DOI QR코드

DOI QR Code

Fast and Accurate Algorithm for Motion Estimation in Mobile Environments

모바일 환경에서 모션 추정을 위한 빠르고 정확한 알고리즘

  • 김준호 (전북대학교 컴퓨터공학부) ;
  • 오일석 (전북대학교 컴퓨터공학부)
  • Received : 2009.11.10
  • Accepted : 2009.11.26
  • Published : 2010.03.28

Abstract

In this paper, we propose a new method of improving accuracy of motion estimation in mobile environments, compared with Rosten's algorithm. The present method selects corners as feature points. The Rosten's algorithm uses simple addition and subtraction to detect the corners. Although it has the advantage of faster processing speed, Rosten's algorithm has a drawback of low performance in motion estimation. We use the NCC(Normalized Cross Correlation) coefficients to match the corners, and remove in two steps the outliers of inaccurate matching corners. We compare the proposed algorithm with Rosten's algorithm by applying both to the real images. We find that the proposed method shows better performance than Rosten's algorithm in motion estimation. In addition, we implement the present method on mobile devices and confirm that it works in mobile environments in real time.

본 논문에서는 모바일 환경에서 모션을 추정하기 위하여 특징점을 코너로 선택하고, 기존 코너 검출 알고리즘인 Rosten 알고리즘 보다 모션 추정의 정확성을 높이는 방법을 제안한다. Rosten 알고리즘은 간단한 덧셈과 뺄셈만으로 코너를 검출함에 따라 처리 속도가 빠른 장점이 있지만, 코너를 매칭하면서 모션추정의 성능이 떨어지는 단점을 가지고 있다. 우리는 Normalized Cross Correlation(NCC) 계수를 사용하여 코너를 매칭하고, 두 단계에 걸쳐 부정확한 매칭에 의한 외톨이를 제거한다. 기존의 Rosten 알고리즘과 제안하는 알고리즘을 실제 영상에서 실험을 통하여 성능을 비교하고, 실제 모바일 장치의 응용 프로그램에 적용한다. 제안한 알고리즘이 Rosten 알고리즘 보다 더 정확한 모션을 추정해 냄을 실험 결과 확인하였고, 실제 모바일 환경에서도 실시간으로 동작함을 확인하였다.

Keywords

References

  1. S. Bucolo, M. Billinghurst, and D. Sickinger, "User Experiences with Mobile Phone Camera Game Interfaces," Proceedings of the 4th international conference on Mobile and ubiquitous multimedia, pp.87-94, 2005. https://doi.org/10.1145/1149488.1149503
  2. M. Hachet, J. Pouderoux, and P. Guitton, "A Camera-Based Interface for Interaction with Mobile Handheld Computers," Proceedings of the 2005 symposium on Interactive 3D graphics and games, pp.65-72, 2005. https://doi.org/10.1145/1053427.1053438
  3. https://www.icg.tugraz.at/~daniel/HistoryOfMobileAR/
  4. http://handheld.softpedia.com/get/Games/Arcade/Marble-Revolution-21182.shtml
  5. D. Wigdor and R. Balakrishnan, "TiltText: Using Tilt for Text Input to Mobile Phones," Proceedings of the 16th annual ACM symposium on User interface software and technology, pp.81-90, 2003. https://doi.org/10.1145/964696.964705
  6. S. A. Drab and N. M. Artner, "Motion Detection as Interaction Technique for Games & Applications on Mobile Devices," Proceedings of Workshop on Pervasive Mobile Interaction Devices (PERMID 2005), 2005.
  7. A. Haro, K. Mori, T. Capin, and S. Wilkinson, "Mobile Camera-based User Interaction," Proceedings of IEEE International Conference on Computer Vision Workshop on Human-Computer Interaction, pp.79-89, 2005.
  8. J. Wang, S. Zhai, and J. Canny, "Camera Phone Based Motion Sensing: Interaction Techniques, Applications and Performance Study," Proceedings of the 19th annual ACM symposium on User interface software and technology, pp.101-110, 2006. https://doi.org/10.1145/1166253.1166270
  9. J. Hannuksela, P. Sangi, and J. Heikkil, "Vision-based motion estimation for interaction with mobile devices," Computer Vision and Image Understanding, Vol.108, pp.188-195, 2007. https://doi.org/10.1016/j.cviu.2006.10.014
  10. M. W. Kim and I. S. Oh, "Estimation of Rapid-motion for Mobile Devices Using Temporal Coherence," Image and Vision Computing New Zealand, pp.1-6, 2008. https://doi.org/10.1109/IVCNZ.2008.4762091
  11. E. Rosten and T. Drummond, "Machine learning for high-speed corner detection," In European Conference on Computer Vision, pp.430-443, 2006. https://doi.org/10.1007/11744023_34
  12. M. Trajkovic and M. Hedley, "Fast Corner Detection," Image and Vision Computing, Vol.16, pp.75-87, 1998. https://doi.org/10.1016/S0262-8856(97)00056-5
  13. http://www.nintendo.co.kr/Wii/main.php