DOI QR코드

DOI QR Code

Implementation of a 3D Recognition applying Depth map and HMM

깊이 맵과 HMM을 이용한 인식 시스템 구현

  • Han, Chang-Ho (Dept. of Information and Communication Engineering, SunMoon University) ;
  • Oh, Choon-Suk (Dept. of Information and Communication Engineering, SunMoon University)
  • 한창호 (선문대학교 정보통신공학과) ;
  • 오춘석 (선문대학교 정보통신공학과)
  • Received : 2012.02.21
  • Accepted : 2012.04.13
  • Published : 2012.04.30

Abstract

Recently, we used to recognize for human motions with some recognition algorithms. examples, HMM, DTW, PCA etc. In many human motions, we concentrated our research on recognizing fighting motions. In previous work, to obtain the fighting motion data, we used motion capture system which is developed with some active markers and infrared rays cameras and 3 dimension information converting algorithms by the stereo matching method. In this paper, we describe that the different method to acquiring 3 dimension fighting motion data and a HMM algorithm to recognize the data. One of the obtaining 3d data we used is depth map algorithm which is calculated by a stereo method. We test the 3d acquiring and the motion recognition system, and show the results of accuracy and performance results.

최근 연구에서 모션 인식을 위해 여러 가지 인식 알고리즘을 사용하였다. 예를 들면, HMM, DTW, PCA 등의 기법을 이용하여 권투 모션을 인식하는 방법을 제시했다. 이러한 방법을 이용하기 위해서 연기자로부터 3차원 데이터를 얻기 위해 액티브 마커를 사용하여 손의 위치를 얻는다. 얻은 2차원 위치 정보는 다시 스테레오 기법을 이용하여 3차원 정보로 전환하여 구한다. 본 논문에서는 3차원 모션 데이터를 얻는 방법을 깊이 맵에 대한 알고리즘을 이용하여 구하였다. 그리고 3차원 위치 데이터 정보의 정확성 나타냈으며, 그리고 모션 동작에 대한 인식을 실험을 하였고, 그 실험 결과에 대해서 언급했다.

Keywords

References

  1. Jean, Grace V. Road warriors: robots get smarter, but who will buy them? National Defense, March 2008.
  2. Kageyama, Yuri. "Walking, talking female robot to hit Japan catwalk." The Seattle Times. 16 March 2009.
  3. OPRoS 팀, www.opros.or.kr
  4. Park,H.S., "Development of robot S/W platform verification and estimation automation technology", OPRoS combination workshop 2008. 11.
  5. Han,C.H., Oh,C.S., "Development of a 3D Object Recognition Component for OPRoS", IWIT, Vol11-3-12, 2011. 6
  6. Trucco, Emanuele. Introductory Techniques for 3D Computer Vision. Prentice Hall Inc, 1998.
  7. H. Jeong and S.C. Park, "Generalized Trellis Stereo Matching with Systolic Array," In Lecture Notes in Computer Science, Vol.3358, 2004, pp.263-267.
  8. Abhijit S. Ogale and Yiannis Aloimonos, "Shape and the Stereo Correspondence Problem", DCV 65,3, pp. 147- 162, 2005.
  9. Sukjune Yoon, Sung-Kee Park, Sungchul Kang, Yoon Keun Kwak, "Fast correlation-based stereo matching with the reduction of systematic errors", Pattern Recognition Letters 26, pp. 2221- 2231,2005. https://doi.org/10.1016/j.patrec.2005.03.037
  10. Michael Bleyer, Margrit Gelautz, "A layered stereo matching algorithm using image segmentation and global visibility constraints", ISPRS Journal of Photogrammetry & Remote Sensing 59, pp. 128- 150, 2005. https://doi.org/10.1016/j.isprsjprs.2005.02.008
  11. Hansung Kim, Kwanghoon Sohn, "3D reconstruction from stereo images for interactions between real and virtual objects", Signal Processing: Image Communication 20, pp. 61- 75, 2005. https://doi.org/10.1016/j.image.2004.10.004
  12. K. Muhlmann, D. Maier, 1. Hesser and R. Manner, "Calculating Dense Disparity Maps from Color Stereo Images, an Efficient Implementation", DCV 47, 1/2/3, pp. 79-88, 2002.
  13. Bradski, Gary; Kaehler, Adrian. Learning OpenCV: Computer Vision with the OpenCV Library. O'Reilly Media Inc, 2008.

Cited by

  1. Detection of Moving Objects using Depth Frame Data of 3D Sensor vol.14, pp.5, 2014, https://doi.org/10.7236/JIIBC.2014.14.5.243