Human Tracking and Body Silhouette Extraction System for Humanoid Robot

휴머노이드 로봇을 위한 사람 검출, 추적 및 실루엣 추출 시스템

  • 곽수영 (연세대학교 컴퓨터과학과) ;
  • 변혜란 (연세대학교 컴퓨터과학과)
  • Published : 2009.06.30

Abstract

In this paper, we propose a new integrated computer vision system designed to track multiple human beings and extract their silhouette with an active stereo camera. The proposed system consists of three modules: detection, tracking and silhouette extraction. Detection was performed by camera ego-motion compensation and disparity segmentation. For tracking, we present an efficient mean shift based tracking method in which the tracking objects are characterized as disparity weighted color histograms. The silhouette was obtained by two-step segmentation. A trimap is estimated in advance and then this was effectively incorporated into the graph cut framework for fine segmentation. The proposed system was evaluated with respect to ground truth data and it was shown to detect and track multiple people very well and also produce high quality silhouettes. The proposed system can assist in gesture and gait recognition in field of Human-Robot Interaction (HRI).

본 논문은 스테레오 카메라가 이동하는 환경에서 카메라 움직임을 보정하여 새로운 다수의 사람을 검출하는 방법과 검출된 사람을 추적하고, 실루엣을 추출하는 통합된 시스템을 제안한다. 제안하는 시스템은 사람 검출, 추적, 실루엣 추출 3가지 모듈로 구성되어 있으며 3가지 모듈은 카메라가 이동하는 환경을 고려한 것이다. 사람 검출 모듈에서는 카메라 움직임(egomotion) 보정을 이용한 움직이는 영역 추출 결과와 스테레오 정보를 결합하여 움직이는 객체를 검출하였으며, 추적모듈은 변위 정보가 가중된 히스토그램 알고리즘으로 검출된 객체를 추적한다. 실루엣을 추출하는 모듈은 트라이맵(trimap)을 이용하여 사람의 실루엣 부분을 대략적으로 추정하는 단계와 그래프컷(graph cut)을 적용하여 정교하게 실루엣 추출하는 단계로 이루어져 있다. 본 논문에서 제안하는 방법을 실내 환경에서 팬-틸트(pan-tilt) 스테레오 카메라로 획득한 실험데이터를 대상으로 실험한 결과 다수의 사람의 검출 및 추적, 정교한 실루엣 추출이 가능한 것을 확인하였다. 본 논문의 실루엣 추출결과는 제스처 인식이나 걸음걸이 인식 등의 다양한 분야에도 적용가능하다.

Keywords

References

  1. I. Haritaoglu, D. Harwood, and L.S. Davis,'W4: Real-Time Surveillance of People and Their Activities', IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.22, No.8, pp. 809-830, 2000 https://doi.org/10.1109/34.868683
  2. A. Yilmaz, X. Li and M. Shah, 'Object ContourTracking Using Level Sets', Asian Conferenceon Computer Vision, 2004
  3. L. Davis, V. Philomin and R. Duraiswami 'Tracking humans from a moving platform',The 15th International Conference on Pattern Recognition. Vol. 4, pp. 171-78, 2000 https://doi.org/10.1109/ICPR.2000.902889
  4. C. Stauffer and W. E. L. Grimson, 'Adaptive background mixture models for real-time tracking', Proceeding IEEE International Conference on Computer Vision and Pattern Recognition, pp. 246-252, 1999
  5. S. Yu, R. Gross and J. Shi, 'Concurrent object recognition and segmentation by graph partitioning', Proceeding Neural InformationProcessing Systems, pp. 1383-1390. 2002
  6. Y. Boykov, and M. Jolly, 'Iterative graph cuts for optimal boundary and region segmentation of objects in N-D Images,' Proceeding IEEE 8th International Conference on Computer Vision, Canada, 2001
  7. Y. Li, J. Sun, C.-K. Tang and H.-Y. Shum,'Lazy Snapping', Proceeding ACM SIGRAPH,Vol 23, No. 3, 2004 https://doi.org/10.1145/1015706.1015719
  8. A. Blake, C. Rother, M. Brown, P. Perez, and P. Torr. 'Interactive image segmentation using an adaptive GMMRF model,' Proceeding European Conference on Computer Vision, pp.428-442, 2004
  9. C. Harris and M. J. Stephens, 'A combined corner and edge detector,' In Alvey Vision Conference, pp. 147–152, 1988
  10. D. Comaniciu, and V. Ramesh.: Kernel-Based Object Tracking. IEEE Transaction on Pattern Analysis and Machine Intelligence Vol. 25. pp.564-577, 2003 https://doi.org/10.1109/TPAMI.2003.1195991
  11. M. P. Wand and M. C. Jones.: KernelSmoothing. Chapman & Hall. 1995
  12. D. Comaniciu and P. Meer, 'Mean shift: arobust approach toward feature space analysis,' IEEE Transaction on Pattern Analysis and Machine Intelligence, pp. 603-619, 2002
  13. Y. Boykov and V. Kolmogorov, 'An experimental comparison of min-cut/ max-flow algorithms for energy minimization in vision', IEEE Transaction on Pattern Analysis andMachine Intelligence, Vol. 26, pp. 1124-1137, 2004 https://doi.org/10.1109/TPAMI.2004.60