Human pose estimation with data driven belief propagation

Details Human pose estimation with data driven belief propagation Human pose estimation with data driven belief propagation

2007-05-01

2007-05-01

Miriam, Daniel (Department: 2624)

Image analysis

Learning systems

Trainable classifiers or pattern recognizers

Reexamination Certificate

active

11266830

ABSTRACT:
A statistical formulation estimates two-dimensional human pose from single images. This is based on a Markov network and on inferring pose parameters from cues such as appearance, shape, edge, and color. A data-driven belief propagation Monte Carlo algorithm performs efficient Bayesian inferencing within a rigorous statistical framework. Experimental results demonstrate the effectiveness of the method in estimating human pose from single images.

REFERENCES:
patent: 2003/0103647 (2003-06-01), Rui et al.
patent: 2003/0208289 (2003-11-01), Ben-Arie
patent: 2005/0129278 (2005-06-01), Rui et al.
patent: 2005/0147278 (2005-07-01), Rui et al.
patent: 2005/0188013 (2005-08-01), Rui et al.
patent: 2005/0210103 (2005-09-01), Rui et al.
patent: 2005/0226471 (2005-10-01), Singh et al.
patent: WO 2005/096216 (2005-10-01), None
Black “inferring 3D people from 2D images”, department of computer science, Brown University, pp. 1-72, Aug. 2003.
Lin, et al “Capturing human hand motion in image sequences”, IEEE, pp. 1-6, 2002.
Moeslund, et al “Sequential monte carlo tracking of body parameters in a sub-space”, IEEE, pp. 1-8, 2003.
Sullivan, et al “Recognizing and tracking human action”, European conference on computer vision, LNCS 2352, vol. 1, pp. 1-16.
Barron, Carlos et al., “Estimating Anthropometry and Pose From a Single Uncalibrated Image,” Computer Vision and Image Understanding, 2001, pp. 269-284, vol. 81.
Buades Rubio, Jose Maria et al., “A New Method for Detection and Initial Pose Estimation Based on Mumford-Shah Segmentation Functional,” Universitat de les Illes Balears, 9 pages.
Felzenszwalb, Pedro et al., “Efficient Matching of Pictorial Structures,” 10 pages.
Freeman, William T., “Learning Low-Level Vision,” Mitsubishi Electric Information Technology Center America, 2000, 43 pages, Cambridge, MA.
Hua, Gang et al., “Multi-Scale Visual Tracking by Sequential Belief Propagation,” Proceedings of the IEEE Computer Society on Computer Vision and Patter Recognition (CVPR'04), 2004, 8 pages.
Ioffe, Sergey et al., “Finding People By Sampling,” 1999, IEEE, pp. 1092-1097.
Isard, M., “Pampas: Real-Valued Graphical Models for Computer Vision,” Microsoft Research, Mountain View, CA, 8 pages.
Jordan, Michael I., “Graphical Models: Probabilistic Inference,” 17 pages.
Lee, Mun Wai et al., “Proposal Maps Driven MCMC for Estimating Human Body Pose in Static Images,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR'2004), Jun. 2004, 8 pages.
Mori, Greg et al., “Recovering Human Body Configurations: Combining Segmentation and Recognition,” 8 pages.
Roth, Stefan et al., “Gibbs Likelihood for Bayesian Tracking,” 8 pages.
Shakhnarovich, Gregory et al., “Fast Pose Estimation with Parameter Sensitive Hashing, Al Memo 2003-009,” Apr. 2003, Massachusetts Institute of Technology, Cambridge, MA, 11 pages.
Sigal, Leonid et al., “Attractive People: Assembling Loose-Limbed Models Using Non-Parametric Belief Propagation,” 8 pages.
Sidenbladh, Hedvig et al., “Learning the Statistics of People in Images and Video,” International Journal of Computer Vision 54(1/2/3), 2003, pp. 183-209, Kluwer Academic Publishers, The Netherlands.
Sudderth, Erik B., “Nonparametric Belief Propagation,” Proceedings of the 2003 IEEE Conference on Computer Vision and Pattern Recognition, Jun. 2003, pp. 605-612, vol. I.
Tipping, Michael E., “Probabilistic Principal Component Analysis,” Microsoft Research, Sep. 27, 1999, 13 pages, Cambridge, UK.
Tu, Zhuowen et al., “Image Segmentation by Data-Driven Markov Chain Monte Carlo,” IEEE Transactions On Pattern Analysis and Machine Intelligence, May 2002, pp. 657-673, vol. 24, No. 5.
Viola, Paul et al., “Rapid Object Detection Using A Boosted Cascade of Simple Features,” Accepted Conference on Computer Vision and Pattern Recognition, 2001, 9 pages.

Affiliated with

Also associated with

Rating

Human pose estimation with data driven belief propagation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Human pose estimation with data driven belief propagation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Human pose estimation with data driven belief propagation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3737485