基于单目视觉的人体检测和运动恢复
|
摘要
人体检测与运动恢复是当前人工智能和计算机视觉领域研究的热点,已广泛应用于车载辅助系统、智能监控系统、人机交互以及体育运动训练等领域。对人体检测问题的有效解决能够为其他对象检测提供借鉴。直接从图像或视频中获取人体运动数据,不仅降低动作获取成本,同时,也使用户可以从大量的视频源中挖掘更多的潜在信息。
基于单目视觉的人体检测与运动恢复技术主要面临以下三个难点：1)人体数据中噪声所占比例大,每帧中待检测窗口数量大,且人体所占比例极少；2)人体数据及动作具有非常大的类内散度,包括人体形态上的差异与动作差异；3)人体运动目标从三维投影到二维会造成深度信息丢失,且检测结果容易受复杂背景、遮挡、光照和外观变化影响。
本文围绕基于单目视觉的人体检测、骨架抽取与运动恢复这一主线,借鉴当前一些特征抽取、机器学习、运动恢复的主流技术,提出了若干改进方法,论文的主要工作如下：
(1)提出一种混合特征的人体特征描述子及快速的人体检测器。在面对复杂背景,光照及外观变化较大的场景时,单特征描述的人体检测器描述能力有限,难以满足高检率、低误报率的要求。本文通过融合图像梯度方向直方图特征与Census变换特征来提高分类器的鲁棒性。基于Adaboost学习的分类器训练过程较慢,针对此问题,通过快速特征选择、双阈值判决两方面的改进,提高了分类器的训练时间。在检测速度上,从分类器设计及目标窗口特征计算两方面做了改进。利用Cascade结构构造分类器,采用逐级排除非人体目标的策略,提高分类器检测速度。提出基于“块”更新的目标扫描策略,当检测窗口在待检测图像上滑动扫描时,只对窗口变化区域的“块”重新提取特征,计算其直方图分布来加速检测过程。实验结果表明,改进后的基于混合特征的级联AdaBoost人体检测器,可以检测静态图像中各种分辨率下的人体目标。与单特征的人体检测方法相比,在公开数据集上验证了本文方法在检测性能与检测速度上均有所提高。
(2)提出一种基于多示例学习的多部位人体检测方法。由于整体滑动窗口检测方法忽略了人体的非刚性,其特征描述是建立在一个矩形窗口上。所以在处理多姿势、部分遮挡、视角变化等人体目标时鲁棒性不高。本文对基于部位的人体检测算法进行改进,根据生理结构将图像分割成若干区域,每个区域包含多个示例,利用AdaBoost多示例学习算法来训练部位检测器。然后利用各部位检测器对训练样本进行测试得到其响应值,从而将训练样本转化为部位响应值组成的低维特征向量。再用SVM方法对这些样本部位向量进行学习,最终形成部位组合分类器。在INRIA数据集上的实验结果表明,算法能改进单示例学习的检测性能,能检测出部分被遮挡的人体目标。同时评价了3种不同部位划分及其对检测性能的影响。
(3)提出基于单目视觉的无标记、无初始化的人体运动恢复方法。在现有的无标记单目视频运动恢复方法中,需要在初始帧进行手工初始化。很多基于概率模型或基于学习的方法,存在着计算复杂度过高或依赖样例库等问题。本文的运动恢复工作包括直接从图像信息中抽取骨架,估计关节点初始二维坐标,并进一步恢复人体三维坐标等操作。首先,利用图像梯度变换方法从单目视频图像中自动抽取人体的线形骨架,并利用人体生理特征骨骼比例关系对骨架的主要关节点位置进行估计,从而在初始帧避免人工初始化。在比例正交投影的假设下对三维人体运动信息进行恢复,通过计算适用于人体比例因子来对每段骨骼进行恢复,利用卡尔曼滤波对每段骨骼运动进行跟踪。本方法无需对摄像机进行标定,无需专门辅助设备,对数据环境也无特殊要求。
Nowadays Human detection and motion recovery is one of the most active topics in artificial intelligence and computer vision community. The research have made a significant impact in many different disciplines, such as on-board driving assistance system, smart surveillance system, user interfaces, and motion analysis in sports training etc. The effective solutions to human detection issues can also facilitate other object detections. Capturing the human motion from the videos significantly reduces the cost of motion capture. Moreover, due to the wide range of the video sources, it also helps the users to find more underlying information.
Currently human detection and motion recovery from monocular mainly face three challenges:1) Human data is greatly occupied by the noise. Besides, there exist a big amount of detecting window need to be classified in a single frame, however, most space in the frame is non-pedestrian;2) Human data and motion possesses a lot inner-class variation, including both pose variation and action variation;3) The depth information could be lost while the3D objects being projected onto a2D image. Furthermore, the detection results are easily affected by the complex background, occluding, lighting or changing from the appearance.
This thesis is following the main line of human detection, skeleton extraction and motion recovery in monocular video. Inspired by recent key techniques of feature abstraction, machine learning and motion recovery, we present several improved approaches. The main work is summarized as follows:
(1) We propose a mixed feature descriptor and fast detector for human detection. While facing the scene with complex background, various lighting or fast changing appearance, human detection system based on a single feature descriptor can not meet the requirements of efficient detecting and low false alarm rate. We improve the robustness of human detector by concatenating the histogram of oriented gradients (HOG) and the histogram of census transform (CT) of images. In view of the problem of the slow training time of AdaBoost learning method, we improve the training speed by optimizing quick feature selection and dual threshold value selection. In the respect of detecting speed, we improve the design of the classifier and modify the feature calculation for the target window. We train the cascade structure classifier, which excludes the non-human target by coarse-to-fine strategy, to reduce the detecting time. Moreover, we also proposed a target scanning approach based on "block" updating to speed up the process of detection. More specifically, when the scanning window is sliding on the test image, our approach only extracts the feature from the changed "blocks" and re-calculates the histogram distribution. Experimental results indicate that the improved human detector based on the combined feature descriptor and cascade AdaBoost can detect the human target from various resolution static images. We apply our approach on INRIA person dataset and compare it with the method of single feature descriptor. The results show that our approach is obviously better in both the performance and detecting speed.
(2) We propose a human detection method based on multi-part and multi-instance learning method. The global-based sliding window detection approach neglects the non rigidness of human as the feature descriptor is extracted from a rectangle window. For this reason, the approach is not robust enough in some cases, for example when it has various pose, when the human target is partly occluded or when the view direction is changed. We propose an improved algorithm for part-based human detecting method. Specifically the training samples are partitioned into several regions which per contains multiple instances according to the real body structure. Then the part detectors are trained using multi-instance learning method based on AdaBoost algorithm. Part detectors are used individually to obtain the responding scores when predicting on the training bags. Therefore, the training samples are converted to low dimension feature vectors which are composed by part scores. The final assemble detector is learned using a linear SVM method. Experiments on INRIA dataset show that our approach improves the detection performance of the single instance learning method and can successfully detect partly-occluded human. Finally we evaluate the detection performance on the three different multi-part divisions.
(3) We propose a markless and uninitialized method to restore human motion from monocular. The traditional markless approaches based on monocular need to manually set the initial position at the first frame. A lot of approaches based on probability model or learning methods pose some problems, such as high computation complexity and over depending on the training example databases. The proposed motion recovery method in this thesis has several steps:directly extracting skeleton from image, measuring the initial2D coordinates of joints and further recovering the original3D coordinates. More specifically, by using the gradient of distance transform of image, the linear skeleton of the human body is automatically extracted from monocular video images. The positions of joints are determined by using the pre-knowledge of the anthropotomy. Therefore, we avoid initializing the positions of joints to recover the3D position at the first frame. In the assumptions of the scaled orthogonal projection model, we recover the human motion. We calculate the scale factor of the entire body according to the length of the joints of a customized human skeleton model. This scale factor is later used for restoring the position of each bone. Finally, each bone is tracked through kalman filters. The present method does not have any special requirements of camera pre-setting, auxiliary equipment or data context.
基于单目视觉的人体检测与运动恢复技术主要面临以下三个难点：1)人体数据中噪声所占比例大,每帧中待检测窗口数量大,且人体所占比例极少；2)人体数据及动作具有非常大的类内散度,包括人体形态上的差异与动作差异；3)人体运动目标从三维投影到二维会造成深度信息丢失,且检测结果容易受复杂背景、遮挡、光照和外观变化影响。
本文围绕基于单目视觉的人体检测、骨架抽取与运动恢复这一主线,借鉴当前一些特征抽取、机器学习、运动恢复的主流技术,提出了若干改进方法,论文的主要工作如下：
(1)提出一种混合特征的人体特征描述子及快速的人体检测器。在面对复杂背景,光照及外观变化较大的场景时,单特征描述的人体检测器描述能力有限,难以满足高检率、低误报率的要求。本文通过融合图像梯度方向直方图特征与Census变换特征来提高分类器的鲁棒性。基于Adaboost学习的分类器训练过程较慢,针对此问题,通过快速特征选择、双阈值判决两方面的改进,提高了分类器的训练时间。在检测速度上,从分类器设计及目标窗口特征计算两方面做了改进。利用Cascade结构构造分类器,采用逐级排除非人体目标的策略,提高分类器检测速度。提出基于“块”更新的目标扫描策略,当检测窗口在待检测图像上滑动扫描时,只对窗口变化区域的“块”重新提取特征,计算其直方图分布来加速检测过程。实验结果表明,改进后的基于混合特征的级联AdaBoost人体检测器,可以检测静态图像中各种分辨率下的人体目标。与单特征的人体检测方法相比,在公开数据集上验证了本文方法在检测性能与检测速度上均有所提高。
(2)提出一种基于多示例学习的多部位人体检测方法。由于整体滑动窗口检测方法忽略了人体的非刚性,其特征描述是建立在一个矩形窗口上。所以在处理多姿势、部分遮挡、视角变化等人体目标时鲁棒性不高。本文对基于部位的人体检测算法进行改进,根据生理结构将图像分割成若干区域,每个区域包含多个示例,利用AdaBoost多示例学习算法来训练部位检测器。然后利用各部位检测器对训练样本进行测试得到其响应值,从而将训练样本转化为部位响应值组成的低维特征向量。再用SVM方法对这些样本部位向量进行学习,最终形成部位组合分类器。在INRIA数据集上的实验结果表明,算法能改进单示例学习的检测性能,能检测出部分被遮挡的人体目标。同时评价了3种不同部位划分及其对检测性能的影响。
(3)提出基于单目视觉的无标记、无初始化的人体运动恢复方法。在现有的无标记单目视频运动恢复方法中,需要在初始帧进行手工初始化。很多基于概率模型或基于学习的方法,存在着计算复杂度过高或依赖样例库等问题。本文的运动恢复工作包括直接从图像信息中抽取骨架,估计关节点初始二维坐标,并进一步恢复人体三维坐标等操作。首先,利用图像梯度变换方法从单目视频图像中自动抽取人体的线形骨架,并利用人体生理特征骨骼比例关系对骨架的主要关节点位置进行估计,从而在初始帧避免人工初始化。在比例正交投影的假设下对三维人体运动信息进行恢复,通过计算适用于人体比例因子来对每段骨骼进行恢复,利用卡尔曼滤波对每段骨骼运动进行跟踪。本方法无需对摄像机进行标定,无需专门辅助设备,对数据环境也无特殊要求。
Nowadays Human detection and motion recovery is one of the most active topics in artificial intelligence and computer vision community. The research have made a significant impact in many different disciplines, such as on-board driving assistance system, smart surveillance system, user interfaces, and motion analysis in sports training etc. The effective solutions to human detection issues can also facilitate other object detections. Capturing the human motion from the videos significantly reduces the cost of motion capture. Moreover, due to the wide range of the video sources, it also helps the users to find more underlying information.
Currently human detection and motion recovery from monocular mainly face three challenges:1) Human data is greatly occupied by the noise. Besides, there exist a big amount of detecting window need to be classified in a single frame, however, most space in the frame is non-pedestrian;2) Human data and motion possesses a lot inner-class variation, including both pose variation and action variation;3) The depth information could be lost while the3D objects being projected onto a2D image. Furthermore, the detection results are easily affected by the complex background, occluding, lighting or changing from the appearance.
This thesis is following the main line of human detection, skeleton extraction and motion recovery in monocular video. Inspired by recent key techniques of feature abstraction, machine learning and motion recovery, we present several improved approaches. The main work is summarized as follows:
(1) We propose a mixed feature descriptor and fast detector for human detection. While facing the scene with complex background, various lighting or fast changing appearance, human detection system based on a single feature descriptor can not meet the requirements of efficient detecting and low false alarm rate. We improve the robustness of human detector by concatenating the histogram of oriented gradients (HOG) and the histogram of census transform (CT) of images. In view of the problem of the slow training time of AdaBoost learning method, we improve the training speed by optimizing quick feature selection and dual threshold value selection. In the respect of detecting speed, we improve the design of the classifier and modify the feature calculation for the target window. We train the cascade structure classifier, which excludes the non-human target by coarse-to-fine strategy, to reduce the detecting time. Moreover, we also proposed a target scanning approach based on "block" updating to speed up the process of detection. More specifically, when the scanning window is sliding on the test image, our approach only extracts the feature from the changed "blocks" and re-calculates the histogram distribution. Experimental results indicate that the improved human detector based on the combined feature descriptor and cascade AdaBoost can detect the human target from various resolution static images. We apply our approach on INRIA person dataset and compare it with the method of single feature descriptor. The results show that our approach is obviously better in both the performance and detecting speed.
(2) We propose a human detection method based on multi-part and multi-instance learning method. The global-based sliding window detection approach neglects the non rigidness of human as the feature descriptor is extracted from a rectangle window. For this reason, the approach is not robust enough in some cases, for example when it has various pose, when the human target is partly occluded or when the view direction is changed. We propose an improved algorithm for part-based human detecting method. Specifically the training samples are partitioned into several regions which per contains multiple instances according to the real body structure. Then the part detectors are trained using multi-instance learning method based on AdaBoost algorithm. Part detectors are used individually to obtain the responding scores when predicting on the training bags. Therefore, the training samples are converted to low dimension feature vectors which are composed by part scores. The final assemble detector is learned using a linear SVM method. Experiments on INRIA dataset show that our approach improves the detection performance of the single instance learning method and can successfully detect partly-occluded human. Finally we evaluate the detection performance on the three different multi-part divisions.
(3) We propose a markless and uninitialized method to restore human motion from monocular. The traditional markless approaches based on monocular need to manually set the initial position at the first frame. A lot of approaches based on probability model or learning methods pose some problems, such as high computation complexity and over depending on the training example databases. The proposed motion recovery method in this thesis has several steps:directly extracting skeleton from image, measuring the initial2D coordinates of joints and further recovering the original3D coordinates. More specifically, by using the gradient of distance transform of image, the linear skeleton of the human body is automatically extracted from monocular video images. The positions of joints are determined by using the pre-knowledge of the anthropotomy. Therefore, we avoid initializing the positions of joints to recover the3D position at the first frame. In the assumptions of the scaled orthogonal projection model, we recover the human motion. We calculate the scale factor of the entire body according to the length of the joints of a customized human skeleton model. This scale factor is later used for restoring the position of each bone. Finally, each bone is tracked through kalman filters. The present method does not have any special requirements of camera pre-setting, auxiliary equipment or data context.
引文
[1]D. Geronimo, A.M. Lopez, A.D. Sappa, T. Graf. Survey of Pedestrian Detection for Advanced Driver Assistance Systems[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(7):1239-1258.
[2]T.B. Moeslund, A.Hilton, V Kruger. A survey of advances in vision-based human motion capture and analysis[J]. Computer Vision and Image Understanding 2006,1 04(2-3):90-126.
[3]R.Poppe. Vision-based human motion analysis:An overview[J]. Computer Vision and Image Understanding,2007,108(1-2):4-18.
[4]M. Enzweiler, D. M. Gavrila. Monocular Pedestrian Detection:Survey and Experiments[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2009: 2179-2195.
[5]Dollar P, Wojek C, Schiele B, et al. Pedestrian detection:an evaluation of the state of the art[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2011, 99:1-20.
[6]许言午.面向行人检测的组合分类计算模型与应用研究.中国科技大学博士学位论文[D],2009年5月.
[7]Pedro F. Felzenszwalb, Daniel P. Huttenlocher. Efficient Matching of Pictorial Structures[C]. Proc. IEEE Conf Computer Vision and Pattern Recognition,2000: 66-73.
[8]D.M. Gavrila, V.Philomin. Real-Time Object Detection for "Smart" Vehicles[C]. IEEE International Conference on Computer Vision,1999,1:87-93.
[9]Curio C, Edelbrunner J, Kalinke T, Tzomakas C, Bruckhoff C, Bergener T, Seelen W. walking pedestrian recognition[J]. IEEE Transactions on Intelligent Transport Systems,2000,1:155-163.
[10]Cutler R, Davis L S. Robust real-time periodic motion detection, analysis and applications [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22:781-796.
[11]Wohler C, Kressler U and AnlaufJ K. Pedestrian recognition by classification of image sequences:global approaches vs. local spatio-temporal processing[C]. Proceedings of 15th International Conference on Pattern Recognition,2000, 2:540-544.
[12]刘亚洲.基于时空分析和多粒度特征表示的人体检测方法研究[D].哈尔滨工业大学博士学位论文,2009年9月.
[13]陈坚.单目视频人体运动跟踪和获取技术研究[D].中国科学院研究生院博士学位论文,2005年5月.
[14]李娜.面向人机交互的单目视频三维人体姿态估计研究[D].浙江大学博士学位论文,2008年7月.
[15]陈姝.基于视频的人体运动跟踪与重构方法研究[D].中南大学博士论文,2008年12月.
[16]Ferrari V, Marln-Jimnez M J, Zisserman A. Pose Search:Retrieving People Using Their Pose[C]. In Proc of IEEE Conference on Computer Vision and Pattern Recognition,2009:1-8.
[17]Singh M, Mandal M, Basu A. Pose Recognition Using the Radon Transform[C]. In Proc of Midwest Symposium on Circuits and Systems,2005:1091-1094.
[18]Jiang Hao. Human Pose Estimation Using Consistent Max Covering[C]. In Proc of International Conference on Image Processing,2007:357-360.
[19]Daubney B, Gibson D, Campbell N. Monocular 3D Human Pose Estimation Using Sparse Motion Features [C]. In Proc of International Conference on Computer Vision,2009:1050-1057.
[20]Andriluka M, Roth S, Schiele B. Monocular 3D Pose Estimation and Tracking by Detection[C]. In Proc of IEEE Conference on Computer Vision and Pattern Recognition,2010:623-630.
[21]Wang Yi, Qian Gang. Robust Human Pose Recognition Using Unlabeled Markers[C]. In Proc of Workshop on Application of Computer Vision,2008:1-7.
[22]Kohli P, Rihan J, Bray M, et al. Simultaneous Segmentation and Pose Estimation of Humans using Dynamic Graph Cuts[J]. International Journal of Computer Vision,2008,79(3):285-298.
[23]Okada R, Soatto S. Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images[C]. In Proc of European Conference on Computer Vision,2008:434-445.
[24]Chen Cheng, Yang Yi, Nie Feiping, et al.3d Human Pose Recovery from Image by Efficient Visual Feature Selection[J]. Computer Vision and Image Understanding,2011,115(3):290-299.
[25]C.Sminchisescu, B.Triggs. A Robust Multiple Hypothesis Approach to Monocular Human Motion Tracking [C]. INRIA Research Report,2001.
[26]C.Sminchisescu, B.Triggs. Variational Mixture Smoothing for Non-Linear Dynamical Systems[C]. IEEE International Conference on Computer Vision and Pattern Recognition,2004,Ⅱ:608-615.
[27]Balan, A. Black, M.J. An adaptive appearance model approach for model based articulated object tracking[C]. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition,2006,1:758-765.
[28]罗忠祥,庄越挺,刘丰.基于视频的人体动画[J].计算机研究与发展,2003,40(2)：269-276.
[29]刘钢,彭群生,鲍虎军.基于图像建模技术研究综述与展望[J].计算机辅助设计与图形学学报,2005,17(1):18-27.
[30]陈成.基于视频的人体三维运动恢复相关技术研究[D].浙江大学博士学位论文,2009年1月.
[31]http://nlpr-web.ia.ac.cn/index.asp.
[32]Minglei Tong, Yuncai Liu, Thomas.S.Huang.3D Human Model and Joint Parameter Estimation from Monocular Image[J].Pattern Recognition Letters, 2007,28(7):797-805.
[33]仝明磊.非标定单目序列图像的三维人体运动分析[D].上海交通大学博士论文,2007年10月.
[34]王文中,王兆其,邓小明,夏时洪,邱显杰.基于局部先验模型的单目视频人 体运动跟踪[J].计算机辅助设计与图形学学报,2011,23(9):1545-1552.
[35]苏延超,艾海舟,劳世竑.图像和视频中基于部件检测器的人体姿态估计[J].电子与信息学报,2011,33(6)：1413-1419.
[36]邹北骥,陈姝,彭小宁,史操.适用于单目视频的无标记三维人体运动跟踪[J].计算机辅助设计与图形学学报,2008,20(8):1047-1055.
[37]Devi Parikh, C. Lawrence Zitnick. The role of features, algorithms and data in visual recognition[J]. In CVPR,2010,2328-2335.
[38]P.Viola, M.Jones. Rapid Object Detection using a Boosted Cascade of Simple Features[C]. In Proceeding of International Conference on Computer Vision and Pattern Recognition,2001,1:511-518.
[39]P.Viola, M.Jones, D. Snow. Detecting Pedestrians Using Patterns of Motion and Appearance[J]. International Journal of Computer Vision,2005,63(2):153-161.
[40]S.Belongie, J.Malik, J.Puzicha. Shape matching and object recognition using shape contexts[J]. IEEE Trans. Pattern Anal. Mach.Intell.,2002,24(4):509-522.
[41]Gavrila D M, Giebel J. Shape-based pedestrian detection and tracking[C]. Intelligent Vehicle Symposium,2002,1(17-21):8-14.
[42]Bertozzi M, Broggi A, Chapuis R. Shape-based pedestrian detection and localization [J]. Intelligent Transportation Systems,2003,1:328-333.
[43]Leibe B, Seemann E, Schiele B. Pedestrian detection in crowded scenes[C]. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005,20-25.
[44]N. Dalal, B. Triggs. Histograms of oriented gradients for human detection[C]. In CVPR,2005,1:886-893.
[45]Q. Zhu, M.C. Yeh, K.T. Cheng, and S. Avidan. Fast human detection using a cascade of histograms of oriented gradients[C]. In CVPR,2006:1491-1498.
[46]R.Zabih, J.Woodfill. A non-parametric approach to visual correspondence [J]. IEEE Transactions on Pattern Analysis and Machine intelligence,1996.
[47]Wu J X, Rehg J M. CENTRIST:A visual descriptor for scene categorization [J]. IEEE Trans, on Pattern Analysis and Machine Intelligent,2011,33(8):1489-1501.
[48]Wu J X, Greyer C, Rehg J M. Real-time human detection using contour cues[A]. In Proc. IEEE ICRA,2011:860-867.
[49]T.Ojala, M.Pietik"ainen, D.Harwood. A comparative study of texture measures with classification based on featured distributions[J]. Pattern Recognition,1996, 29(1):51-59.
[50]Yadong Mu, Shuicheng Yan, Yi Liu, Thomas Huang, Bingfeng Zhou. Unsupervised Learning of Human Perspective Context Using ME-DT for Efficient Human Detection in Surveillance [C]. In CVPR,2008:1-8.
[51]N.Dalal, B.Triggs, C.Schmid. Human Detection Using Oriented Histograms of Flow and Appearance[C]. European Conference on Computer Vision,2006(2): 428-441.
[52]C.Wojek, S.Walk, B.Schiele. Multi-cue Onboard Pedestrian Detection[C]. IEEE Conference on Computer Vision and Pattern Recognition,2009:794-801.
[53]O.Javed, M.Shah. Tracking and Object Classification for Automated Surveillance[C]. In Proc Seventh European Conference on Computer Vision,2002, IV:343-357.
[54]Dollar P, Rabaud V, Cotterll G, Belongie S. Behavior recognition via sparse spatio-temporal features[C]. In 2nd joint IEEE International workshop on Visual Surveillance and Performance Evaluation of tracking and Surveillance, 2005:65-72.
[55]朱谊强.基于AdaBoost算法的实时性人检测系统[D].西北工业大学硕士学位论文,2006年4月.
[56]Yazhou Liu, Xilin Chen, Hongxun Yao, Xinyi Cui, Chaoran Liu, Wen Gao. Contour-motion feature(CMF):A space-time approach for robust pedestrian detection[J]. Pattern Recognition Letters(PRL),2009,30(2):148-156.
[57]ZHU Guang-yu, XU Chang-shen. Action recognition in broadcast tennis video[C]. In Proc of the 18th International Conference on Pattern Recognition,2006: 251-254.
[58]Laptev I, Lindeberg T. Local descriptors for spatio-temporal recognition[C]. In First International Workshop on Spatial Coherence for Visual Motion Analysis, 2004:91-103.
[59]苏松志,李绍滋,陈淑媛,蔡国榕,吴云东.行人检测技术综述[J].电子学报,2012(40)：814-820.
[60]B.Wu, R.Nevatia. Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors[C]. IEEE International Conference on Computer Vision,2005,1:90-97.
[61]Gavrila D. A Bayesian. Exemplar-based approach to hierarchical shape matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(8):1-14.
[62]Mu Y, Yan S, Liu Y, et al. Discriminative local binary patterns for pedestrian detection in personal album[C]. In Proc. IEEE CVPR,2008:1-8.
[63]O.Tuzel, F.Porikli, P.Meer. Human detection via classification on riemannian manifolds[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008,30(10):1713-1727.
[64]J. Friedman, T. Hastie, R. Tibshirani. Additive logistic regression:A statistical view of boosting. Ann. Statist,2000,28(2):337-407.
[65]Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung, Kuang-Yu Chang. Multi-Class Multi-Instance Boosting for Part-Based Human Detection[C].9th IEEE International Workshop on Visual Surveillance,2009:1177-1184.
[66]Wantanbe T, Ito S, Yokoi K. Co-occurrence histograms of oriented gradients for pedestrian detection[C]. In Proc. of the 3th Pacific-Rim Symposium on Image and Video Technology,2009:37-47.
[67]Dollar P, Tu Z W, Perona P, et al. Integral channel features[C]. In Proc. BMVC, 2009:1-11.
[68]Gao W, Ai H, Lao S. Adaptive Contour Features in oriented granular space for human detection and segmentation[A]. In Proc. IEEE CVPR,2009:1786-1793.
[69]Yazhou Liu, Shiguang Shan, Wenchao Zhang, Xilin Chen, Wen Gao. Granularity-tunable gradients partition (GGP) descriptors for human detection[C]. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, CVPR,2009:1255-1262.
[70]Walk S, Majer N, Schindler K, et al. New features and insights for pedestrian detection[A]. In Proc. Of CVPR,2010:1030-1037.
[71]S.Maji, A.Berg, J.Malik. Classification using intersection kernel support vector machines is efficient[C]. In CVPR,2008:1-8.
[72]Wanli Ouyang, Xiaogang Wang. A discriminative deep model for pedestrian detection with occlusion handling[C]. In CVPR,2012:3258-3265.
[73]Yuanyuan Ding, Jing xiao. Contextual Boost for Pedestrian Detection[C]. In Proc. Of CVPR,2012:2895-2902.
[74]Oren M, Papageorion C, Sinha P, et al. Pedestrian detection using wavelet templates[C]. In Proc. IEEE CVPR,1997:193-199.
[75]P.Sabzmeydani, G.Mori. Detecting Pedestrians by Learning Shapelet Features[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007:1-8.
[76]C.Wojek, B.Schiele. A performance evaluation of single and multi-feature people detection. In Proc.of the 30th DAGM Symp. on Pattern Recognition,2008:82-91.
[77]B.Wu, R.Nevatia. Optimizing discrimination-efficientcy tradeoff in integrating heterogeneous local features for object detection[J]. In CVPR,2008:1-8.
[78]Chen Y T, Chen C S. Fast human detection using a novel boosted cascading structure with meta stages[J]. IEEE Trans.on Image Processing,2008,17(8): 1452-1464.
[79]P.Viola, M.Jones. Robust real-time face detection[J]. International Journal of Computer Vision,2004,57(2):137-154.
[80]Kim T K, Cipolla R. MCBoost:Multiple classifiers boosting for perceptual co-clustering of images and visual features[J]. In Proc. IEEE NIPS,2008.
[81]Mohan, C.Papageorgiu, T Poggio. Example-Based Object Detection in Images by Components[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2001, 23(4):349-361.
[82]Felzenszwalb P, Girshick R, McAllester D, et al. Object detection with discriminatively trained part based models[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2009,32(9):1627-1645.
[83]Felzenszwalb P, Girshick R, McAllester D. Cascade object detection with deformable part models[C]. In Proc. IEEE CVPR,2010:2241-2248.
[84]Pedersoli M, Vedaldi A, Gonzalez J. A coarse-to-fine approach for fast deformable object detection[C]. In Proc. IEEE CVPR,2011:1353-1360.
[85]Parikh D, Zitnick C. Finding the weakest link in person detectors[C]. In Proc. IEEE CVPR,2011:1425-1432.
[86]C.Sminchisescu, A.Kanaujia, Zhiguo Li, et al. Discriminative density Propagation for 3D human motion estimation[C]. In Proc of the Conference on Computer Vision and Pattern Recognition,2005:390-397.
[87]Chen Yisheng, Lee Jinho, Parent Rick, Machiraju Raghu. Markerless Monocular Motion Capture Using Image Features and Physical Constraints. Computer Graphics International,2005:36-43.
[88]Agarwal, B.Triggs.Recovering 3d human pose from monocular images[J]. IEEE Trans. Pattern Anal. Mach.Intell.,2006,28(1):44-58.
[89]Urtasun R, Fleet D J, Fua P.3D people tracking with Gaussian process dynamical models[C]. In Proc of IEEE International Conference on Computer Vision and Pattern Recognition,2006.1:238-245.
[90]Cheng Chen, Yueting Zhuang, Jun Xiao. Towards Robust 3D Reconstruction of Human Motion from Monocular Video[C]. In Proc of International Conference on Artificial Reality and Tele-Existence,2006:594-603.
[91]Guo Feng, Qian Gang.3D Huaman Motion Tracking Using Manifold Learing[C]. In Proc of International Conference on Image Processing,2007:357-360.
[92]X.Zhao, Y.Liu. Generative tracking of 3d human motion by hierarchical annealed genetic algorithm[J]. Pattern Recognition,2008,41(8):2470-2483.
[93]Ning, W.Xu, Y.Gong, T.S.Huang. Discriminative learning of visual words for 3d human pose estimation[C]. In CVPR,2008:1-8.
[94]M.W.Lee, R.Nevatia. Human pose tracking in monocular sequence using multilevel structured models[J]. IEEE Trans. Pattern Anal.Mach.Intell.,2009, 31(1):27-38.
[95]Liu M.Y., Tuzel O., Veeraraghavan A., et al. Fast directional chamfer matching[C]. In CVPR,2010:1696-1703.
[96]Andreas Baak, Meinard Muller, Gaurav Bharaj, et al. A Data-Driven Approach for Real-Time Full Body Pose Reconstruction from a Depth Camera[C]. In ICCV, 2011:1092-1099.
[97]Catalin Ionescu, Fuxin Li, Cristian Sminchisescu. Latent Structured Models for Human Pose Estimation[C]. In ICCV,2011:2220-2227.
[98]Jamie Shotton, Ross Girshick, Andrew Fitzgibbon, et al. Efficient Human Pose Estimation from Single Depth Image[J]s. In Trans. PAMI,2012.
[99]Norimichi Ukita. Articulated Pose Estimation with Parts Connectivity using Discriminative Local Oriented Contours[C]. In CVPR,2012:3154-3161.
[100]罗忠祥,庄越挺,潘云鹤.基于双摄像机的视频特征跟踪方法研究[J].计算机辅助设计与图形学学报,2002,14(7):646-650.
[101]Y.Wu, G.Hua, T.Yu. Tracking articulated body by dynamic markov network[C]. In ICCV,2003:1094-1101.
[102]R.Rosales, S.Sclaroff. Inferring Body Pose without Tracking Body Parts[C]. In IEEE International Conference on Computer Vision and Pattern Recognition, 2000:721-727.
[103]Howe N R, Leventon M E, Freeman W T. Bayesian reconstruction of 3D human motion from single-camera video[J]. Advances in Neural Information Processing Systems,2000:820-826.
[104]T.Zhao, T.S.Wang, H.Y.Shum. Learning a Highly Structured Motion for 3D Human Tracking[C]. Proceedings of the 5th Asian Conference on Computer Vision, 2002:144-149.
[105]A.Elgammal, C.-S.Lee. Inferring 3d body pose from silhouettes using activity manifold learning[C]. In Proc.of IEEE Conference on Computer Vision and Pattern Recognition,2004:681-688.
[106]Agarwal A, Triggs B.3d human pose from silhouettes by relevance vector regression[C]. In Proceedings of CVPR,2004:882-888.
[107]Rogez G, Rihan J, Ramalingam S, et al. Randomized Trees for Human Pose Detection[C]. In Proc of IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
[108]G.Mori J.Malik. Estimating Human Body Configurations using Shape Context Matching[C]. In Proc European Conf. Computer Vision,2002,3:666-680.
[109]Park M J, Choi MG, YShin S. Human motion reconstruction from inter-frame feature correspondences of a single video stream using a motion library[C]. Proceedings of the ACM SIGGRAPH Symposium on Computer Animation,2002: 113-120.
[110]C. Sminchisescu, B. Triggs. Estimating articulated human motion with covariance scaled sampling[J]. International Journal of Robotics Research,2003, 22(6):371-391.
[111]Antonio S.Micilotta, Eng Jon Ong and Richard Bowden. Real-time Upper Body 3D Pose Estimation from a Single Uncalibrated Camera[C]. In Eurographics 2005.
[112]N.R.Howe. Silhouette lookup for monocular 3d pose tracking[C]. Image Vision Comput.2007,25(3):331-341.
[113]C. Nakajima, M. Pontil, B. Heisele, T.Poggio. People Recognition in Image Sequences by Supervised Learning. A.I.Memo No.1688,2000.
[114]Wantanbe T, Ito S, Yokoi K. Co-occurrence histograms of oriented gradients for pedestrian detection[C]. In Proc. of the 3th Pacific-Rim Symposium on Image and Video Technology,2009:37-47.
[115]徐翠,郑颖,汪增福.一种基于图像底层特征的隐马尔可夫人体检测方法[J].模式识别与人工智能,2009,22(5):743-749.
[116]黄如锦,李谊,李文辉,江琦,杨赢涛.基于多特征的AdaBoost行人检测算法[J].吉林大学学报,2010,48(3):450-456.
[117]Wu J X, Rehg J M. Where am I:Place instance and category recognition using spatial PACT[C].In CVPR,2008:24-26.
[118]Freund, Y., Schapire, R.E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. In Computational Learning Theory:Eurocolt, Springer-Verlag,1995:23-37.
[119]Schapire R E, Singer Y. Improved boosting algorithms using confidence-rated predictions [J]. Machine Learning,1999,37(3):297-33.
[120]Bo Wu, Haizhou Ai, Chang Huang, Shihong Lao. Fast Rotation Invariant Multi-View Face Detection Based on Real Adaboost[C]. IEEE International Conference on Automatic Face and Gesture Recognition,2004:79-84.
[121]Xinwen Hou, Cheng-Lin Liu, Tieniu Tan. Learning Boosted Asymmetric Classifiers for Object Detection[C].In IEEE Conf. Computer Vision and Pattern Recognition,2006,1:330-338.
[122]J.Wu, S.C.Brubaker, D.Mullin, J.M.Rehg. Fast Asymmetric Learning for Cascade Face Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(3):369-382.
[123]徐垫,徐佩霞.一种基于改进Adaboost的人体检测算法[J].电子技术,2009(11)：69-71.
[124]R. Xiao, L. Zhu, H.-J. Zhang. Boosting chain learning for object detection[C]. In IEEE International Conference on Computer Vision,2003:709-715.
[125]Xiaoyu Wang, Tony X. Han, Shuicheng Yan. An HOG-LBP Human Detector with Partial Occlusion Handling[C]. In ICCV,2009:32-39.
[126]V. Ferrari, L. Fevrier, F. Jurie, C. Schmid. Groups of adjacent contour segments for object detection[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2008,30(1):36-51.
[127]Lampert C, Blaschko M, Hofmann T. Efficient subwindow search:a branch and bound framework for object localization[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2009,31(12):2129-2142.
[128]S.An, P.Peursum, W.Liu, S.Venkatesh. Efficient algorithms for subwindow search in object detection and localization[C]. In CVPR,2009:264-271.
[129]Vijayanarasimhan S, Grauman K. Efficient region search for object detection[C]. In Proc. IEEE CVPR,2011:1401-1408.
[130]Yuan J S, Liu Z C, Wu Y. Discriminative video pattern search for efficient action detection[J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,2011, 99:1-17.
[131]T.Huang, G.Yang, G.Tang. A fast two-dimensional median filtering algorithm[C]. ICASSP,1979,27(1):13-18.
[132]M.Sizintsev, K.G.Derpanis, A.Hogue. Histogram-based search:a comparative study[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2008:1-8.
[133]H.W. Chang, H.T. Chen. A Square-Root Sampling Approach to Fast Histogram-Based Search[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2010:3043-3049.
[134]Yichen Wei, Litian Tao. Efficient Histogram-Based Sliding Window[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2010: 3003-3010.
[135]Patrick Ott, Mark Everingham. Implicit Color Segmentation Features for Pedestrian Detection[C]. In ICCV,2009:723-730.
[136]T.Watanabe, S.Ito K.Yokoi. Co-occurrence Histograms of Oriented Gradients for Human Detection[J]. Information and Media Technologies,2010,5(2):659-667.
[137]Ran Xu, Baochang Zhang, Qixiang Ye, Jian Bin Jiao. Cascaded L1-norm Minimization Learning (CLML) Classifier for Human Detection[C]. In CVPR, 2010:89-96.
[138]J. Pang, Q. Huang, S. Jiang. Multiple instance boost using graph embedding based decision stump for pedestrian detection[C]. European Conference on Computer Vision,2008,5:12-18
[139]P. Viola, J. Platt, C. Zhang. Multiple instance boosting for object detection[C]. In NIPS,2005:1417-1424.
[140]Dollar P, Babenko B, Belongie S, Perona P, Tu Z. Multiple component learning for object detection[C]. In Proc of the European Conference on Computer Vision, 2008,Ⅱ:211-224.
[141]Zhe Lin, Gang Hua, Larry S. Davis. Multiple Instance Feature for Robust Part-based Object Detection[C]. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition,2009:405-412.
[142]T.G.Dietterich, R.H.Lathrop, P.T.Lozano. Solving the multiple instance problem with axis-parallel rectangles [J]. Artificial Intelligence,1997,89 (122):31-71.
[143]Maron O. Learning from ambiguity[D]. PhD dissertation, Department of Electrical Engineering and Computer Science,1998.
[144]周志华.多示例学习.见：刘大有主编,知识科学中的基本问题研究[M].北京：清华大学出版社,2006,322-336.
[145]龙敏.基于多示例学习的Adaboost算法及其在人脸检测中的应用[D].上海交通大学硕士学位论文,2007年1月.
[146]Z. Zhou, M. Zhang. Multi-instance multi-label learning with application to scene classification[C]. In NIPS,2006:1609-1616.
[147]Alexander Vezhnevets, Joachim Buhmann. Towards Weakly Supervised Semantic Segmentation by Means of Multiple Instance and Multitask Learning[C]. In Proc. CVPR,2010:3249-3256.
[148]Boris Babenko, Ming-Hsuan Yang, Serge Belongie. Visual Tracking with Online Multiple Instance Learning[C]. In Proc. CVPR,2009:983-990.
[149]Maron, T.Lozano-Perez. A framework for multiple-instance learning[C]. Advances in Neural Information Processing Systems,1998.
[150]Zhang Q, Goldman S A. EM-DD:an improved multipie-instance learning technique[C]. Advances in Neural Information Processing Systems,2002,14: 1073-1080.
[151]D.D.Lee, H. S. Seung. Learning the parts of objects by non-negative matrix factorization[j]. Nature,1999,401(6755):788-791.
[152]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[J].计算机科学,2009,11(3):242-246.
[153]C.-C. Chang and C.-J. Lin. LIBSVM:a library for support vector machines,2001. Software available at http://www.csie.ntu.edu.tw/-cjlin/libsvm.
[154]Junbiao Pang, Qingming Huang, Shuqiang Jiang, Wen Gao. Pedestrian detection via logistic multiple instance boosting[C]. In ICIP,2008:1464-1467.
[155]刘俊涛,刘文予,吴彩华,原亮.一种提取物体线形骨架的新方法[J].自动化学报,2008,34(6)：617-622.
[156]李劝男.灰度图像骨架的提取及在物体检测中的应用[D].华中科技大学硕士学位论文,2009年5月.
[157]Y. Zhou, A. Kaufman, A. W. Toga. Three-dimensional Skeleton and Centerline Generation Based on an Approximate Minimum Distance Field[J]. The Visual Computer,1998,14(7):303-314.
[158]Sundar H, Silver D, Gagvani N, et al. Skeleton Based Shape Matching and Retrieval[C]. In Proceedings of the Shape Modeling International,2003:130-138.
[159]刘文予,刘俊涛.基于骨架树描述符匹配的物体相似性度量方法[J].红外与毫米波学报,2005,24(6):432-436.
[160]Wade L, Parent RE. Automated Generation of Control Skeletons for Use in Animation[J]. The Visual Computer,2002, (18):97-110.
[161]Ge Y, Fitzpatrick J M. On the generation of skeletons from discrete euclidean distance maps[J]. IEEE Trans, on Pattern Analysis and Machine Intelligence,1996, 18(11):1055-1066.
[162]人体解剖学编写组.人体解剖学[M].北京：高等教育出版社,1997.
[163]邵立康,赵晓红,郑佳琪,等.基于人体轮廓图像确定关节位置的方法[J].工程图学学报,2006(2)：122-126.
[164]范斌,汪增福.一种基于轮廓的人体关节位置确定方法[J].模式识别与人工智能,2006,19(1)：67-72.
[165]雷涛,罗薇薇,樊养,沈瑜.复杂环境下的运动人体骨架提取算法[J].计算机应用研究,2010,27(8)：3194-3197.
[166]陈坚.单目视频人体运动跟踪和获取技术研究[D].中国科学院博士学位论文,2005年6月.
[167]刘晨光,基于单目视频无标记点的三维人体姿态估计的研究[D].哈尔滨工业大学博士论文,2011年6月.
[168]欧阳毅.单目视频中人体运动建模及姿态估计研究[D].浙江大学博士学位论文,2012年3月.
[169]C.J.Taylor. Reconstruction of articulated objects from point correspondences in a single uncalibrated image[J]. Computer Vision and Image Understanding,2000, 80(3):349-363.
[170]B. Zou, S. Chen, C. Shi and U. M. Providence. Automatic reconstruction of 3D human motion pose from uncalibrated monocular video sequences based on markerless human motion tracking[J]. Pattern Recognition,2009,42(1): 1559-157.
[2]T.B. Moeslund, A.Hilton, V Kruger. A survey of advances in vision-based human motion capture and analysis[J]. Computer Vision and Image Understanding 2006,1 04(2-3):90-126.
[3]R.Poppe. Vision-based human motion analysis:An overview[J]. Computer Vision and Image Understanding,2007,108(1-2):4-18.
[4]M. Enzweiler, D. M. Gavrila. Monocular Pedestrian Detection:Survey and Experiments[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2009: 2179-2195.
[5]Dollar P, Wojek C, Schiele B, et al. Pedestrian detection:an evaluation of the state of the art[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2011, 99:1-20.
[6]许言午.面向行人检测的组合分类计算模型与应用研究.中国科技大学博士学位论文[D],2009年5月.
[7]Pedro F. Felzenszwalb, Daniel P. Huttenlocher. Efficient Matching of Pictorial Structures[C]. Proc. IEEE Conf Computer Vision and Pattern Recognition,2000: 66-73.
[8]D.M. Gavrila, V.Philomin. Real-Time Object Detection for "Smart" Vehicles[C]. IEEE International Conference on Computer Vision,1999,1:87-93.
[9]Curio C, Edelbrunner J, Kalinke T, Tzomakas C, Bruckhoff C, Bergener T, Seelen W. walking pedestrian recognition[J]. IEEE Transactions on Intelligent Transport Systems,2000,1:155-163.
[10]Cutler R, Davis L S. Robust real-time periodic motion detection, analysis and applications [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000,22:781-796.
[11]Wohler C, Kressler U and AnlaufJ K. Pedestrian recognition by classification of image sequences:global approaches vs. local spatio-temporal processing[C]. Proceedings of 15th International Conference on Pattern Recognition,2000, 2:540-544.
[12]刘亚洲.基于时空分析和多粒度特征表示的人体检测方法研究[D].哈尔滨工业大学博士学位论文,2009年9月.
[13]陈坚.单目视频人体运动跟踪和获取技术研究[D].中国科学院研究生院博士学位论文,2005年5月.
[14]李娜.面向人机交互的单目视频三维人体姿态估计研究[D].浙江大学博士学位论文,2008年7月.
[15]陈姝.基于视频的人体运动跟踪与重构方法研究[D].中南大学博士论文,2008年12月.
[16]Ferrari V, Marln-Jimnez M J, Zisserman A. Pose Search:Retrieving People Using Their Pose[C]. In Proc of IEEE Conference on Computer Vision and Pattern Recognition,2009:1-8.
[17]Singh M, Mandal M, Basu A. Pose Recognition Using the Radon Transform[C]. In Proc of Midwest Symposium on Circuits and Systems,2005:1091-1094.
[18]Jiang Hao. Human Pose Estimation Using Consistent Max Covering[C]. In Proc of International Conference on Image Processing,2007:357-360.
[19]Daubney B, Gibson D, Campbell N. Monocular 3D Human Pose Estimation Using Sparse Motion Features [C]. In Proc of International Conference on Computer Vision,2009:1050-1057.
[20]Andriluka M, Roth S, Schiele B. Monocular 3D Pose Estimation and Tracking by Detection[C]. In Proc of IEEE Conference on Computer Vision and Pattern Recognition,2010:623-630.
[21]Wang Yi, Qian Gang. Robust Human Pose Recognition Using Unlabeled Markers[C]. In Proc of Workshop on Application of Computer Vision,2008:1-7.
[22]Kohli P, Rihan J, Bray M, et al. Simultaneous Segmentation and Pose Estimation of Humans using Dynamic Graph Cuts[J]. International Journal of Computer Vision,2008,79(3):285-298.
[23]Okada R, Soatto S. Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images[C]. In Proc of European Conference on Computer Vision,2008:434-445.
[24]Chen Cheng, Yang Yi, Nie Feiping, et al.3d Human Pose Recovery from Image by Efficient Visual Feature Selection[J]. Computer Vision and Image Understanding,2011,115(3):290-299.
[25]C.Sminchisescu, B.Triggs. A Robust Multiple Hypothesis Approach to Monocular Human Motion Tracking [C]. INRIA Research Report,2001.
[26]C.Sminchisescu, B.Triggs. Variational Mixture Smoothing for Non-Linear Dynamical Systems[C]. IEEE International Conference on Computer Vision and Pattern Recognition,2004,Ⅱ:608-615.
[27]Balan, A. Black, M.J. An adaptive appearance model approach for model based articulated object tracking[C]. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition,2006,1:758-765.
[28]罗忠祥,庄越挺,刘丰.基于视频的人体动画[J].计算机研究与发展,2003,40(2)：269-276.
[29]刘钢,彭群生,鲍虎军.基于图像建模技术研究综述与展望[J].计算机辅助设计与图形学学报,2005,17(1):18-27.
[30]陈成.基于视频的人体三维运动恢复相关技术研究[D].浙江大学博士学位论文,2009年1月.
[31]http://nlpr-web.ia.ac.cn/index.asp.
[32]Minglei Tong, Yuncai Liu, Thomas.S.Huang.3D Human Model and Joint Parameter Estimation from Monocular Image[J].Pattern Recognition Letters, 2007,28(7):797-805.
[33]仝明磊.非标定单目序列图像的三维人体运动分析[D].上海交通大学博士论文,2007年10月.
[34]王文中,王兆其,邓小明,夏时洪,邱显杰.基于局部先验模型的单目视频人 体运动跟踪[J].计算机辅助设计与图形学学报,2011,23(9):1545-1552.
[35]苏延超,艾海舟,劳世竑.图像和视频中基于部件检测器的人体姿态估计[J].电子与信息学报,2011,33(6)：1413-1419.
[36]邹北骥,陈姝,彭小宁,史操.适用于单目视频的无标记三维人体运动跟踪[J].计算机辅助设计与图形学学报,2008,20(8):1047-1055.
[37]Devi Parikh, C. Lawrence Zitnick. The role of features, algorithms and data in visual recognition[J]. In CVPR,2010,2328-2335.
[38]P.Viola, M.Jones. Rapid Object Detection using a Boosted Cascade of Simple Features[C]. In Proceeding of International Conference on Computer Vision and Pattern Recognition,2001,1:511-518.
[39]P.Viola, M.Jones, D. Snow. Detecting Pedestrians Using Patterns of Motion and Appearance[J]. International Journal of Computer Vision,2005,63(2):153-161.
[40]S.Belongie, J.Malik, J.Puzicha. Shape matching and object recognition using shape contexts[J]. IEEE Trans. Pattern Anal. Mach.Intell.,2002,24(4):509-522.
[41]Gavrila D M, Giebel J. Shape-based pedestrian detection and tracking[C]. Intelligent Vehicle Symposium,2002,1(17-21):8-14.
[42]Bertozzi M, Broggi A, Chapuis R. Shape-based pedestrian detection and localization [J]. Intelligent Transportation Systems,2003,1:328-333.
[43]Leibe B, Seemann E, Schiele B. Pedestrian detection in crowded scenes[C]. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2005,20-25.
[44]N. Dalal, B. Triggs. Histograms of oriented gradients for human detection[C]. In CVPR,2005,1:886-893.
[45]Q. Zhu, M.C. Yeh, K.T. Cheng, and S. Avidan. Fast human detection using a cascade of histograms of oriented gradients[C]. In CVPR,2006:1491-1498.
[46]R.Zabih, J.Woodfill. A non-parametric approach to visual correspondence [J]. IEEE Transactions on Pattern Analysis and Machine intelligence,1996.
[47]Wu J X, Rehg J M. CENTRIST:A visual descriptor for scene categorization [J]. IEEE Trans, on Pattern Analysis and Machine Intelligent,2011,33(8):1489-1501.
[48]Wu J X, Greyer C, Rehg J M. Real-time human detection using contour cues[A]. In Proc. IEEE ICRA,2011:860-867.
[49]T.Ojala, M.Pietik"ainen, D.Harwood. A comparative study of texture measures with classification based on featured distributions[J]. Pattern Recognition,1996, 29(1):51-59.
[50]Yadong Mu, Shuicheng Yan, Yi Liu, Thomas Huang, Bingfeng Zhou. Unsupervised Learning of Human Perspective Context Using ME-DT for Efficient Human Detection in Surveillance [C]. In CVPR,2008:1-8.
[51]N.Dalal, B.Triggs, C.Schmid. Human Detection Using Oriented Histograms of Flow and Appearance[C]. European Conference on Computer Vision,2006(2): 428-441.
[52]C.Wojek, S.Walk, B.Schiele. Multi-cue Onboard Pedestrian Detection[C]. IEEE Conference on Computer Vision and Pattern Recognition,2009:794-801.
[53]O.Javed, M.Shah. Tracking and Object Classification for Automated Surveillance[C]. In Proc Seventh European Conference on Computer Vision,2002, IV:343-357.
[54]Dollar P, Rabaud V, Cotterll G, Belongie S. Behavior recognition via sparse spatio-temporal features[C]. In 2nd joint IEEE International workshop on Visual Surveillance and Performance Evaluation of tracking and Surveillance, 2005:65-72.
[55]朱谊强.基于AdaBoost算法的实时性人检测系统[D].西北工业大学硕士学位论文,2006年4月.
[56]Yazhou Liu, Xilin Chen, Hongxun Yao, Xinyi Cui, Chaoran Liu, Wen Gao. Contour-motion feature(CMF):A space-time approach for robust pedestrian detection[J]. Pattern Recognition Letters(PRL),2009,30(2):148-156.
[57]ZHU Guang-yu, XU Chang-shen. Action recognition in broadcast tennis video[C]. In Proc of the 18th International Conference on Pattern Recognition,2006: 251-254.
[58]Laptev I, Lindeberg T. Local descriptors for spatio-temporal recognition[C]. In First International Workshop on Spatial Coherence for Visual Motion Analysis, 2004:91-103.
[59]苏松志,李绍滋,陈淑媛,蔡国榕,吴云东.行人检测技术综述[J].电子学报,2012(40)：814-820.
[60]B.Wu, R.Nevatia. Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors[C]. IEEE International Conference on Computer Vision,2005,1:90-97.
[61]Gavrila D. A Bayesian. Exemplar-based approach to hierarchical shape matching[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(8):1-14.
[62]Mu Y, Yan S, Liu Y, et al. Discriminative local binary patterns for pedestrian detection in personal album[C]. In Proc. IEEE CVPR,2008:1-8.
[63]O.Tuzel, F.Porikli, P.Meer. Human detection via classification on riemannian manifolds[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008,30(10):1713-1727.
[64]J. Friedman, T. Hastie, R. Tibshirani. Additive logistic regression:A statistical view of boosting. Ann. Statist,2000,28(2):337-407.
[65]Yu-Ting Chen, Chu-Song Chen, Yi-Ping Hung, Kuang-Yu Chang. Multi-Class Multi-Instance Boosting for Part-Based Human Detection[C].9th IEEE International Workshop on Visual Surveillance,2009:1177-1184.
[66]Wantanbe T, Ito S, Yokoi K. Co-occurrence histograms of oriented gradients for pedestrian detection[C]. In Proc. of the 3th Pacific-Rim Symposium on Image and Video Technology,2009:37-47.
[67]Dollar P, Tu Z W, Perona P, et al. Integral channel features[C]. In Proc. BMVC, 2009:1-11.
[68]Gao W, Ai H, Lao S. Adaptive Contour Features in oriented granular space for human detection and segmentation[A]. In Proc. IEEE CVPR,2009:1786-1793.
[69]Yazhou Liu, Shiguang Shan, Wenchao Zhang, Xilin Chen, Wen Gao. Granularity-tunable gradients partition (GGP) descriptors for human detection[C]. IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, CVPR,2009:1255-1262.
[70]Walk S, Majer N, Schindler K, et al. New features and insights for pedestrian detection[A]. In Proc. Of CVPR,2010:1030-1037.
[71]S.Maji, A.Berg, J.Malik. Classification using intersection kernel support vector machines is efficient[C]. In CVPR,2008:1-8.
[72]Wanli Ouyang, Xiaogang Wang. A discriminative deep model for pedestrian detection with occlusion handling[C]. In CVPR,2012:3258-3265.
[73]Yuanyuan Ding, Jing xiao. Contextual Boost for Pedestrian Detection[C]. In Proc. Of CVPR,2012:2895-2902.
[74]Oren M, Papageorion C, Sinha P, et al. Pedestrian detection using wavelet templates[C]. In Proc. IEEE CVPR,1997:193-199.
[75]P.Sabzmeydani, G.Mori. Detecting Pedestrians by Learning Shapelet Features[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2007:1-8.
[76]C.Wojek, B.Schiele. A performance evaluation of single and multi-feature people detection. In Proc.of the 30th DAGM Symp. on Pattern Recognition,2008:82-91.
[77]B.Wu, R.Nevatia. Optimizing discrimination-efficientcy tradeoff in integrating heterogeneous local features for object detection[J]. In CVPR,2008:1-8.
[78]Chen Y T, Chen C S. Fast human detection using a novel boosted cascading structure with meta stages[J]. IEEE Trans.on Image Processing,2008,17(8): 1452-1464.
[79]P.Viola, M.Jones. Robust real-time face detection[J]. International Journal of Computer Vision,2004,57(2):137-154.
[80]Kim T K, Cipolla R. MCBoost:Multiple classifiers boosting for perceptual co-clustering of images and visual features[J]. In Proc. IEEE NIPS,2008.
[81]Mohan, C.Papageorgiu, T Poggio. Example-Based Object Detection in Images by Components[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2001, 23(4):349-361.
[82]Felzenszwalb P, Girshick R, McAllester D, et al. Object detection with discriminatively trained part based models[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence,2009,32(9):1627-1645.
[83]Felzenszwalb P, Girshick R, McAllester D. Cascade object detection with deformable part models[C]. In Proc. IEEE CVPR,2010:2241-2248.
[84]Pedersoli M, Vedaldi A, Gonzalez J. A coarse-to-fine approach for fast deformable object detection[C]. In Proc. IEEE CVPR,2011:1353-1360.
[85]Parikh D, Zitnick C. Finding the weakest link in person detectors[C]. In Proc. IEEE CVPR,2011:1425-1432.
[86]C.Sminchisescu, A.Kanaujia, Zhiguo Li, et al. Discriminative density Propagation for 3D human motion estimation[C]. In Proc of the Conference on Computer Vision and Pattern Recognition,2005:390-397.
[87]Chen Yisheng, Lee Jinho, Parent Rick, Machiraju Raghu. Markerless Monocular Motion Capture Using Image Features and Physical Constraints. Computer Graphics International,2005:36-43.
[88]Agarwal, B.Triggs.Recovering 3d human pose from monocular images[J]. IEEE Trans. Pattern Anal. Mach.Intell.,2006,28(1):44-58.
[89]Urtasun R, Fleet D J, Fua P.3D people tracking with Gaussian process dynamical models[C]. In Proc of IEEE International Conference on Computer Vision and Pattern Recognition,2006.1:238-245.
[90]Cheng Chen, Yueting Zhuang, Jun Xiao. Towards Robust 3D Reconstruction of Human Motion from Monocular Video[C]. In Proc of International Conference on Artificial Reality and Tele-Existence,2006:594-603.
[91]Guo Feng, Qian Gang.3D Huaman Motion Tracking Using Manifold Learing[C]. In Proc of International Conference on Image Processing,2007:357-360.
[92]X.Zhao, Y.Liu. Generative tracking of 3d human motion by hierarchical annealed genetic algorithm[J]. Pattern Recognition,2008,41(8):2470-2483.
[93]Ning, W.Xu, Y.Gong, T.S.Huang. Discriminative learning of visual words for 3d human pose estimation[C]. In CVPR,2008:1-8.
[94]M.W.Lee, R.Nevatia. Human pose tracking in monocular sequence using multilevel structured models[J]. IEEE Trans. Pattern Anal.Mach.Intell.,2009, 31(1):27-38.
[95]Liu M.Y., Tuzel O., Veeraraghavan A., et al. Fast directional chamfer matching[C]. In CVPR,2010:1696-1703.
[96]Andreas Baak, Meinard Muller, Gaurav Bharaj, et al. A Data-Driven Approach for Real-Time Full Body Pose Reconstruction from a Depth Camera[C]. In ICCV, 2011:1092-1099.
[97]Catalin Ionescu, Fuxin Li, Cristian Sminchisescu. Latent Structured Models for Human Pose Estimation[C]. In ICCV,2011:2220-2227.
[98]Jamie Shotton, Ross Girshick, Andrew Fitzgibbon, et al. Efficient Human Pose Estimation from Single Depth Image[J]s. In Trans. PAMI,2012.
[99]Norimichi Ukita. Articulated Pose Estimation with Parts Connectivity using Discriminative Local Oriented Contours[C]. In CVPR,2012:3154-3161.
[100]罗忠祥,庄越挺,潘云鹤.基于双摄像机的视频特征跟踪方法研究[J].计算机辅助设计与图形学学报,2002,14(7):646-650.
[101]Y.Wu, G.Hua, T.Yu. Tracking articulated body by dynamic markov network[C]. In ICCV,2003:1094-1101.
[102]R.Rosales, S.Sclaroff. Inferring Body Pose without Tracking Body Parts[C]. In IEEE International Conference on Computer Vision and Pattern Recognition, 2000:721-727.
[103]Howe N R, Leventon M E, Freeman W T. Bayesian reconstruction of 3D human motion from single-camera video[J]. Advances in Neural Information Processing Systems,2000:820-826.
[104]T.Zhao, T.S.Wang, H.Y.Shum. Learning a Highly Structured Motion for 3D Human Tracking[C]. Proceedings of the 5th Asian Conference on Computer Vision, 2002:144-149.
[105]A.Elgammal, C.-S.Lee. Inferring 3d body pose from silhouettes using activity manifold learning[C]. In Proc.of IEEE Conference on Computer Vision and Pattern Recognition,2004:681-688.
[106]Agarwal A, Triggs B.3d human pose from silhouettes by relevance vector regression[C]. In Proceedings of CVPR,2004:882-888.
[107]Rogez G, Rihan J, Ramalingam S, et al. Randomized Trees for Human Pose Detection[C]. In Proc of IEEE Conference on Computer Vision and Pattern Recognition,2008:1-8.
[108]G.Mori J.Malik. Estimating Human Body Configurations using Shape Context Matching[C]. In Proc European Conf. Computer Vision,2002,3:666-680.
[109]Park M J, Choi MG, YShin S. Human motion reconstruction from inter-frame feature correspondences of a single video stream using a motion library[C]. Proceedings of the ACM SIGGRAPH Symposium on Computer Animation,2002: 113-120.
[110]C. Sminchisescu, B. Triggs. Estimating articulated human motion with covariance scaled sampling[J]. International Journal of Robotics Research,2003, 22(6):371-391.
[111]Antonio S.Micilotta, Eng Jon Ong and Richard Bowden. Real-time Upper Body 3D Pose Estimation from a Single Uncalibrated Camera[C]. In Eurographics 2005.
[112]N.R.Howe. Silhouette lookup for monocular 3d pose tracking[C]. Image Vision Comput.2007,25(3):331-341.
[113]C. Nakajima, M. Pontil, B. Heisele, T.Poggio. People Recognition in Image Sequences by Supervised Learning. A.I.Memo No.1688,2000.
[114]Wantanbe T, Ito S, Yokoi K. Co-occurrence histograms of oriented gradients for pedestrian detection[C]. In Proc. of the 3th Pacific-Rim Symposium on Image and Video Technology,2009:37-47.
[115]徐翠,郑颖,汪增福.一种基于图像底层特征的隐马尔可夫人体检测方法[J].模式识别与人工智能,2009,22(5):743-749.
[116]黄如锦,李谊,李文辉,江琦,杨赢涛.基于多特征的AdaBoost行人检测算法[J].吉林大学学报,2010,48(3):450-456.
[117]Wu J X, Rehg J M. Where am I:Place instance and category recognition using spatial PACT[C].In CVPR,2008:24-26.
[118]Freund, Y., Schapire, R.E. A decision-theoretic generalization of on-line learning and an application to boosting[J]. In Computational Learning Theory:Eurocolt, Springer-Verlag,1995:23-37.
[119]Schapire R E, Singer Y. Improved boosting algorithms using confidence-rated predictions [J]. Machine Learning,1999,37(3):297-33.
[120]Bo Wu, Haizhou Ai, Chang Huang, Shihong Lao. Fast Rotation Invariant Multi-View Face Detection Based on Real Adaboost[C]. IEEE International Conference on Automatic Face and Gesture Recognition,2004:79-84.
[121]Xinwen Hou, Cheng-Lin Liu, Tieniu Tan. Learning Boosted Asymmetric Classifiers for Object Detection[C].In IEEE Conf. Computer Vision and Pattern Recognition,2006,1:330-338.
[122]J.Wu, S.C.Brubaker, D.Mullin, J.M.Rehg. Fast Asymmetric Learning for Cascade Face Detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(3):369-382.
[123]徐垫,徐佩霞.一种基于改进Adaboost的人体检测算法[J].电子技术,2009(11)：69-71.
[124]R. Xiao, L. Zhu, H.-J. Zhang. Boosting chain learning for object detection[C]. In IEEE International Conference on Computer Vision,2003:709-715.
[125]Xiaoyu Wang, Tony X. Han, Shuicheng Yan. An HOG-LBP Human Detector with Partial Occlusion Handling[C]. In ICCV,2009:32-39.
[126]V. Ferrari, L. Fevrier, F. Jurie, C. Schmid. Groups of adjacent contour segments for object detection[J]. IEEE Trans.on Pattern Analysis and Machine Intelligence, 2008,30(1):36-51.
[127]Lampert C, Blaschko M, Hofmann T. Efficient subwindow search:a branch and bound framework for object localization[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence,2009,31(12):2129-2142.
[128]S.An, P.Peursum, W.Liu, S.Venkatesh. Efficient algorithms for subwindow search in object detection and localization[C]. In CVPR,2009:264-271.
[129]Vijayanarasimhan S, Grauman K. Efficient region search for object detection[C]. In Proc. IEEE CVPR,2011:1401-1408.
[130]Yuan J S, Liu Z C, Wu Y. Discriminative video pattern search for efficient action detection[J]. IEEE Trans. On Pattern Analysis and Machine Intelligence,2011, 99:1-17.
[131]T.Huang, G.Yang, G.Tang. A fast two-dimensional median filtering algorithm[C]. ICASSP,1979,27(1):13-18.
[132]M.Sizintsev, K.G.Derpanis, A.Hogue. Histogram-based search:a comparative study[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2008:1-8.
[133]H.W. Chang, H.T. Chen. A Square-Root Sampling Approach to Fast Histogram-Based Search[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2010:3043-3049.
[134]Yichen Wei, Litian Tao. Efficient Histogram-Based Sliding Window[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2010: 3003-3010.
[135]Patrick Ott, Mark Everingham. Implicit Color Segmentation Features for Pedestrian Detection[C]. In ICCV,2009:723-730.
[136]T.Watanabe, S.Ito K.Yokoi. Co-occurrence Histograms of Oriented Gradients for Human Detection[J]. Information and Media Technologies,2010,5(2):659-667.
[137]Ran Xu, Baochang Zhang, Qixiang Ye, Jian Bin Jiao. Cascaded L1-norm Minimization Learning (CLML) Classifier for Human Detection[C]. In CVPR, 2010:89-96.
[138]J. Pang, Q. Huang, S. Jiang. Multiple instance boost using graph embedding based decision stump for pedestrian detection[C]. European Conference on Computer Vision,2008,5:12-18
[139]P. Viola, J. Platt, C. Zhang. Multiple instance boosting for object detection[C]. In NIPS,2005:1417-1424.
[140]Dollar P, Babenko B, Belongie S, Perona P, Tu Z. Multiple component learning for object detection[C]. In Proc of the European Conference on Computer Vision, 2008,Ⅱ:211-224.
[141]Zhe Lin, Gang Hua, Larry S. Davis. Multiple Instance Feature for Robust Part-based Object Detection[C]. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition,2009:405-412.
[142]T.G.Dietterich, R.H.Lathrop, P.T.Lozano. Solving the multiple instance problem with axis-parallel rectangles [J]. Artificial Intelligence,1997,89 (122):31-71.
[143]Maron O. Learning from ambiguity[D]. PhD dissertation, Department of Electrical Engineering and Computer Science,1998.
[144]周志华.多示例学习.见：刘大有主编,知识科学中的基本问题研究[M].北京：清华大学出版社,2006,322-336.
[145]龙敏.基于多示例学习的Adaboost算法及其在人脸检测中的应用[D].上海交通大学硕士学位论文,2007年1月.
[146]Z. Zhou, M. Zhang. Multi-instance multi-label learning with application to scene classification[C]. In NIPS,2006:1609-1616.
[147]Alexander Vezhnevets, Joachim Buhmann. Towards Weakly Supervised Semantic Segmentation by Means of Multiple Instance and Multitask Learning[C]. In Proc. CVPR,2010:3249-3256.
[148]Boris Babenko, Ming-Hsuan Yang, Serge Belongie. Visual Tracking with Online Multiple Instance Learning[C]. In Proc. CVPR,2009:983-990.
[149]Maron, T.Lozano-Perez. A framework for multiple-instance learning[C]. Advances in Neural Information Processing Systems,1998.
[150]Zhang Q, Goldman S A. EM-DD:an improved multipie-instance learning technique[C]. Advances in Neural Information Processing Systems,2002,14: 1073-1080.
[151]D.D.Lee, H. S. Seung. Learning the parts of objects by non-negative matrix factorization[j]. Nature,1999,401(6755):788-791.
[152]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[J].计算机科学,2009,11(3):242-246.
[153]C.-C. Chang and C.-J. Lin. LIBSVM:a library for support vector machines,2001. Software available at http://www.csie.ntu.edu.tw/-cjlin/libsvm.
[154]Junbiao Pang, Qingming Huang, Shuqiang Jiang, Wen Gao. Pedestrian detection via logistic multiple instance boosting[C]. In ICIP,2008:1464-1467.
[155]刘俊涛,刘文予,吴彩华,原亮.一种提取物体线形骨架的新方法[J].自动化学报,2008,34(6)：617-622.
[156]李劝男.灰度图像骨架的提取及在物体检测中的应用[D].华中科技大学硕士学位论文,2009年5月.
[157]Y. Zhou, A. Kaufman, A. W. Toga. Three-dimensional Skeleton and Centerline Generation Based on an Approximate Minimum Distance Field[J]. The Visual Computer,1998,14(7):303-314.
[158]Sundar H, Silver D, Gagvani N, et al. Skeleton Based Shape Matching and Retrieval[C]. In Proceedings of the Shape Modeling International,2003:130-138.
[159]刘文予,刘俊涛.基于骨架树描述符匹配的物体相似性度量方法[J].红外与毫米波学报,2005,24(6):432-436.
[160]Wade L, Parent RE. Automated Generation of Control Skeletons for Use in Animation[J]. The Visual Computer,2002, (18):97-110.
[161]Ge Y, Fitzpatrick J M. On the generation of skeletons from discrete euclidean distance maps[J]. IEEE Trans, on Pattern Analysis and Machine Intelligence,1996, 18(11):1055-1066.
[162]人体解剖学编写组.人体解剖学[M].北京：高等教育出版社,1997.
[163]邵立康,赵晓红,郑佳琪,等.基于人体轮廓图像确定关节位置的方法[J].工程图学学报,2006(2)：122-126.
[164]范斌,汪增福.一种基于轮廓的人体关节位置确定方法[J].模式识别与人工智能,2006,19(1)：67-72.
[165]雷涛,罗薇薇,樊养,沈瑜.复杂环境下的运动人体骨架提取算法[J].计算机应用研究,2010,27(8)：3194-3197.
[166]陈坚.单目视频人体运动跟踪和获取技术研究[D].中国科学院博士学位论文,2005年6月.
[167]刘晨光,基于单目视频无标记点的三维人体姿态估计的研究[D].哈尔滨工业大学博士论文,2011年6月.
[168]欧阳毅.单目视频中人体运动建模及姿态估计研究[D].浙江大学博士学位论文,2012年3月.
[169]C.J.Taylor. Reconstruction of articulated objects from point correspondences in a single uncalibrated image[J]. Computer Vision and Image Understanding,2000, 80(3):349-363.
[170]B. Zou, S. Chen, C. Shi and U. M. Providence. Automatic reconstruction of 3D human motion pose from uncalibrated monocular video sequences based on markerless human motion tracking[J]. Pattern Recognition,2009,42(1): 1559-157.