单目视频中于退火粒子滤波的三维人体运动跟踪
|
摘要
三维人体运动跟踪是近年来机器视觉领域一个十分重要的研究方向,其应用领域相当广泛,如人机交互、智能动画合成、视频监控等。目前有关三维人体运动跟踪的研究大多基于多目视频,单目视频由于深度信息的缺乏使得三维人体运动跟踪的难度更大,且大多单目视频三维运动跟踪只考虑平行于镜头无遮挡的运动。针对上述问题,使用基于蒙特卡罗思想的粒子滤波方法并结合人体运动的先验知识实现对单目视频三维人体运动的跟踪。
在粒子滤波算法中融入退火思想,解决粒子数量大的问题。由于人体运动状态的高维性,要正确表达后验分布需要大量粒子,这导致普通粒子滤波算法计算效率过低而不可行。为解决该问题使用退火思想,在粒子集进行预测前对粒子集进行多层退火,使粒子集逐渐聚集在似然函数值高的位置,使得粒子集更加有效。
综合运用边缘和剪影两种图像特征构造似然函数,使得模型投影与图像之间的匹配程度的量化估计更准确,以达到对粒子重要性做出合理判断的目的,从而使得跟踪结果的鲁棒性更好。
将人体运动约束集成到整个跟踪框架,包括骨骼运动角度范围约束和肢体非穿透性约束;从而对姿态数据的可行区域进行一定的限制,防止非法姿态数据的产生,提高三维人体跟踪的准确性。此外,在跟踪过程中加入简单线性预测模型,并验证了两种线性运动预测模型对跟踪效果的影响。
实验证明,使用上述方法对复杂背景下带旋转的行走动作最多可跟踪100帧左右,对长时间序列的三维人体运动跟踪还有一定的困难,需要加入更复杂的运动预测模型及人体力学约束来指导跟踪。
Three-dimensional human motion tracking is an important research domain in machine vision field in recent years. It has a wide range of applications, such as human-computer interaction, monitoring of intelligent video and animation etc. At present, many research topics about three-dimensional human motion tracking are based on multiple video sequences, however, monocular video sequences couldn’t reach a satisfied accuracy in resuming human body three-dimensional attitude data because of monocular video lacking of detailed information and self-occlusion between the body parts. Concerning on this issue, we choosed particle filtering method based on the Monte Carlo methods, combined with prior knowledge of human movement to realize human body three-dimensional tracking.
We add simulated annealing to reduce the number of particles. In the tracking process, we took advantage of weighted particles collection to approach the posterior probability distribution, and adjusted the location of particles from time to time, let them close to the peak of likelihood function gradually , in order to make the weighted particles to have a better reflection of distribution in each moment.
We used two kinds of image features edge and silhouette to construct likelihood function, making the quantification-comparability estimation between model projections and images more accurate to achieve the purpose of determining the importance of particles reasonablely, which makes robustness of tracking results more finer.
Integrate the constrained human motion into the entire track framework, including the perspective scope restriction of the skeleton movement constrained and non-penetrating restriction of limbs in order to restrict the feasible area of attitude data for preventing the emergence of illegal attitude data and improving the accuracy of three-dimensional human tracking. In addition, add a simple linear prediction model into the process of tracking, and verified the influence of two linear movement prediction models to tracking effect.
Experiments show that the method mentioned above are effective in 100 frames for walking motion tracking with rotary under the complex background , while it's difficult for the method to track 3D human motion in long time sequence which need adding more complex motion prediction models and human movement restrictions to be superintended.
在粒子滤波算法中融入退火思想,解决粒子数量大的问题。由于人体运动状态的高维性,要正确表达后验分布需要大量粒子,这导致普通粒子滤波算法计算效率过低而不可行。为解决该问题使用退火思想,在粒子集进行预测前对粒子集进行多层退火,使粒子集逐渐聚集在似然函数值高的位置,使得粒子集更加有效。
综合运用边缘和剪影两种图像特征构造似然函数,使得模型投影与图像之间的匹配程度的量化估计更准确,以达到对粒子重要性做出合理判断的目的,从而使得跟踪结果的鲁棒性更好。
将人体运动约束集成到整个跟踪框架,包括骨骼运动角度范围约束和肢体非穿透性约束;从而对姿态数据的可行区域进行一定的限制,防止非法姿态数据的产生,提高三维人体跟踪的准确性。此外,在跟踪过程中加入简单线性预测模型,并验证了两种线性运动预测模型对跟踪效果的影响。
实验证明,使用上述方法对复杂背景下带旋转的行走动作最多可跟踪100帧左右,对长时间序列的三维人体运动跟踪还有一定的困难,需要加入更复杂的运动预测模型及人体力学约束来指导跟踪。
Three-dimensional human motion tracking is an important research domain in machine vision field in recent years. It has a wide range of applications, such as human-computer interaction, monitoring of intelligent video and animation etc. At present, many research topics about three-dimensional human motion tracking are based on multiple video sequences, however, monocular video sequences couldn’t reach a satisfied accuracy in resuming human body three-dimensional attitude data because of monocular video lacking of detailed information and self-occlusion between the body parts. Concerning on this issue, we choosed particle filtering method based on the Monte Carlo methods, combined with prior knowledge of human movement to realize human body three-dimensional tracking.
We add simulated annealing to reduce the number of particles. In the tracking process, we took advantage of weighted particles collection to approach the posterior probability distribution, and adjusted the location of particles from time to time, let them close to the peak of likelihood function gradually , in order to make the weighted particles to have a better reflection of distribution in each moment.
We used two kinds of image features edge and silhouette to construct likelihood function, making the quantification-comparability estimation between model projections and images more accurate to achieve the purpose of determining the importance of particles reasonablely, which makes robustness of tracking results more finer.
Integrate the constrained human motion into the entire track framework, including the perspective scope restriction of the skeleton movement constrained and non-penetrating restriction of limbs in order to restrict the feasible area of attitude data for preventing the emergence of illegal attitude data and improving the accuracy of three-dimensional human tracking. In addition, add a simple linear prediction model into the process of tracking, and verified the influence of two linear movement prediction models to tracking effect.
Experiments show that the method mentioned above are effective in 100 frames for walking motion tracking with rotary under the complex background , while it's difficult for the method to track 3D human motion in long time sequence which need adding more complex motion prediction models and human movement restrictions to be superintended.
引文
[1] Poppe R. Vision-based human motion analysis:An overview. Computer Vision and Image Understanding, 2007, 108(3): 4~18
[2] Taylor C J. Reconstruction of articulated objects from point correspondences in a single uncalibrated image. Computer Vision and Image Understanding, 2000, 80(3): 349~363
[3]邱显杰.基于视频的三维人体运动捕获方法研究: [博士学位论文]。北京:中科院计算所, 2006.
[4] Thomas B. Moeslund, Granum E. A survey of computer vision-based human motion capture. Computer Vision and Image Understanding, 2001, 81(3): 231~268
[5] Zhao X, Liu Y C. Generative tracking of 3D human motion by hierarchical annealed genetic algorithm. Pattern Recognition, 2008, 41(8): 2470~2483
[6] Urtasun R, Fleet D L, Fua P. Gaussian Process Dynamical Models for 3D people tracking. Computer Vision and Pattern Recognition, New York, June, 2006. 7-11
[7] Li R, Yang M H, Sclaroff S, et al. Monocular tracking of 3D human motion with a coordinated mixture of factor analyzers. In: ECCV. Proceedings of 9th European Conference on Computer Vision (ECCV 2006), Berlin, Germany: Springer-Verlag Berlin, 2006. 5~7
[8] Ning H Z, Xu W, Gong Y H, et al. Discriminative learning of visual words for 3D human pose estimation. In IEEE. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York, USA 23-28 June 2008.1~8
[9] Nait H, Charif,S.J.McKenna. Head tracking and action recognition in a smart meeting room. Proceedings of 4th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Graz Austri,2003. 24~31
[10] Wu Y, Huang T S. Robust visual tracking by integrating multiple cues based on co-inference learning. International Journal of Computer Vision, 2004, 58(1): 55~71
[11] Shan C F, WeiY C, Tan T N, et al. Real time hand tracking by combining particle filtering and mean shift. In: Proceedings of 6th International Conference on Automatic Face and Gesture Recognition. Los Alamitos USA: IEEE Computer Soc press, 2004. 669~674
[12] KaewTrakulPong P, Bowden R. A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes. Image andVision Computing,2003, 21(10): 913~929
[13] Wang J, Cohen M F. Very low frame-rate video streaming for face-to-face teleconference. In: IEEE. Proceedings of IEEE Data Compression Conference. Los Alamitos, USA: IEEE Computer Soc press, 2005. 309~318
[14]陈坚.单目视频人体运动跟踪和获取技术研究: [博士学位论文]。北京:中科院计算所, 2005.
[15]仝明磊.非标定单目序列图像的三维人体运动分析: [博士学位论文]。上海:上海交通大学图像处理与模式识别研究所, 2007.
[16] Wang L, Hu W M, Tan T N. Recent Developments in Human Motion Analysis. Pattern Recognition, 2003, 36(3): 585~601
[17] T.B. Moeslund, A. Hilton, V. Krüger. A survey of advances in vision-based human motion capture and analysis. CVIU,2006,104 :90~126
[18] D.Hogg. Model-Based Vision: A Program to See a Walking Person. Image and Vision Computing, February 1983, 1(1):15~24
[19] R. T. Collins et al. A system for video surveillance and monitoring. VSAM final report, Carnegie Mellon University, 2000:17~25
[20] I. Haritaoglu, D. Harwood, L.S. Davis. W4: real-time surveillance of people and their activities. IEEE Trans on Pattern Analysis and Machine Intelligence, 22(8): 809~830
[21] Sminchisescu C, Triggs B. A Robust Multiple Hypothesis Approach to Monoclar Human Motion Tracking. INRIA Research Report, 2001, 15~19
[22] C.Sminchisescu,B.Triggs. Covariance Scaled Sampling for Monocular 3D Body Tracking. IEEE International Conference on Computer Vision and Pattern Recognition, Hawaii, 2001.56~64
[23] C.Sminchisescu,B.Triggs. Kinematic Jump Processes for Monocular 3D HumaTracking. IEEE International Conference on Computer Vision and Pattern Reognition, 2003.36-39
[24] Agarwal A, Triggs B. Recovering 3D human pose from monocular images. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) ,2006, 28 (1): 44~58
[25] Agarwal A, Triggs B. 3D Human Pose from Silhouettes by Relevance Vector Regression. In: IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos USA: IEEE Computer Soc 2004.882~888
[26] Agarwal A, Triggs B. Tracking Articulated Motion using a Mixture of Autoregressive Models. In Proceedings of 8th European Conference on Computer Vision,Prague, Berlin, Germany: Springer-Verlag Berlin, 2004.19~31
[27] C.Sminchisescu,A.Kanaujia, Z. Li et al. Discriminative Density Propagation for 3D Human Motion Estimation. In: Proceedings of Conference on Computer Vision and Pattern Recognition. Los Alamitos USA: IEEE Computer Soc press, 2005.13~15
[28] C. Sminchisescu,A.Kanajujia,D.Metaxas. Learning Joint Top-Down and Bottom-Up Processes for 3D Visual Inference. In:IEEE. Proceedings of International Conference on Computer Vision and Pattern Recognition.New York, USA: IEEE Computer Soc2006. 17~19
[29] A.Kanaujia,C.Sminchisescu,D.Metaxas. Semi-supervised Hierarchical Models for 3D Human Pose Reconstruction. In:IEEE. Proceedings of Conference on Computer Vision and Pattern Recognition CVPR. New York, USA: IEEE press, 2007.10~11
[30] Urtasun R, Fleet D J,.Geiger A, et al. Modeling human locomotion with Topologically-Constrained Latent Variable Models.To appear in International 2nd Workshop on Human Motion Understanding, Modeling. Berlin, Germany: Springer-Verlag Berlin, 2008. 45~57
[31] Urtasun R, Fleet D J, Fua P. Gaussian Process Dynamical Models for 3D people tracking. In: IEEE. Proceedings of Conference on Computer Vision and Pattern Recognition, New York, USA: IEEE Computer Soc, 2006. 25~29
[32] Urtasun R, Fleet D J, Fua P. Temporal Motion Models for Monocular and Multiview 3-D Human Body Tracking, Computer Vision and Image Understanding, 2006,104(2): 157~177
[33] Sigal L, Isard M, Sigelman B H, et al. Attractive people: Assembling loose-limbed models using non-parametric belief propagation. In: NIPS. Proceedings of 17th Annual Conference on Neural Information Processing Systems (NIPS), USA: MIT press, 2004. 1539~1546
[34] Leonid Sigal, S.Bhatia, S.Roth, M. J. Black. Tracking loose-limbed people. IEEE Conf. on Computer Vision and Pattern Recognition, 2004, 1(1):421~428
[35] Leonid Sigal.and M.J. Black, Measure locally, reason globally: Occlusion- sensitive articulated pose estimation, IEEE Conf. on Computer Vision and Pattern Recognition, New York, June 2006, 2:2041~2048
[36] Balan A, Black M J. An adaptive appearance model approach for model-basedarticulated object tracking. In: IEEE. Proceedings of Conference. on Computer Vision and Pattern Recognition, New York, USA: IEEE Computer Soc press 2006. 758~765
[37] Sigal L, Black M J. HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion. Techniacl Report CS-06-08, Brown University, 2006
[38]陈睿,刘国翌,赵国英,等.基于序列蒙特卡罗方法的3D人体运动跟踪.计算机辅助设计与图形学学报, 2005, 78~96
[39]刘国翌,陈睿,邓宇,等.基于视频的三维人体运动跟踪.计算机辅助设计与图形学学报, 2006, 18(1):83~88
[40] Wang L, Tan T, Ning H Z, Weiming Hu. Silhoutte analysis based gait recognition for human identification, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(2): 1505~1518,
[41]罗忠祥,庄越挺,刘丰,等.基于视频的人体动画.计算机研究与发展, 2007, 40(2): 269~276
[42] Pan H L, Liu Y C. Motion estimation of elastic articulated objects from points and contours with volume invariable constraint. Pattern Recognition, 2008, 41(2): 458~467
[43] Tong M L, Liu Y C, Huang T S. 3D human model and joint parameter estimation from monocular image. Pattern Recognition Letters, 2007, 28(7): 797~805
[44] Zhao X, Liu Y C. Generative Estimation of 3D Human Pose Using Shape Contexts Matching. In: ACCV. Proceedings of 8th Asian Conference on Computer Vision. Berlin, Germany: Springer-Verlag Berlin press, 2007. 419~429
[45] Zhao Xu, Liu Yuncai. Tracking 3D Human Motion in Compact Base Space Proceedings.In:WACV.Austin ,USA, 2007, 39~44
[46]刘国翌.基于视频的人体运动跟踪技术研究: [博士学位论文]。北京:中科院计算所, 2005.
[47] NEDEL,Luciana Porcher. Simulating Virtual Humans. XI Brazilian Symposium on Computer GraphicsOctober 1998.25~37
[48]陈睿.基于概率模型的三维人体跟踪研究: [博士学位论文]。北京:中科院, 2005.
[49] Sand P, Millan M L, Popovic J. Continuous Capture of Skin Deformation. In: ACM. Proceedings of Annual Symposium of the ACM SIGGRAPH. New York,USA: Assoc Computing Machinery press, 2003. 17~24
[50] Fleet D, Weiss Y. Optical flow estimation. In Mathematical Models of Computer Vision: The Handbook, N.Paragios et al. (eds). Springer, 2005,15:239~258
[51] Wachter S, Nagel H H. Tracking Persons in Monocular Image Sequences. Computer Vision and Image Understanding. 1999, 74(3):174~192
[52] Sidenbladh H, Black MJ, Sigal L. ImplicitProbabilistic models of human motion for synthesis and tracking.In: 7th European Conference on Computer Vision. Berlin, Germany . Springer-Verlag Berlin ,2002,784~800
[53] Hogg D C. Model-based vision:a program to see a walking person. Image and Vision Computing, 1983, 1(1):5~20
[54] Stauffer C, Grimson E L. Learning patterns of activity using real-time tracking. In:EEE Transactions on Pattern Analysis and Machine Intelligence. IEEE Computer Soc, Los Alamitos, USA, 2000. 747~757
[55] Khatib O. Reai-Time Obstacle Avoidance for Manipulators and Mobile Robots. The Int .J.of Robotics Research, 1986, 5(1): 90~98
[56] Bougust.J.Y. Calibration Toolbox for Matlab. http//www.vision.caltech.edu/ bougust/calib_doc/
[2] Taylor C J. Reconstruction of articulated objects from point correspondences in a single uncalibrated image. Computer Vision and Image Understanding, 2000, 80(3): 349~363
[3]邱显杰.基于视频的三维人体运动捕获方法研究: [博士学位论文]。北京:中科院计算所, 2006.
[4] Thomas B. Moeslund, Granum E. A survey of computer vision-based human motion capture. Computer Vision and Image Understanding, 2001, 81(3): 231~268
[5] Zhao X, Liu Y C. Generative tracking of 3D human motion by hierarchical annealed genetic algorithm. Pattern Recognition, 2008, 41(8): 2470~2483
[6] Urtasun R, Fleet D L, Fua P. Gaussian Process Dynamical Models for 3D people tracking. Computer Vision and Pattern Recognition, New York, June, 2006. 7-11
[7] Li R, Yang M H, Sclaroff S, et al. Monocular tracking of 3D human motion with a coordinated mixture of factor analyzers. In: ECCV. Proceedings of 9th European Conference on Computer Vision (ECCV 2006), Berlin, Germany: Springer-Verlag Berlin, 2006. 5~7
[8] Ning H Z, Xu W, Gong Y H, et al. Discriminative learning of visual words for 3D human pose estimation. In IEEE. Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. New York, USA 23-28 June 2008.1~8
[9] Nait H, Charif,S.J.McKenna. Head tracking and action recognition in a smart meeting room. Proceedings of 4th IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, Graz Austri,2003. 24~31
[10] Wu Y, Huang T S. Robust visual tracking by integrating multiple cues based on co-inference learning. International Journal of Computer Vision, 2004, 58(1): 55~71
[11] Shan C F, WeiY C, Tan T N, et al. Real time hand tracking by combining particle filtering and mean shift. In: Proceedings of 6th International Conference on Automatic Face and Gesture Recognition. Los Alamitos USA: IEEE Computer Soc press, 2004. 669~674
[12] KaewTrakulPong P, Bowden R. A real time adaptive visual surveillance system for tracking low-resolution colour targets in dynamically changing scenes. Image andVision Computing,2003, 21(10): 913~929
[13] Wang J, Cohen M F. Very low frame-rate video streaming for face-to-face teleconference. In: IEEE. Proceedings of IEEE Data Compression Conference. Los Alamitos, USA: IEEE Computer Soc press, 2005. 309~318
[14]陈坚.单目视频人体运动跟踪和获取技术研究: [博士学位论文]。北京:中科院计算所, 2005.
[15]仝明磊.非标定单目序列图像的三维人体运动分析: [博士学位论文]。上海:上海交通大学图像处理与模式识别研究所, 2007.
[16] Wang L, Hu W M, Tan T N. Recent Developments in Human Motion Analysis. Pattern Recognition, 2003, 36(3): 585~601
[17] T.B. Moeslund, A. Hilton, V. Krüger. A survey of advances in vision-based human motion capture and analysis. CVIU,2006,104 :90~126
[18] D.Hogg. Model-Based Vision: A Program to See a Walking Person. Image and Vision Computing, February 1983, 1(1):15~24
[19] R. T. Collins et al. A system for video surveillance and monitoring. VSAM final report, Carnegie Mellon University, 2000:17~25
[20] I. Haritaoglu, D. Harwood, L.S. Davis. W4: real-time surveillance of people and their activities. IEEE Trans on Pattern Analysis and Machine Intelligence, 22(8): 809~830
[21] Sminchisescu C, Triggs B. A Robust Multiple Hypothesis Approach to Monoclar Human Motion Tracking. INRIA Research Report, 2001, 15~19
[22] C.Sminchisescu,B.Triggs. Covariance Scaled Sampling for Monocular 3D Body Tracking. IEEE International Conference on Computer Vision and Pattern Recognition, Hawaii, 2001.56~64
[23] C.Sminchisescu,B.Triggs. Kinematic Jump Processes for Monocular 3D HumaTracking. IEEE International Conference on Computer Vision and Pattern Reognition, 2003.36-39
[24] Agarwal A, Triggs B. Recovering 3D human pose from monocular images. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI) ,2006, 28 (1): 44~58
[25] Agarwal A, Triggs B. 3D Human Pose from Silhouettes by Relevance Vector Regression. In: IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Los Alamitos USA: IEEE Computer Soc 2004.882~888
[26] Agarwal A, Triggs B. Tracking Articulated Motion using a Mixture of Autoregressive Models. In Proceedings of 8th European Conference on Computer Vision,Prague, Berlin, Germany: Springer-Verlag Berlin, 2004.19~31
[27] C.Sminchisescu,A.Kanaujia, Z. Li et al. Discriminative Density Propagation for 3D Human Motion Estimation. In: Proceedings of Conference on Computer Vision and Pattern Recognition. Los Alamitos USA: IEEE Computer Soc press, 2005.13~15
[28] C. Sminchisescu,A.Kanajujia,D.Metaxas. Learning Joint Top-Down and Bottom-Up Processes for 3D Visual Inference. In:IEEE. Proceedings of International Conference on Computer Vision and Pattern Recognition.New York, USA: IEEE Computer Soc2006. 17~19
[29] A.Kanaujia,C.Sminchisescu,D.Metaxas. Semi-supervised Hierarchical Models for 3D Human Pose Reconstruction. In:IEEE. Proceedings of Conference on Computer Vision and Pattern Recognition CVPR. New York, USA: IEEE press, 2007.10~11
[30] Urtasun R, Fleet D J,.Geiger A, et al. Modeling human locomotion with Topologically-Constrained Latent Variable Models.To appear in International 2nd Workshop on Human Motion Understanding, Modeling. Berlin, Germany: Springer-Verlag Berlin, 2008. 45~57
[31] Urtasun R, Fleet D J, Fua P. Gaussian Process Dynamical Models for 3D people tracking. In: IEEE. Proceedings of Conference on Computer Vision and Pattern Recognition, New York, USA: IEEE Computer Soc, 2006. 25~29
[32] Urtasun R, Fleet D J, Fua P. Temporal Motion Models for Monocular and Multiview 3-D Human Body Tracking, Computer Vision and Image Understanding, 2006,104(2): 157~177
[33] Sigal L, Isard M, Sigelman B H, et al. Attractive people: Assembling loose-limbed models using non-parametric belief propagation. In: NIPS. Proceedings of 17th Annual Conference on Neural Information Processing Systems (NIPS), USA: MIT press, 2004. 1539~1546
[34] Leonid Sigal, S.Bhatia, S.Roth, M. J. Black. Tracking loose-limbed people. IEEE Conf. on Computer Vision and Pattern Recognition, 2004, 1(1):421~428
[35] Leonid Sigal.and M.J. Black, Measure locally, reason globally: Occlusion- sensitive articulated pose estimation, IEEE Conf. on Computer Vision and Pattern Recognition, New York, June 2006, 2:2041~2048
[36] Balan A, Black M J. An adaptive appearance model approach for model-basedarticulated object tracking. In: IEEE. Proceedings of Conference. on Computer Vision and Pattern Recognition, New York, USA: IEEE Computer Soc press 2006. 758~765
[37] Sigal L, Black M J. HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion. Techniacl Report CS-06-08, Brown University, 2006
[38]陈睿,刘国翌,赵国英,等.基于序列蒙特卡罗方法的3D人体运动跟踪.计算机辅助设计与图形学学报, 2005, 78~96
[39]刘国翌,陈睿,邓宇,等.基于视频的三维人体运动跟踪.计算机辅助设计与图形学学报, 2006, 18(1):83~88
[40] Wang L, Tan T, Ning H Z, Weiming Hu. Silhoutte analysis based gait recognition for human identification, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(2): 1505~1518,
[41]罗忠祥,庄越挺,刘丰,等.基于视频的人体动画.计算机研究与发展, 2007, 40(2): 269~276
[42] Pan H L, Liu Y C. Motion estimation of elastic articulated objects from points and contours with volume invariable constraint. Pattern Recognition, 2008, 41(2): 458~467
[43] Tong M L, Liu Y C, Huang T S. 3D human model and joint parameter estimation from monocular image. Pattern Recognition Letters, 2007, 28(7): 797~805
[44] Zhao X, Liu Y C. Generative Estimation of 3D Human Pose Using Shape Contexts Matching. In: ACCV. Proceedings of 8th Asian Conference on Computer Vision. Berlin, Germany: Springer-Verlag Berlin press, 2007. 419~429
[45] Zhao Xu, Liu Yuncai. Tracking 3D Human Motion in Compact Base Space Proceedings.In:WACV.Austin ,USA, 2007, 39~44
[46]刘国翌.基于视频的人体运动跟踪技术研究: [博士学位论文]。北京:中科院计算所, 2005.
[47] NEDEL,Luciana Porcher. Simulating Virtual Humans. XI Brazilian Symposium on Computer GraphicsOctober 1998.25~37
[48]陈睿.基于概率模型的三维人体跟踪研究: [博士学位论文]。北京:中科院, 2005.
[49] Sand P, Millan M L, Popovic J. Continuous Capture of Skin Deformation. In: ACM. Proceedings of Annual Symposium of the ACM SIGGRAPH. New York,USA: Assoc Computing Machinery press, 2003. 17~24
[50] Fleet D, Weiss Y. Optical flow estimation. In Mathematical Models of Computer Vision: The Handbook, N.Paragios et al. (eds). Springer, 2005,15:239~258
[51] Wachter S, Nagel H H. Tracking Persons in Monocular Image Sequences. Computer Vision and Image Understanding. 1999, 74(3):174~192
[52] Sidenbladh H, Black MJ, Sigal L. ImplicitProbabilistic models of human motion for synthesis and tracking.In: 7th European Conference on Computer Vision. Berlin, Germany . Springer-Verlag Berlin ,2002,784~800
[53] Hogg D C. Model-based vision:a program to see a walking person. Image and Vision Computing, 1983, 1(1):5~20
[54] Stauffer C, Grimson E L. Learning patterns of activity using real-time tracking. In:EEE Transactions on Pattern Analysis and Machine Intelligence. IEEE Computer Soc, Los Alamitos, USA, 2000. 747~757
[55] Khatib O. Reai-Time Obstacle Avoidance for Manipulators and Mobile Robots. The Int .J.of Robotics Research, 1986, 5(1): 90~98
[56] Bougust.J.Y. Calibration Toolbox for Matlab. http//www.vision.caltech.edu/ bougust/calib_doc/
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |