006, XVIII: 1417-1424 [5] Babenko B, Yang M, Belongie S. Visual Tracking with Online Multiple Instance Learning // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 983-990 [6] Pang Junbiao, Huang Qingming, Jiang Shuqiang. Multiple Instance Boost Using Graph Embedding Based Decision Stump for Pedestrian Detection // Proc of the 10th European Conference on Computer Vision. Mareille, France, 2008: 541-552 [7] Dollar P, Babenko B, Belongie S, et al. Multiple Component Learning for Object Detection // Proc of the 10th European Conference on Computer Vision. Mareille, France, 2008: 211-224 [8] Lin Zhe, Hua Gang, Davis L S. Multiple Instance Feature for Robust Part-Based Object Detection // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Miami, USA, 2009: 405-412 [9] Dietterich T G, Lathrop R H, Lozano-Pérez T. Solving the Multiple-Instance Problem with Axis-Parallel Rectangles. Artificial Intelligence, 1997, 89(1/2): 31-71 [10] Zhou Zhihua. Multiply Instance Learning [EB/OL]. [2011-04-25]. http://cs.nju.cn/zhouzh/zhouzh.files/publication/ks03.pdf (in Chinese) (周志华.多示例学习[EB/OL]. [2011-04-25]. http://cs.nju.cn/zhouzh/zhouzh.files/publication/ks03.pdf) [11] Freund Y, Schapire R. A Decision-Theoretic Generalization of On-line Learning and an Application to Boosting. Journal of Computer and System Sciences, 1997, 55(1): 119-139
2011, Vol. 24 
