Human Detection Method Based on Multi-Part Detector and Multi-Instance Learning
DING Jian-Hao1,2, GENG Wei-Dong1, WANG Yi-Gang2
1. State Key Laboratory of CAD CG,Zhejiang University,Hangzhou 310027 2.Institute of Computer Graphics and Image Processing,Hangzhou Dianzi University,Hangzhou 310018
Abstract:Part-based detection methods can deal with large articulated pose variations of human target and partial occlusions. Multi-instance learning is employed in content-based image retrieval and scene understanding, because it is good at handling the inherent ambiguity of images.A human detection method based on multi-part and multi-instance learning methods is presented. Firstly, the training samples are partitioned into several regions containing multi-instance according to body structure. Then, the part detectors are trained by using multiple instance learning method based on AdaBoost algorithm. After that the responding scores from the training samples tests are obtained by using the individual part detector when predicting on the positive and negative training bags. Therefore, the training samples are converted to feature vectors composed of part scores. The final assemble detector is learned using a linear SVM method. The experimental results on INRIA database show that the proposed approach improves the detection performance in single instance learning and the influence of the three different multi-part divisions on detection performance is evaluated.
[1] Dalal N,Triggs B.Histograms of Oriented Gradients for Human Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.San Diego,USA,2005: 886-893 [2] Xu Ran,Zhang Baochang,Ye Qixiang,et al.Cascaded L1-Norm Minimization Learning (CLML) Classifier for Human Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.San Francisco,USA,2010: 89-96 [3] Felzenszwalb P.Girshick R,McAllester D.Cascade Object Detection with Deformable Part Models // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.San Francisco,USA,2010: 2241-2248 [4] Singh V,Nevatia R,Huang Chang.Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation // Proc of the European Conference on Computer Vision.Heraklion,Greece,2010,III: 314-327 [5] Dietterich T G,Lathrop R H,Lozano P T.Solving the Multiple Instance Problem with Axis-Parallel Rectangles.IEEE Trans on Artificial Intelligence,1997,89 (1/2): 31-71 [6] Maron O,Lozano-Perez T.A Framework for Multiple-Instance Learning // Jordan M J,Kearns M J,Solla S A,eds.Advances in Neural Information Processing Systems.Cambridge,USA: MIT Press,1998,X: 570-576 [7] Zhou Zhihua,Zhang Minling.Multi-Instance Multi-Label Learning with Application to Scene Classification // Schlkopf B,Platt J,Hofmann T,eds.Advances in Neural Information Processing Systems.Cambridge,USA: MIT Press,2006,XIX: 1609-1616 [8] Vezhnevets A,Buhmann J.Towards Weakly Supervised Semantic Segmentation by Means of Multiple Instance and Multitask Learning // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.San Francisco,USA,2010: 3249- 3256 [9] Babenko B,Yang M H,Belongie S.Visual Tracking with Online Multiple Instance Learning // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Miami Beach,USA,2009: 983-990 [10] Zhang Q,Goldman S A.EM-DD: An Improved Multiple-Instance Learning Technique // Becker S,Thrn S,Obermayer K,eds.Advances in Neural Information Processing Systems.Cambridge,USA: MIT Press,2002,XV: 1073-1080 [11] Dollar P,Babenko B,Belongie S,Perona P,Tu Z.Multiple Component Learning for Object Detection // Proc of the European Conference on Computer Vision.Marseille,France,2008,II: 211-224 [12] Pang Junbiao,Huang Qingming,Jiang Shuqiang,et al.Pedestrian Detection via Logistic Multiple Instance Boosting // Proc of the International Conference on Image Processing.San Diego,USA,2008: 1464-1467 [13] Lin Z,Hua G,Davis L S.Multiple Instance Feature for Robust Part-Based Object Detection // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Miami Beach,USA,2009: 405- 412 [14] Chen Yuting,Chen Chusong,Huang Yiping,et al.Multi-Class Multi-Instance Boosting for Part Based Human Detection // Proc of the IEEE International Workshop on Visual Surveillance.Kyoto,Japan,2009: 1177-1184 [15] Mohan A,Papageorgiou C,Poggio T.Example Based Object Detection in Images by Components.IEEE Trans on Pattern Analysis and Machine Intelligence,2001,23(4): 349-36 [16] Mikolajczyk K,Schmid C,Zisserman A.Human Detection Based on a Probabilistic Assembly of Robust part Detectors // Proc of the European Conference on Computer Vision.Prague,Czech Republic,2004: 69-82 [17] Bo W,Nevatia R.Detection of Multiple,Partially Occluded Humans in a Single Image by Bayesian Combination of Edgelet Part Detectors // Proc of the IEEE International Conference on Computer Vision.Beijing,China,2000: 90-97 [18] Leibe B,Leonardis A,Schiele B.Pedestrian Detection in Crowded Scenes // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.San Diego,USA,2005: 878-885 [19] Lin Z,Davis L S,Doermann D,et al.Hierarchical Part-Template Matching for Human Detection and Segmentation // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Rio de Janeiro,Brazil,2007: 1152-1159 [20] Lee D D,Seung H S.Learning the Parts of Objects by Non-Negative Matrix Factorization.Nature,1999,401(6755): 788-791 [21] Viola P,Jones M.Rapid Object Detection Using a Boosted Cascade of Simple Features // Proc of the IEEE Conference on Computer Vision and Pattern Recognition.Kauai,USA,2001: 1511- 1518 [22] Viola P,Platt J,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,2005,XVIII: 1417-1424 [23] Hu Bin,Wang Shengjin,Ding Xiaoqing.Pedestrian Detection Method Based on Part Detector and Substructure Assemble.Computer Science,2009,11(3): 242-246 (in Chinese) (胡 斌,王生进,丁晓青.基于部位检测和子结构组合的行人检测方法.计算机科学,2009,11(3): 242-246)