cvpr cvpr2013 cvpr2013-398 cvpr2013-398-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Wanli Ouyang, Xiaogang Wang
Abstract: In this paper, we address the challenging problem of detecting pedestrians who appear in groups and have interaction. A new approach is proposed for single-pedestrian detection aided by multi-pedestrian detection. A mixture model of multi-pedestrian detectors is designed to capture the unique visual cues which are formed by nearby multiple pedestrians but cannot be captured by single-pedestrian detectors. A probabilistic framework is proposed to model the relationship between the configurations estimated by single- and multi-pedestrian detectors, and to refine the single-pedestrian detection result with multi-pedestrian detection. It can integrate with any single-pedestrian detector without significantly increasing the computation load. 15 state-of-the-art single-pedestrian detection approaches are investigated on three widely used public datasets: Caltech, TUD-Brussels andETH. Experimental results show that our framework significantly improves all these approaches. The average improvement is 9% on the Caltech-Test dataset, 11% on the TUD-Brussels dataset and 17% on the ETH dataset in terms of average miss rate. The lowest average miss rate is reduced from 48% to 43% on the Caltech-Test dataset, from 55% to 50% on the TUD-Brussels dataset and from 51% to 41% on the ETH dataset.
[1] A. Bar-Hillel, D. Levi, E. Krupka, and C. Goldberg. Partbased feature synthesis for human detection. In ECCV, 2010. 2
[2] O. Barinova, V. Lempitsky, and P. Kohli. On detection of multiple object instances using hough transforms. In CVPR, 2010. 1, 2
[3] L. Bourdev and J. Malik. Poselets: body part detectors trained using 3D human pose annotations. In ICCV, 2009. 2
[4] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, 2005. 1, 2, 6, 8
[5] C. Desai, D. Ramanan, and C. Fowlkes. Discriminative models for multi-class object layout. In ICCV, 2009. 2
[6] Y. Ding and J. Xiao. Contextual boost for pedestrian detection. In CVPR, 2012. 2, 7
[7] S. K. Divvala, D. Hoiem, J. H. Hays, A. A. Efros, and M. Hebert. An empirical study of context in object detection. In CVPR, 2009. 2
[8] P. Doll a´r, S. Belongie, and P. Perona. The fastest pedestrian detector in the west. In BMVC, 2010. 6
[9] P. Doll a´r, Z. Tu, P. Perona, and S. Belongie. Integral channel features. In BMVC, 2009. 2, 6
[10] P. Doll a´r, C. Wojek, B. Schiele, and P. Perona. Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell., 34(4):743 761, 2012. 1, 6 M. Enzweiler and D. M. Gavrila. A multilevel mixture-ofexperts framework for pedestrian classification. IEEE Trans. Image Process., 20(10):2967–2979, 2011. 2 A. Ess, B. Leibe, and L. V. Gool. Depth and appearance for mobile scene analysis. In ICCV, 2007. 2, 6 P. Felzenszwalb, R. B. Grishick, D.McAllister, and D. Ramanan. Object detection with discriminatively trained part based models. IEEE Trans. Pattern Anal. Mach. Intell., 32:1627–1645, 2010. 1, 2, 4, 5, 6 P. F. Felzenszwalb and D. P. Huttenlocher. Pictorial structures for object recognition. Int’l J. Computer Vision, 61:55– 79, 2005. 2 C. Galleguillosy, B. McFeey, S. Belongiey, and G. Lanckriet. Multi-class object localization by combining local contextual interactions. In CVPR, 2010. 2 R. Girshick, P. Felzenszwalb, and D. McAllester. Object detection with grammar models. In NIPS, 2011. 2 A. Hare. Handbook of small group research. Macmillan, 1962. 1 C. Lampert, M. Blaschko, and T. Hofmann. Beyond sliding windows: object localization by efficient subwindow search. In CVPR, 2008. 2 –
[11]
[12]
[13]
[14]
[15]
[16]
[17]
[18] 333222000422 sareimt.25816430 −2false1p0oitv rmage974856 1207853 1HMCSFPLVakuhoiJPlsOtSnDaFgvWpelGSiRLIFtmnrbesvlp+−CVMto21SiE0naetrsm.18654320 −false1p0oitvrmage56789103 285% %1 MCLPHFVSuhaslkiOoJtnDgSlaGiFWvLepImntbrsvel+−MCtV1oS20iEn smierta.51468230−falsep1oitv0rmg456871236590 FLMHCPSV1alusiohJOPgtknD+SlsGFivLVOpWe+RItmbuMrnlOe−+vstuCVMOr1Su2+o−OtirEu0+n2 raetsim.18654320 −false1poitvr0mg657834902% 1 LMHPVS0FCaukiOo1hslJtSg+anDGVFieLOpvIWMtmnbur−+pels OrtV+CMu1oSr2ti−+OEu1nr02 (a) Caltech-Test (b) TUD-Brussels rsiaemt.12536480 956 7201547% % VMFLPHC SuhaOslioJtDkGSgnliWpeFvLItnmbrelvps+−tCVMS21o−Ein 10−3 10−2 10−1 100 101 false positives per image tmsriea.36285140 −2104657391860% %10 CHPSFL1MV tsuOlhaoPJki+GngtSlDipOeVLFvW+bIntmueMlrpO vs+−tuOV MCru2o1SO t+rui−OEn+ru false positives per image (c) ETH Figure 5. Detection results of existing approaches (top) and integrating them with our framework (bottom) on the datasets Caltech-Test (a), TUD-Brussels (b) and ETH (c). The results of integrating existing approaches with our framework are denoted by ’+Our’ . For example, the result of integrating HOG [4] with our framework is denoted by HOG+Our.
[19] C. Li, D. Parikh, and T. Chen. Extracting adaptive contextual cues from unlabeled regions. In ICCV, pages 511–5 18. IEEE, 2011. 2
[20] Z. Lin and L. Davis. A pose-invariant descriptor for human detection and segmentation. In ECCV, 2008. 6
[21] S. Maji, A. C. Berg, and J. Malik. Classification using intersection kernel support vector machines is efficient. In CVPR, 2008. 2, 6
[22] M. Moussaid, N. Perozo, S. Garnier, D. Helbing, and G. Theraulaz. The walking behaviour of pedestrian social groups and its impact on crowd dynamics. PLoS ONE, 5(4):e10047, 2010. 1, 3
[23] W. Ouyang and X. Wang. A discriminative deep model
[24]
[25]
[26]
[27]
[28]
[29]
[30] [3 1]
[32]
[33]
[34]
[35] for pedestrian detection with occlusion handling. In CVPR, 2012. 2 W. Ouyang, X. Zeng, and X. Wang. Modeling mutual visibility relationship in pedestrian detection. In CVPR, 2013. 2 D. Park, D. Ramanan, and C. Fowlkes. Multiresolution models for object detection. In ECCV, 2010. 2, 6, 7 F. Porikli. Integral histogram: a fast way to extract histograms in cartesian spaces. In CVPR, 2005. 2 P. Sabzmeydani and G. Mori. Detecting pedestrians by learning shapelet features. In CVPR, 2007. 2, 6 W. Schwartz, A. Kembhavi, D. Harwood, and L. Davis. Human detection using partial least squares analysis. In ICCV, 2009. 2, 6 Z. Song, Q. Chen, Z. Huang, Y. Hua, and S. Yan. Contextualizing object detection and classification. In CVPR, 2011. 2 S. Tang, M. Andriluka, and B. Schiele. Detection and tracking of occluded people. In BMVC, Surrey, UK, 2012. 2 O. Tuzel, F. Porikli, and P. Meer. Pedestrian detection via classification on riemannian manifolds. IEEE Trans. Pattern Anal. Mach. Intell., 30(10): 1713–1727, Oct. 2008. 1, 2 P. Viola, M. J. Jones, and D. Snow. Detecting pedestrians using patterns of motion and appearance. Int’l J. Computer Vision, 63(2): 153–161, 2005. 2, 6 S. Walk, N. Majer, K. Schindler, and B. Schiele. New features and insights for pedestrian detection. In CVPR, 2010. 2, 6, 7 X. Wang, X. Han, and S. Yan. An hog-lbp human detector with partial occlusion handling. In CVPR, 2009. 1, 2, 6 C. Wojek and B. Schiele. A performance evaluation of single
[36]
[37]
[38]
[39]
[40]
[41]
[42]
[43] and multi-feature people detection. In DAGM, 2008. 6 C. Wojek, S. Walk, and B. Schiele. Multi-cue onboard pedestrian detection. In CVPR, 2009. 6 B. Wu and R. Nevatia. Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors. In ICCV, 2005. 2 B. Wu and R. Nevatia. Detection and tracking of multiple, partially occluded humans by bayesian combination of edgelet based part detectors. Int’l J. Computer Vision, 75(2):247–266, 2007. 2 J. Yan, Z. Lei, D. Yi, and S. Z. Li. Multi-pedestrian detection in crowded scenes: A global view. In CVPR, 2012. 2 Y. Yang, S. Baker, A. Kannan, and D. Ramanan. Recognizing proxemics in personal photos. In CVPR, 2012. 2 Y. Yang and D. Ramanan. Articulated pose estimation with flexible mixtures-of-parts. In CVPR, 2011. 2 B. Yao and L. Fei-Fei. Modeling mutual context of object and human pose in human-object interaction activities. In CVPR, 2010. 2 L. Zhu, Y. Chen, A. Yuille, and W. Freeman. Latent hierarchical structural learning for object detection. In CVPR, 2010. 2 333222000533