People tracking based on motion model and motion constraints with automatic initialization

Human motion analysis is currently one of the most active research topics in computer vision. This paper presents a model-based approach to recovering motion parameters of walking people from monocular image sequences in a CONDENSATION framework. From the semi-automatically acquired training data, we learn a motion model represented as Gaussian distributions, and explore motion constraints by considering the dependency of motion parameters and represent them as conditional distributions. Then both of them are integrated into a dynamic model to concentrate factored sampling in the areas of the state-space with most posterior information. To measure the observation density with accuracy and robustness, a pose evaluation function (PEF) combining both boundary and region information is proposed. The function is modeled with a radial term to improve the efficiency of the factored sampling. We also address the issue of automatic acquisition of initial model pose and recovery from severe failures. A large number of experiments carried out in both indoor and outdoor scenes demonstrate that the proposed approach works well (C) 2004 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

[1]  Dariu Gavrila,et al.  The Visual Analysis of Human Movement: A Survey , 1999, Comput. Vis. Image Underst..

[2]  Jake K. Aggarwal,et al.  Human Motion Analysis: A Review , 1999, Comput. Vis. Image Underst..

[3]  H. Shum,et al.  Learning A Highly Structured Motion Model for 3D Human Tracking , 2002 .

[4]  Peter Green,et al.  Markov chain Monte Carlo in Practice , 1996 .

[5]  Junichi Hoshino,et al.  A match moving technique for merging CG and human video sequences , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[6]  Michael Isard,et al.  A mixed-state condensation tracker with automatic model-switching , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[7]  Olivier D. Faugeras,et al.  3D Articulated Models and Multiview Tracking with Physical Forces , 2001, Comput. Vis. Image Underst..

[8]  Hsi-Jian Lee,et al.  Determination of 3D human body postures from a single view , 1985, Comput. Vis. Graph. Image Process..

[9]  D. Lowe.  Fitting Parameterized 3-D Models to Images , 1989 .

[10]  Tieniu Tan,et al.  Automatic gait recognition based on statistical shape analysis , 2003, IEEE Trans. Image Process..

[11]  Olivier D. Faugeras,et al.  3D articulated models and multi-view tracking with silhouettes , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[12]  Cristian Sminchisescu,et al.  Covariance scaled sampling for monocular 3D body tracking , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[13]  Chris J. Harris,et al.  Statistical gait recognition via temporal moments , 2000 .

[14]  Hans-Hellmut Nagel,et al.  Tracking Persons in Monocular Image Sequences , 1999, Comput. Vis. Image Underst..

[15]  M. P. Murray.  Gait as a total pattern of movement. , 1967, American journal of physical medicine.

[16]  B. Triggs,et al.  A Robust Multiple Hypothesis Approach to Monocular Human Motion Tracking , 2000 .

[17]  Derek R. Magee,et al.  Detecting Lameness in Livestock using Resampling Condensation and Multi-stream Cyclic Hidden Markov Models , 2000, BMVC.

[18]  Mark S. Nixon,et al.  Automatic Gait Recognition by Symmetry Analysis , 2001, AVBPA.

[19]  Alex Pentland,et al.  Looking at People: Sensing for Ubiquitous and Wearable Computing , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  K. Rohr.  Towards model-based recognition of human movements in image sequences , 1994 .

[21]  Andrea Bottino,et al.  A Silhouette Based Technique for the Reconstruction of Human Movement , 2001, Comput. Vis. Image Underst..

[22]  Tieniu Tan,et al.  Model-based tracking of human walking in monocular image sequences , 2002, 2002 IEEE Region 10 Conference on Computers, Communications, Control and Power Engineering. TENCOM '02. Proceedings..

[23]  Tieniu Tan,et al.  Articulated model based people tracking using motion models , 2002, Proceedings. Fourth IEEE International Conference on Multimodal Interfaces.

[24]  José M. F. Moura,et al.  Capture and Representation of Human Walking in Live Video Sequences , 1999, IEEE Trans. Multim..

[25]  David C. Hogg.  Model-based vision: a program to see a walking person , 1983, Image Vis. Comput..

[26]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[27]  Pascal Fua,et al.  Articulated Soft Objects for Video-based Body Modeling , 2001, ICCV.

[28]  Thomas B. Moeslund,et al.  A Survey of Computer Vision-Based Human Motion Capture , 2001, Comput. Vis. Image Underst..

[29]  Yoshiaki Shirai,et al.  Model-Based Vision , 1984 .

[30]  David J. Fleet,et al.  Stochastic Tracking of 3D Human Figures Using 2D Image Motion , 2000, ECCV.

[31]  Christoph Bregler,et al.  Learning and recognizing human dynamics in video sequences , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[32]  Adam Prügel-Bennett,et al.  New Area Based Metrics for Gait Recognition , 2001, AVBPA.

[33]  Murray Mp,et al.  Gait as a total pattern of movement. , 1967 .

[34]  Michael Isard,et al.  ICONDENSATION: Unifying Low-Level and High-Level Tracking in a Stochastic Framework , 1998, ECCV.

[35]  A. David Marshall,et al.  A Hierarchical Model of Dynamics for Tracking People with a Single Video Camera , 2000, BMVC.

[36]  David G. Lowe,et al.  Fitting Parameterized Three-Dimensional Models to Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[37]  Mark S. Nixon,et al.  Statistical gait description via temporal moments , 2000, 4th IEEE Southwest Symposium on Image Analysis and Interpretation.

[38]  Shaogang Gong,et al.  A Dynamic 3D Human Model using Hybrid 2D-3D Representations in Hierarchical PCA Space , 1999, BMVC.

[39]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.