[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
article

Multiple people tracking and pose estimation with occlusion estimation

Published: 01 May 2012 Publication History

Abstract

Simultaneously tracking poses of multiple people is a difficult problem because of inter-person occlusions and self occlusions. This paper presents an approach that circumvents this problem by performing tracking based on observations from multiple wide-baseline cameras. The proposed global occlusion estimation approach can deal with severe inter-person occlusions in one or more views by exploiting information from other views. Image features from non-occluded views are given more weight than image features from occluded views. Self occlusion is handled by local occlusion estimation. The local occlusion estimation is used to update the image likelihood function by sorting body parts as a function of distance to the cameras. The combination of the global and the local occlusion estimation leads to accurate tracking results at much lower computational costs. We evaluate the performance of our approach on a pose estimation data set in which inter-person and self occlusions are present. The results of our experiments show that our approach is able to robustly track multiple people during large movement with severe inter-person occlusions and self occlusions, whilst maintaining near real-time performance.

References

[1]
Moeslund, T.B., Hilton, A. and Kruger, V., A survey of advances in vision-based human motion capture and analysis. Computer Vision and Image Understanding. v104. 90-126.
[2]
Poppe, R., Vision-based human motion analysis: an overview. Computer Vision and Image Understanding. v108. 4-18.
[3]
Gavrila, D. and Davis, L.S., 3D model-based tracking of human in action: a multi-view approach. CVPR. 73-80.
[4]
Gupta, A., Mittal, A. and Davis, L.S., Constraint integration for efficient multiview pose estimation with self-occlusions. IEEE Transactions on Pattern Analysis and Machine Intelligence. v30 i3. 493-506.
[5]
Lee, M.W. and Nevatia, R., Human pose tracking in monocular sequence using multilevel structured models. IEEE Transactions on Pattern Analysis and Machine Intelligence. v31 i1. 27-38.
[6]
Lee, M.W. and Cohen, I., A model-based approach for estimating human 3D poses in static images. IEEE Transactions on Pattern Analysis and Machine Intelligence. v28 i6. 905-916.
[7]
Zhu, Y., Dariush, B. and Fujimura, K., Kinematic self retargeting: a framework for human pose estimation. Computer Vision and Image Understanding. v114. 1362-1375.
[8]
Lanz, O., Chippendale, P. and Brunelli, R., An appearance-based particle filter for visual tracking in smart room. Lecture Notes in Computer Science. v4625. 57-69.
[9]
Lanz, O., Approximation Bayesian multibody tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence. v28 i9. 1436-1449.
[10]
Stauffer, C. and Grimson, W., Adaptive background mixture models for real-time tracking. CVPR. v2. 246-252.
[11]
P. KaewTraKulPong, R. Bowden, An improved adaptive background mixture model for real-time tracking with shadow detection, in: Proceedings European Workshop on Advanced Video Based Surveillance System, 2001.
[12]
Comaniciu, D., Ramesh, V. and Meer, P., Kernel-based object tracking. IEEE Transactions on Pattern Analysis and Machine Intelligence. v25 i5. 564-577.
[13]
Jiang, H., Human pose estimation using consistent max-covering. ICCV. 1357-1364.
[14]
Tracking people by learning their appearance. IEEE Transactions on Pattern Analysis and Machine Intelligence. v29 i1. 65-81.
[15]
Deutscher, J., Blake, A. and Reid, I., Articulated body motion capture by annealed particle filtering. CVPR. v2. 126-133.
[16]
Deutscher, J. and Reid, I., Articulated body motion capture by stochastic search. International Journal of Computer Vision. v61 i2. 185-205.
[17]
A. Micilotta, Detection and tracking of humans for visual interaction, Doctoral Thesis, School of Electronics and Physical Sciences, University of Surrey, September 2005, pp. 43-47.
[18]
Sigal, L., Bhatia, S., Roth, S., Black, M.J. and Isard, M., Tracking loose-limbed people. CVPR. 421-428.
[19]
An adaptive appearance model approach for model-based articulated object tracking. CVPR. 421-428.
[20]
J. Jung, K. Cho, H.S. Yang, Real-time robust body part tracking for augmented reality interface, in: 8th International Conference on Virtual Reality Continuum and its Applications in Industry, 2009, pp. 203-207.
[21]
Sigal, L., Balan, A.O. and Black, M.J., HumanEva: synchronized video and motion capture dataset and baseline algorithm for evaluation of articulated human motion. International Journal of Computer Vision. v87 i1. 4-27.
[22]
Peursum, P., Venkatesh, S. and West, G., A study on smoothing for particle-filtered 3D human body tracking. International Journal of Computer Vision. v87 i1. 53-74.
[23]
Gall, J., Rosenhahn, B., Brox, T. and Seidel, H.P., Optimization and filtering for human motion capture. International Journal of Computer Vision. v87 i1. 75-92.
[24]
Rogez, G., Rihan, J. and Ramalingam, S., Randomized trees for human pose detection. CVPR. 1-8.
[25]
Okad, R. and Soatto, S., Relevant feature selection for human pose estimation and localization in cluttered images. ECCV. v2. 434-445.
[26]
N. Thome, D. Merad, S. Miguet, Human body part labeling and tracking using graph matching theory, in: International Conference on Video and Signal Based Surveillance, 2006, pp. 38-43.
[27]
Hoshino, R. and Arita, D., Real-time human motion analysis based on analysis of silhouette contour and color blob. Lecture Notes in Computer Science. 92-103.
[28]
Isard, M. and Blake, A., CONDENSATION-conditional density propagation for visual tracking. International Journal of Computer Vision. v29. 5-28.
[29]
F.M., Porikli, O. Tuzel, Human body tracking by adaptive background models and mean-shift analysis, in: IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, 2003.
[30]
Agarwal, A. and Triggs, B., Recovering 3D human pose from monocular images. IEEE Transactions on Pattern Analysis and Machine Intelligence. v28 i1. 44-58.
[31]
Mori, G. and Malik, J., Recovering 3D human body configurations using shape contexts. IEEE Transactions on Pattern Analysis and Machine Intelligence. v28 i7. 1052-1062.
[32]
Yue, Z. and Chellappa, R., Synthesis of silhouettes and visual hull reconstruction for articulated humans. IEEE Transactions on Multimedia. v10 i8. 1565-1577.
[33]
Sundaresan, A. and Chellappa, R., Multicamera tracking of articulated human motion using shape and motion cues. IEEE Transactions on Image Processing. v18 i9. 2114-2126.
[34]
Buehler, P., Everingham, M., Huttenlocher, D.P. and Zisserman, A., Long term arm and hand tracking for continuous sign language TV broadcasts. BMVC. 1105-1114.
[35]
F. Huo, E.A. Hendriks, P. Paclik, A.H.J. Oomes, Markerless human motion capture and pose recognition, in: International Workshop on Image Analysis for Multimedia Interactive Services, 2009, pp. 13-16.
[36]
Background and foreground modeling using nonparametric kernel density estimation for visual surveillance. Proceedings of the IEEE. v90 i7. 1151-1163.
[37]
Wren, C.R., Azarbayejani, A., Darrell, T. and Pentland, A.P., Pfinder: real-time tracking of the human body. IEEE Transaction on Pattern Analysis and Machine Intelligence. v19 i7. 780-785.
[38]
Mitchelson, J.R. and Hilton, A., Simultaneous pose estimation of multiple people using multiple-view cues with hierarchical sampling. BMVC.
[39]
F. Huo, E.A. Hendriks, A.H.J. Oomes, P. van Beek, R. Veltkamp, Detection tracking and recognition of human poses for a real time spatial game, in: CASA Workshop on 3D Advanced Media In Gaming and Simulation, 2009, pp. 43-51.
[40]
Maccormick, J. and Blake, A., A probability exclusion principle for tracking multiple objects. International Journal of Computer Vision. v39 i1. 57-71.
[41]
Doucet, A., Godsill, S. and Andrieu, C., On sequential Monte Carlo sampling methods for Bayesian filtering. Statistics and Computing. v10 i3. 197-208.
[42]
Ferrari, V., Marin-Jimenez, M. and Zisserman, A., Progressive search space reduction for human pose estimation. CVPR. 1-8.
[43]
Kuo, P., Makris, D. and Nebel, J.C., Integration of bottom-up/top-down approaches for 2D pose estimation using probabilistic Gaussian modeling. Computer Vision and Image Understanding. v115 i2. 242-255.
[44]
Utsumi, A. and Ohya, J., Multiple-hand-gesture tracking using multiple cameras. CVPR. 473-478.
[45]
MacCormick, J. and Isard, M., Partitioned sampling, articulated objects, and interface-quality hand tracking. ECCV. 3-19.

Cited By

View all
  • (2016)Parallel algorithm implementation for multi‐object tracking and surveillanceIET Computer Vision10.1049/iet-cvi.2015.011510:3(202-211)Online publication date: 1-Apr-2016
  1. Multiple people tracking and pose estimation with occlusion estimation

      Recommendations

      Comments

      Please enable JavaScript to view thecomments powered by Disqus.

      Information & Contributors

      Information

      Published In

      cover image Computer Vision and Image Understanding
      Computer Vision and Image Understanding  Volume 116, Issue 5
      May, 2012
      71 pages

      Publisher

      Elsevier Science Inc.

      United States

      Publication History

      Published: 01 May 2012

      Author Tags

      1. Multiple people tracking
      2. Occlusion estimation
      3. Pose estimation

      Qualifiers

      • Article

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)0
      • Downloads (Last 6 weeks)0
      Reflects downloads up to 06 Jan 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2016)Parallel algorithm implementation for multi‐object tracking and surveillanceIET Computer Vision10.1049/iet-cvi.2015.011510:3(202-211)Online publication date: 1-Apr-2016

      View Options

      View options

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media