ETRI Journal

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Fast Random-Forest-Based Human Pose Estimation Using a Multi-scale and Cascade Approach

  • Received : 2013.04.01
  • Accepted : 2013.11.05
  • Published : 2013.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Since the recent launch of Microsoft Xbox Kinect, research on 3D human pose estimation has attracted a lot of attention in the computer vision community. Kinect shows impressive estimation accuracy and real-time performance on massive graphics processing unit hardware. In this paper, we focus on further reducing the computation complexity of the existing state-of-the-art method to make the real-time 3D human pose estimation functionality applicable to devices with lower computing power. As a result, we propose two simple approaches to speed up the random-forest-based human pose estimation method. In the original algorithm, the random forest classifier is applied to all pixels of the segmented human depth image. We first use a multi-scale approach to reduce the number of such calculations. Second, the complexity of the random forest classification itself is decreased by the proposed cascade approach. Experiment results for real data show that our method is effective and works in real time (30 fps) without any parallelization efforts.

Keywords

References

  1. A. Baak et al., "A Data-Driven Approach for Real-Time Full Body Pose Reconstruction from a Depth Camera," Int. Conf. Comput. Vis., 2011, pp. 1092-1099.
  2. V. Ganapathi, "Real Time Motion Capture Using a Single Timeof- Flight Camera," Comput. Vis. Pattern Recog., 2010, pp. 755- 762.
  3. R. Girshick et al., "Efficient Regression of General-Activity Human Poses from Depth Images," Int. Conf. Comput. Vis., 2011, pp. 415-422.
  4. D. Grest, J. Woetzel, and R. Koch, "Nonlinear Body Pose Estimation from Depth Images," DAGM, 2005, pp. 285-292.
  5. S. Knoop, S. Vacek, and R. Dillamnn, "Sensor Fusion for 3D Human Body Tracking with an Articulated 3D Body Model," IEEE Int. Conf. Robotics Autom., May 2006, pp. 1686-1691.
  6. C. Plagemann et al., "Real-Time Identification and Localization of Body Parts from Depth Images," IEEE Int. Conf. Robotics Autom., May 2010, pp. 3108-3113.
  7. J. Shotton et al., "Real-Time Human Pose Recognition in Parts from Single Depth Images," Comput. Vis. Pattern Recog., June 2011, pp. 1297-1304.
  8. J. Shotton et al., "Efficient Human Pose Estimation from Single Depth Images," IEEE Trans. Pattern Anal. Mach. Intell., vol. 35, 2012, pp. 2821-2840.
  9. M. Siddiqui and G. Medioni, "Human Pose Estimation from a Single View Point, Real-Time Range Sensor," CVCG CVPR, San Francisco, CA, USA, June 2010.
  10. M. Sun, P. Kohli, and J. Shotton, "Conditional Regression Forests for Human Pose Estimation," Comput. Vis. Pattern Recog., 2012, pp. 3394-3401.
  11. J. Taylor et al., "The Vitruvian Manifold: Inferring Dense Correspondences for One-Shot Human Pose Estimation," Comput. Vis. Pattern Recog., 2012, pp. 103-110.
  12. M. Ye and X. Wang, "Accurate 3D Pose Estimation from a Single Depth Image," Int. Conf. Comput. Vis., 2011, pp. 731-738.
  13. Y. Zhu, B. Dariush, and K. Fujimura, "Controlled Human Pose Estimation from Depth Image Streams," Comput. Vis. Pattern Recog., Anchorage, AK, USA, June 2008.
  14. Y. Zhu and K. Fujimura, "Constrained Optimization for Human Pose Estimation from Depth Sequences," Asian Conf. Comput. Vis., Nov. 2007, pp. 408-418.
  15. J. Ziegler, K. Nickel, and R. Stiefelhagen, "Tracking of the Articulated Upper Body on Multi-view Stereo Image Sequences," Comput. Vis. Pattern Recog., 2006, pp. 774-781.
  16. A. Hernández-Vela et al., "Graph Cuts Optimization for Multilimb Human Segmentation in Depth Maps," Comput. Vis. Pattern Recog., June 2012, pp. 726-732.
  17. D. Jo et al., "Tracking and Interaction Based on Hybrid Sensing for Virtual Environments," ETRI J., vol. 35, no. 2, Apr. 2013, pp. 356-359. https://doi.org/10.4218/etrij.13.0212.0170
  18. Microsoft Corp, "Kinect for XBOX 360," Redmond, WA, USA.
  19. L. Breiman, "Random Forests," Mach. Learning, vol. 45, 2001, pp. 5-32. https://doi.org/10.1023/A:1010933404324
  20. D. Comaniciu and P. Meer, "Mean Shift: A Robust Approach toward Feature Space Analysis," IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, 2002, pp. 603-619. https://doi.org/10.1109/34.1000236
  21. S. Escalera, "Human Behavior Analysis from Depth Maps," AMDO, LNCS, vol. 7378, 2012, pp. 282-292.
  22. T.B. Moeslund, A. Hilton, and V. Krüger, "A Survey of Advances in Vision-Based Human Motion Capture and Analysis," Comput. Vis. Image Understanding, vol. 104, 2006, pp. 90-126. https://doi.org/10.1016/j.cviu.2006.08.002
  23. R. Poppe, "Vision-Based Human Motion Analysis: An Overview," Comput. Vis. Image Understanding, vol. 108, 2007, pp. 4-18. https://doi.org/10.1016/j.cviu.2006.10.016
  24. V. Lepetit, P. Lagger, and P. Fua, "Randomized Trees for Real- Time Keypoint Recognition," Comput. Vis. Pattern Recog., 2005, pp. 775-781.
  25. F. Moosmann, B. Triggs, and F. Jurie, "Fast Discriminative Visual Codebooks Using Randomized Clustering Forests," Neural Inf. Process. Syst., 2006, pp. 985-992.
  26. J. Shotton, M. Johnson, and R. Cipolla, "Semantic Texton Forests for Image Categorization and Segmentation," Comput. Vis. Pattern Recog., Anchorage, AK, USA, June 2008.
  27. L. Breiman, "Bagging Predictors," Mach. Learning, vol. 24, 1996, pp. 123-140.
  28. Y. Amit and D. Geman, "Shape Quantization and Recognition with Randomized Trees," Neural Comput., vol. 9, 1997, pp. 1545-1588. https://doi.org/10.1162/neco.1997.9.7.1545
  29. T.K. Ho, "The Random Subspace Method for Constructing Decision Forests," IEEE Trans. Pattern Anal. Mach. Intell., vol. 20, 1998, pp. 832-844. https://doi.org/10.1109/34.709601

Cited by

  1. Dual-Phase Approach to Improve Prediction of Heart Disease in Mobile Environment vol.37, pp.2, 2013, https://doi.org/10.4218/etrij.15.2314.0103
  2. Depth-based detection with region comparison features vol.38, pp.None, 2013, https://doi.org/10.1016/j.jvcir.2016.02.008
  3. Human Pose Estimation from Monocular Images: A Comprehensive Survey vol.16, pp.12, 2013, https://doi.org/10.3390/s16121966
  4. 데이터마이닝을 활용한 골프 스윙 최적화 분석 vol.31, pp.2, 2013, https://doi.org/10.5103/kjsb.2021.31.2.87