基于统计分类的行人检测方法综述

摘要/Abstract

摘要： 作为计算机视觉以及智能交通领域一个重要的研究方向,行人检测技术近年来受到业界广泛关注,其中基于统计分类的方法因为其检测效果好,得到了广泛应用。对基于统计分类的行人检测方法进行综述,归纳了目前用于行人检测的数据集,并给出了每个数据集中各种样本的分布情况;接着总结了行人检测方法中用于目标识别的行人特征及其改进方式;对行人检测主要分类器做了概述;指出了行人检测目前存在的问题并展望了未来的发展方向。

关键词: 综述, 行人检测, 统计分类, 数据集

Abstract: As one of the most important areas of research in the domain of computer vision and intelligent tranffic, pedestrian detection has attacted extensive interest from the research community in recent years. Because the detection based on statistical classification method is efficient, it has been widely applied. Pedestrian detection method was focused based on statistical classification. Standard dataset for evaluation of human detection was reviewed, studying the statistics about these dataset. Extracted features and the improvement on them were summarized. The main classifier for pedestrian detection was summarized. The present problems and future research trends in pedestrian detection were proposed.

Key words: survey, pedestrian detection, statistical classification, dataset

中图分类号:

TP391.41

李威, 王鹏杰, 宋海玉. 基于统计分类的行人检测方法综述[J]. 系统仿真学报, 2016, 28(9): 2186-2194.

Li Wei, Wang Pengjie, Song Haiyu. Survey on Pedestrian Detection Based on Statistical Classification[J]. Journal of System Simulation, 2016, 28(9): 2186-2194.

参考文献 48

[1]	N Brewer, L Andersson, N Pettersson.A new pedestrian dataset for supervised learning[C]// IEEE Intelligent Vehicles Symp., USA: IEEE, 2008.
[2]	C Papageorgiou, T Poggio.A trainable system for object detection[J]. Int. J. Comput.(S1573-1405), 2000, 38(1): 15-33.
[3]	P Viola, M Jones.Rapid object detection using a boosted cascade of simple features[C]// Proc. IEEE Conf. Computer. Vision and Pattern Recognition. USA: IEEE, 2001 (1): 511-518.
[4]	R Lienhart, J Maydt. An Extended Set of Haar-like Features for Rapid Object Detection [C]// International Conference on Image Processing. USA: IEEE, 2002, 1: I-900-I-903.
[5]	G Overett, L Petersson, L Andersson, et al.Boosting a heterogeneous pool of fast HOG features for pedestrian and sign detection[C]// Intelligent Vehicles Symposium IEEE. USA: IEEE, 2009: 584-590.
[6]	Gavrila D.Pedestrian detection from a moving vehicle[C]// Proceedings of European Conference Computer Vision. Dublin, Ireland: Lecture Notes in Computer Science, 2000: 37-49.
[7]	Gavrila D, Giebel J, Munder S.Vision-based pedestrian detection: the protector system[C]// Intelligent Vehicles Symposium, Parma, Italy. USA: IEEE Computer Society, 2004: 13-18.
[8]	Wu B, Nevatia R, Li Y.Segmentation of multiple, partially occluded objects by grouping, merging, assigning part detection responses[J]. Int’ l Journal of Computer Vision (S1573-1405), 2009(82): 185-204.
[9]	Gao W, Ai H Z, Lao S.Adaptive contour features in oriented granular space for human detection and segmentation[C]// Proceedings of IEEE Conference Computer Vision and Pattern Recognition. Miami, Florida, USA. USA: IEEE Computer Society, 2009: 1786-1793.
[10]	Sabzmeydani Payam. Mori, Greg Detecting Pedestrians by Learning Shapelet Features Computer Vision and Pattern Recognition (CVPR) [C]//2007 IEEE Conference on Minneapolis, MN (2007), USA. USA: IEEE, 2007.
[11]	Yu LP, Yao WT, Liu HP, et al.A Monocular Vision Based Pedestrian Detection System for Intelligent Vehicles[C]// IEEE Intelligent Vehicles Symposium, USA: IEEE, 2008.
[12]	N Dalal, B Triggs.Histograms of oriented gradients for human detection[C]// Proc. IEEE Int. Conf. CVPR. USA: IEEE, 2005: 886-893.
[13]	Dollar P, Belongie S, Perona P.The fastest pedestrian detector in the west[C]// Proceedings of British Machine Vision Conference. Aberystwyth, UK : Lecture Notes in Computer Science, 2010: 1-11.
[14]	Wojek C, Schiele B.A performance evaluation of single and multi-feature people detection[J]. Pattern Recognition (S0302-9743), 2008, 5096(1): 82-91.
[15]	Wu J F, Yang S, Zhang L.Pedestrian detection based on improved HOG feature and robust adaptive boosting algorithm[C]// Image and Signal Processing, Shanghai, China. USA: IEEE Computer Society, 2011: 1535-1539.
[16]	Zhu Q, Avidan S.Fast Human Detection Using a Cascade of Histograms of Oriented Gradients [C]// Anon. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. New York, USA, 2006. New York, USA: IEEE Computer Society Press, 2006, 2: 1491-1498.
[17]	Porikli F.Integral histogram: a fast way to extract histogram in cartesian spaces[C]// Proceedings of IEEE Conference Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE Computer Society, 2005: 829-836.
[18]	S Walk, N Majer, K Schindler, et al.New features and insights for pedestrian detection[C]// IEEE Conf. Computer Vision and Pattern Recognition. USA: IEEE, 2010: 1030-1037.
[19]	X Wang, T X Han, S Yan.A hog-lbp human detector with partial occlusion handling[C]// IEEE Intl. Conf. Computer Vision. USA: IEEE, 2009: 32-39.
[20]	车志富. 基于支持向量机的行人检测 [D]. 北京: 北京交通大学, 2010.
[21]	陶建峰. 基于多特征融合的行人检测方法研究 [D]. 南京: 南京理工大学, 2013.
[22]	王兴宝. 复杂场景下多姿态行人检测与识别方法研究[D]. 苏州: 苏州大学, 2012.
[23]	Cutler R, Davis L S.Robust real-time periodic motion detection, analysis and applications[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2000, 22(8): 781-796.
[24]	Wohler C, Kressler U, Anlauf J K.Pedestrian recognition by classifcation of image sequences: global approaches vs. local spatio-temporal processing[C]// Proceedings of 15th International Conference on Pattern Recognition. Barcelona, Spain. USA: IEEE, 2000, 2: 540-544.
[25]	Curio C, Edelbrunner J, Kalinke T, et al.Walking pedestrian recognition[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2000, 1(3): 155-163.
[26]	Ran Yang, Zheng Qin-Fen, Weiss I, et al.Pedestrian classifcation from moving platforms using cyclic motion pattern[C]// Proceedings of International Conference on Image Processing, Genoa, Italy. USA: IEEE, 2005, 2: 854-857.
[27]	Grubb G, Zelinsky A, Nilsson L, et al.3D vision sensing for improved pedestrian safety[C]// Proceedings of IEEE Intelligent Vehicles Symposium, Parma, Italy. USA: IEEE, 2004:19-24.
[28]	Oren M, Papageorgiou C, Sinha P, et al.Pedestrian detection using wavelet templates[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Juan, Puerto Rico. USA: IEEE, 1997: 193-199.
[29]	Maji S, Berg A, Malik J.Classification using intersection kernel SVMs is efficient[C]// Proceedings of IEEE Conference on Computer Vision and Patter Recognition, Anchorage, Alaska, USA. USA: IEEE Computer Society, 2008: 1-8.
[30]	Felzenszwalb P, Girshick R B, McAllester D, et al. Object detection with discriminaltively trained part based models[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence (S0162-8828), 2009, 32(9): 1627-1645.
[31]	Mohan A, Papageorgiou C, Poggio T.Example-based object detection in images by components[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2001, 23(4): 349-361.
[32]	Cheng Hong, Zheng Nanning, Qin Junjie.Pedestrian detection using sparse Gabor filter and support vector machine[C]// Proceedings of IEEE Intelligent Vehicles Symposium, Vienna, Austria. USA: IEEE, 2005: 583.
[33]	Dai Congxia, Zheng Yunfei, Li Xin.Layered representation for pedestrian detection and tracking in infrared imagery[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA. USA: IEEE, 2005, 3: 13.
[34]	Grubb G, Zelinsky A, Nilsson L, et al.3D vision sensing for improved pedestrian safety[C]// Proceedings of IEEE Intelligent Vehicles Symposium, Parma, Italy. USA: IEEE, 2004: 19-24.
[35]	Zhao Liang, Thorpe C.Stereo and neural network-based pedestrian detection[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2000, 1(3): 148-154.
[36]	Franke U, Joos A.Real-time stereo vision for urban traffic scene understanding[C]// Proceedings of IEEE Intelligent Vehicles Symposium, Dearborn, MI, USA. USA: IEEE, 2000: 273-278.
[37]	Szaras M, Yoshizawa A, Yamamoto M, et al.Pedestrian detection with convolutional neural networks[C]// Proceedings of IEEE Intelligent Vehicles Symposium. Las Vegas, Nevada, USA. USA: IEEE, 2005: 224-229.
[38]	Freund BY, Schapire RE.A Decision-theoretic Generalization of Online Learning and an Application to Boosting[J]. Journal of Computer and System Sciences,(S0022-0000), 1997, 55(1): 119-139.
[39]	Friedman J.Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics,(S0090-5364), 2001, 29(5): 1189-1232.
[40]	Paul viola, Michael Jones. Robust Real-time Object Detection[J]. International Journal of Computer Vision,(S0920-5691), 2001, 57(2): 87-112.
[41]	Abramson Y, Steux B.Hardware-friendly pedestrian detection and impact prediction[C]// Proceedings of IEEE Intelligent Vehicles Symposium. Parma, Italy. USA: IEEE, 2004: 590-595.
[42]	Shashua A, Gdalyahu Y, Hayun G.Pedestrian detection for driving assistance systems: single-frame classification and system level performance[C]// Proceedings of IEEE Intelligent Vehicles Symposium, Parma, Italy. USA: IEEE, 2004: 1-6.
[43]	K Mikolajczyk, Schmid C, Zisserman A.2004. Human detection based on a probabilistic assembly robust part detectors[C]// Proceeding of European Conference on Computer Vision. Prague, Czech Republic: Springer: 69-82.
[44]	Oren M, Papageorgiou C, Sinha P'Osuna E, et al. Pedestrian detection using wavelet templates[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. San Juan, Puerto Rico. USA: IEEE, 1997: 193-199.
[45]	王根岭. 行人检测与跟踪中若干关键技术的研究 [D].杭州: 浙江理工大学, 2014.
[46]	石娟峰. 基于视频的行人检测和跟踪 [D]. 北京: 北京邮电大学, 2012.
[47]	周千昊. 自然背景下的行人检测 [D]. 上海: 上海交通大学, 2009.
[48]	徐翠. 基于计算机视觉的汽车安全辅助驾驶若干关键问题研究 [D]. 合肥: 中国科学技术大学, 2009.