More Web Proxy on the site http://driver.im/

article

Recovery of upper body poses in static images based on joints detection

Authors:

Hong YanAuthors Info & Claims

Pattern Recognition Letters, Volume 30, Issue 5

Pages 503 - 512

https://doi.org/10.1016/j.patrec.2008.12.005

Published: 01 April 2009 Publication History

Abstract

Recovering human body poses from static images is challenging without prior knowledge of pose, appearance, background and clothing. In this paper, we propose a novel model-based upper poses recovery method via effective joints detection. In our research, three observables are firstly detected: face, skin, and torso. Then the joints are properly initialized according to the observables and some heuristic configuration constraints. Finally the sample-based Markov chain Monte Carlo (MCMC) method is employed to determine the final pose. The main contributions of this paper include a robust torso detector through maximizing a posterior estimation, effective joints initialization, and two continuous likelihood functions developed for effective pose inference. Experiments on 250 real world images show that our method can accurately recover upper body poses from images with a variety of individuals, poses, backgrounds and clothing.

References

[1]

3D human pose from silhouettes by relevance vector regression. Proc. IEEE Conf. on Computer Vision and Pattern Recognition. v2. 882-888.

[2]

Recovering 3D human pose from monocular images. IEEE Trans. Pattern Anal. Machine Intell. v28 i1. 44-56.

[3]

A local basis representation for estimating human pose from cluttered images. Proc. Asian Conf. on Computer Vision. v1. 50-59.

[4]

Applying 3D human model in a posture recognition system. Pattern Recognition Lett. v27 i15. 1788-1796.

[5]

Chenaoua, K., Bouridane, A., 2006. Skin detection using a markov random field and a new color space. In: Proceedings of IEEE International Conference on Image Processing, 8-11 October, pp. 2673-2676.

[6]

Training deformable models for localization. Proc. IEEE Conf. on Computer Vision and Pattern Recognition. v1. 206-213.

[7]

Fan, B., Wang, Z.F., 2004. Pose estimation of human body based on silhouette images. In: Proceedings of International Conference on Information Acquisition, 21-25 June, pp. 296-300.

[8]

Markov Chain Monte Carlo in Practice. Chapman & Hall.

[9]

Constraint integration for efficient multi-view pose estimation with self-occlusions. IEEE Trans. Pattern Anal. Machine Intell. v30 i3. 493-506.

[10]

Clothing segmentation based on the constrained Delaunay triangulation and foreground and background estimation. Pattern Recognition. v41 i5. 1598-1609.

[11]

Learning to estimate human pose with Data Driven Belief Propagation. Proc. IEEE Conf. on Computer Vision and Pattern Recognition. v2. 747-754.

[12]

A model-based approach for estimating human 3D poses in static images. IEEE Trans. Pattern Anal. Machine Intell. v28 i6. 905-916.

[13]

Lee, M.W., Nevatia, R., 2007. Body part detection for human pose estimation and tracking. In: Proc. IEEE workshop on Motion and Video Computing, pp. 23-31.

Digital Library

[14]

Menier, C., Boyer, E., Raffin, B., 2006. 3D skeleton-based body pose recovery. In: Proc. 3rd International Symposium on 3D Data Processing, Visualization and Transmission, pp. 389-396.

Digital Library

[15]

Estimating human body configurations using shape context matching. Proc. Eur. Conf. on Computer Vision. v3. 666-680.

[16]

Recovering 3D human body configurations using shape contexts. IEEE Trans. Pattern Anal. Machine Intell. v28 i7. 1052-1062.

[17]

Recovering human body configurations: Combining segmentation and recognition. Proc. IEEE Conf. on Computer Vision and Pattern Recognition. v2. 326-333.

[18]

NIST, 1977. Anthrokids - Anthropometric data of children, http://ovrt.nist.gov/projects/anthrokids/.

[19]

Poppe, R., Poel, M., 2005. Example-based pose estimation in monocular images using compact Fourier descriptors. Technical Report TR-CTIT-05-49, University of Twente, Enschede, The Netherlands.

[20]

Recovering human body configurations using pairwise constraints between parts. Proc. IEEE Conf. on Computer Vision. v1. 824-831.

[21]

Roberts, T.J., 2005. Efficient human pose estimation from real world images. Doctor Thesis, Univ. of Dundee, Scotland.

[22]

Face segmentation based on Hue-Cr components and morphological technique. Proc. IEEE Symp. Circuits Systems. v6. 5401-5404.

[23]

Fast pose estimation with parameter sensitive hashing. Proc. IEEE Conf. on Computer Vision. v2. 750-757.

[24]

Shewchuk, J.R., 1996. Triangle: Engineering a 2D quality mesh generator and Delaunay triangulator. In: Proc. 1st Workshop on Applied Computational Geometry, pp. 124-133.

[25]

Attractive people: Assembling loose-limbed models using non-parametric belief propagation. Proc. Conf. Advances Neural Inform. Process. System. v16. 1539-1546.

[26]

Singh, M., Mandal, M., Basu, A., 2005. Pose recognition using the Radon transform. In: Proc. 48th Midwest Symposium on Circuits and Systems, pp. 1091-1094.

[27]

Human pose estimation from silhouettes: A consistent approach using distance level sets. J. WSCG. v10 i1. 232-240.

[28]

Robust real-time face detection. Internat. J. Computer Vision. v57 i2. 137-154.

[29]

Human posture analysis under partial self-occlusion. Proc. IEEE Conf. Image Anal. Recognition. v1. 874-885.

[30]

Xiao, Y., Yan, H., 2004. Extraction of glasses in human face image. In: Proc. 1st International Conf. Biometric Authentication, pp. 214-220.

[31]

A color image segmentation algorithm by using color and spatial information. J. Software. v15 i4. 522-530.

[32]

Zhao, T., Nevatia, R., 2002. Stochastic human segmentation from a static camera. In: Proc. IEEE Workshop on Motion and Video Computing, pp. 9-14.

[33]

Shape skeletonization by identifying discrete local symmetries. Pattern Recognition. v34 i10. 1895-1905.

Cited By

He LWang GLiao QXue J(2018)Depth-images-based pose estimation using regression forests and graphical modelsNeurocomputing10.1016/j.neucom.2015.02.068164:C(210-219)Online publication date: 31-Dec-2018
https://dl.acm.org/doi/10.1016/j.neucom.2015.02.068
Migniot CAbabsa F(2018)Hybrid 3D---2D human tracking in a top viewJournal of Real-Time Image Processing10.1007/s11554-014-0429-711:4(769-784)Online publication date: 20-Dec-2018
https://dl.acm.org/doi/10.1007/s11554-014-0429-7
He LWang GLiao QXue J(2016)Latent variable pictorial structure for human pose estimation on depth imagesNeurocomputing10.1016/j.neucom.2016.04.009203:C(52-61)Online publication date: 26-Aug-2016
https://dl.acm.org/doi/10.1016/j.neucom.2016.04.009
Show More Cited By

Index Terms

Recovery of upper body poses in static images based on joints detection

Recommendations

A Model-Based Approach for Estimating Human 3D Poses in Static Images

Estimating human body poses in static images is important for many image understanding applications including semantic content extraction and image database query and retrieval. This problem is challenging due to the presence of clutter in the image, ...
On population-based simulation for static inference

In this paper we present a review of population-based simulation for static inference problems. Such methods can be described as generating a collection of random variables { X _n} _{n =1, , N} in parallel in order to simulate from some target ...
A review of 3D human body pose estimation and mesh recovery
Abstract
3D human body pose estimation and mesh recovery refer to the approximation of body parts and joint locations and their recovery into a 3D model to visualize the characteristics of the target object from input imaging data. Recent ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Pattern Recognition Letters

Pattern Recognition Letters Volume 30, Issue 5

April, 2009

121 pages

ISSN:0167-8655

Issue’s Table of Contents

Copyright © Elsevier B.V. © 2008.

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 01 April 2009

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

7
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 17 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

He LWang GLiao QXue J(2018)Depth-images-based pose estimation using regression forests and graphical modelsNeurocomputing10.1016/j.neucom.2015.02.068164:C(210-219)Online publication date: 31-Dec-2018
https://dl.acm.org/doi/10.1016/j.neucom.2015.02.068
Migniot CAbabsa F(2018)Hybrid 3D---2D human tracking in a top viewJournal of Real-Time Image Processing10.1007/s11554-014-0429-711:4(769-784)Online publication date: 20-Dec-2018
https://dl.acm.org/doi/10.1007/s11554-014-0429-7
He LWang GLiao QXue J(2016)Latent variable pictorial structure for human pose estimation on depth imagesNeurocomputing10.1016/j.neucom.2016.04.009203:C(52-61)Online publication date: 26-Aug-2016
https://dl.acm.org/doi/10.1016/j.neucom.2016.04.009
Sharma NMaringanti HAsawa KShyamasundar RShastri L(2012)Upper body pose recognition and classifierProceedings of the 5th ACM COMPUTE Conference: Intelligent & scalable system technologies10.1145/2459118.2459126(1-5)Online publication date: 23-Jan-2012
https://dl.acm.org/doi/10.1145/2459118.2459126
Li SLu HRuan XChen Y(2012)Human body segmentation based on deformable models and two-scale superpixelPattern Analysis & Applications10.1007/s10044-011-0220-315:4(399-413)Online publication date: 1-Nov-2012
https://dl.acm.org/doi/10.1007/s10044-011-0220-3
Zhou SFu HLiu LCohen-Or DHan XDeRose T(2010)Parametric reshaping of human bodies in imagesACM SIGGRAPH 2010 papers10.1145/1833349.1778863(1-10)Online publication date: 26-Jul-2010
https://dl.acm.org/doi/10.1145/1833349.1778863
Zhou SFu HLiu LCohen-Or DHan X(2010)Parametric reshaping of human bodies in imagesACM Transactions on Graphics10.1145/1778765.177886329:4(1-10)Online publication date: 26-Jul-2010
https://dl.acm.org/doi/10.1145/1778765.1778863

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents