Journal of KIISE:Software and Applications (한국정보과학회논문지:소프트웨어및응용)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Rotation Invariant 3D Star Skeleton Feature Extraction

회전무관 3D Star Skeleton 특징 추출

  • Published : 2009.10.15
Download PDF
⟨ Previous Next ⟩

Abstract

Human posture recognition has attracted tremendous attention in ubiquitous environment, performing arts and robot control so that, recently, many researchers in pattern recognition and computer vision are working to make efficient posture recognition system. However the most of existing studies is very sensitive to human variations such as the rotation or the translation of body. This is why the feature, which is extracted from the feature extraction part as the first step of general posture recognition system, is influenced by these variations. To alleviate these human variations and improve the posture recognition result, this paper presents 3D Star Skeleton and Principle Component Analysis (PCA) based feature extraction methods in the multi-view environment. The proposed system use the 8 projection maps, a kind of depth map, as an input data. And the projection maps are extracted from the visual hull generation process. Though these data, the system constructs 3D Star Skeleton and extracts the rotation invariant feature using PCA. In experimental result, we extract the feature from the 3D Star Skeleton and recognize the human posture using the feature. Finally we prove that the proposed method is robust to human variations.

포즈인식은 최근에 유비쿼터스 환경, 행위 예술, 로봇 제어 등에서 그 필요성이 증가되고 있는 분야로써, 컴퓨터비전, 패턴인식 등에서 활발히 연구되고 있다. 하지만 기존의 포즈인식 연구들은 사람의 회전이나 이동에 따라서 불안정한 인식률을 보인다는 단점을 갖고 있다. 이는 포즈 인식을 위해 추출한 특징이 사람의 회전, 이동 등의 다양한 변수에 영향을 크게 받기 때문이다. 이를 극복하기 위하여 본 논문에서는, 다 시점(multi-view) 환경에서의 3D Star Skeleton과 주성분 분석(principal component analysis: PCA)에 기반한 사람의 회전에 강건한 특징 추출을 제안한다. 제안된 시스템은 포즈의 특징 추출을 위해 다 시점 환경 기반의 visual hull을 생성하는 과정에서 획득 가능한 깊이 정보를 표현하는 8개의 projection map을 입력데이터로 사용한다. 이를 통해 포즈의 3D 정보를 반영하는 3D Star Skeleton을 구성하고 주성분 분석 기반의 회전에 강건한 특징을 추출한다. 실험결과에서는 다양하게 회전된 사람으로부터 생성된 3D Star Skeleton에서 특징을 추출하고 다양한 인식기를 통해 포즈인식을 해보았으며, 제안된 특징 추출 방법이 사람의 회전에 강건함을 알 수 있었다.

Keywords

References

  1. I. Haritaoglu, D. Harwood and L.S. Davis, 'Ghost: A human body part labeling system using silhouettes,' Proc. of the 14th International Conference on Pattern Recognition, pp.77-82, 1998 https://doi.org/10.1109/ICPR.1998.711084
  2. C. Wren, A. Azarbayejani, T. Darrell and A. Pentland, 'Pfinder: Real time tracking of the human body,' IEEE Transactions on Pattern Analysis Machine Intelligence, pp.780-785, 1997 https://doi.org/10.1109/34.598236
  3. S. Iwasawa, K. Ebihara, J. Ohya, S. Morishima, 'Real-Time Estimation of Human Body Posture from Monocular Thermal Images,' Proc. of 1997 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp.15-20, 1997 https://doi.org/10.1109/CVPR.1997.609290
  4. V. Girondel, A. Caplier, L. Bonnaud and M. Rombaut, 'Belief theory-based classifiers comparison for static human body postures recognition in video,' International Journal of Signal Processing, vol.2, pp.29-33, 2005
  5. A. Baumberg and D. Hogg, 'An adaptive eigenshape model,' Proc. of British Machine Vision Conference, vol.1, pp.87-96, 1995
  6. H. Fujiyoshi, A.J. Lipton and T. Kanade, 'Realtime human motion analysis by image skeletonization,' IEICE Transactions on Information Systems, pp.113-120, 2004
  7. H.S. Chen, H.T. Chen, Y.W. Chen and S.Y. Lee, 'Human Action Recognition Using Star Skeleton,' Proc. of the 4th ACM international workshop on Video surveillance and sensor networks, pp. 171-178, 2006 https://doi.org/10.1145/1178782.1178808
  8. L. Panini and R. Cucchiara, 'A machine learning approach for human posture detection in domestics applications,' Proc. of the 12th International Conference on Image Analysis and Processing, pp. 103-108, 2003 https://doi.org/10.1109/ICIAP.2003.1234034
  9. Y. Kameda, M. Minoh and K. Ikeda, 'Three dimensional pose estimation of an articulated object from its silhouette image,' Proc. of the Asian Conference on Computer Vision, pp.612-615, 1993
  10. G. Mori and J. Malik, 'Estimating Human Body Configurations Using Shape Context Matching,' Proc. of the 7th European Conference on Computer Vision Copenhagen, LNCS, vol.2352, pp. 150-180, 2002
  11. G. Shakhnarovich, P. Viola, T. Darrell, 'Fast Pose Estimation with Parameter-Sensitive Hashing,' Proc. of the 9th IEEE International Conference on Computer Vision, vol.2, pp.750-757, 2003 https://doi.org/10.1109/ICCV.2003.1238424
  12. A.R. Micilotta, E.J. Ong and R. Bowden, 'Realtime upper body detection and 3D pose estimation in monoscopic images,' Proc. of the 9th European Conference on Computer Vision, LNCS, vol.3953, pp.139-150, 2006
  13. B. Boulay, F. Bremond and M. Thonnat, 'Applying 3d human model in a posture recognition system,' Pattern Recognition Letter, vol.27, pp. 1788-1796, 2006 https://doi.org/10.1016/j.patrec.2006.02.008
  14. J.S. Hu, T.M. Su, P.C. L., '3-D Human Posture Recognition System Using 2-D Shape Features,' IEEE International Conference on Robotics and Automation, pp.3933-3938, 2007
  15. Y. Wu and T.S. Huang, 'View-independent Recognition of Hand Postures,' Proc. of IEEE Conference on Computer Vision and Pattern Recognition, vol.2, pp.88-94, 2000 https://doi.org/10.1109/CVPR.2000.854749
  16. A. Imai, N. Shimada and Y. Shirai, '3-D Hand Posture Recognition by Training Contour Variation,' Proc. of the 6th IEEE International Conference on Automatic Face and Gesture Recognition, pp.895-900, 2004 https://doi.org/10.1109/AFGR.2004.1301647
  17. L. Ren, G. Shakhnarovich, J. Hodgins, H. Pfister and P. Viola, 'Learning Silhouette Features for Control of Human Motion,' Proc. of International Conference on Computer Graphics and Interactive Techniques, vol.24, no.4, p.129, 2005 https://doi.org/10.1145/1095878.1095882
  18. Q. Delamarre and O. Faugeras, '3D articulated models and Multi-View tracking with silhouettes,' Proc. of the 7th IEEE International Conference on Computer Vision, pp.716-721, 1999 https://doi.org/10.1109/ICCV.1999.790292
  19. I. Cohen and H. Li, 'Posture and Gesture Recognition using 3D Body Shapes Decomposition,' Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, p. 69, 2005 https://doi.org/10.1109/CVPR.2005.510
  20. A. Mohan, C. Papageorgiou, and T. Poggio, 'Example-Based Object Detection in Images by Components,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.23, no.4, pp. 349-361, 2001 https://doi.org/10.1109/34.917571
  21. B. Moghaddam and M.H. Yang, 'Learning Gender with Support Faces,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.24, no.5, pp.707-711, 2002 https://doi.org/10.1109/34.1000244
  22. M.H. Yang, 'Extraction of 2D Motion Trajectories and Its Application to Hand Gesture Recognition,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.24, no.8, pp.1061-1074, 2002 https://doi.org/10.1109/TPAMI.2002.1023803
  23. A.D. Wilson and A.F. Bobick, 'Configuration States for the Representation and Recognition of Gesture,' Proceeding on International Workshop Automatic Face and Gesture Recognition, pp. 129-134, 1995
  24. D.S. Yeung and X.Z. Wang, 'Improving Performance of Similarity-Based Clustering by Feature Weight Learning,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.24, no.4, pp.556-561, 2002 https://doi.org/10.1109/34.993562
  25. M. Bicego and V. Murino, 'Investigating Hidden Markov Models’ Capabilities in 2D Shape Classification,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.26, no.2, pp.281-286, 2004 https://doi.org/10.1109/TPAMI.2004.1262200
  26. P. Peursum, H.H. Bui, S. Venkatesh and G. West, 'Robust recognition and segmentation of human actions using HMMs with missing observations,' EURASIP Journal on Applied Signal Processing, Special Issue on Advances in Intelligent Vision Systems, vol.13, pp.2110-2126, 2005 https://doi.org/10.1155/ASP.2005.2110
  27. K. Hong, C. Lee, K. Jung and K. Oh, 'Real-time 3D Feature Extraction without Explicit 3D Object Representation,' Proc. of World Academy of Science, Engineering and Technology, vol.34, pp. 283-288, 2008
  28. A. Laurentini, 'The Visual Hull Concept for Silhouette-based Image Understanding,' IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.16, pp.150-162, 1994 https://doi.org/10.1109/34.273735
  29. J.Liu, S.Chen and X.Tan, 'Fractional Order Singular Value Decomposition Representation for Face Recognition,' Pattern Recognition, vol.41, pp.378-395, 2008 https://doi.org/10.1016/j.patcog.2007.03.027
  30. A. Imai, N. Shimada and Y. Shirai, '3-D Hand Posture Recognition by Training Contour Variation,' Proc. of the 6th IEEE International Conference on Automatic Face and Gesture Recognition, pp.895-900, 2004 https://doi.org/10.1109/AFGR.2004.1301647