International Journal of Control, Automation, and Systems

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

An Omnidirectional Vision-Based Moving Obstacle Detection in Mobile Robot

  • Kim, Jong-Cheol (Robot Business Department, KT) ;
  • Suga, Yasuo (Department of Mechanical Engineering, Faculty of Science and Technology, Keio University)
  • Published : 2007.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a new moving obstacle detection method using an optical flow in mobile robot with an omnidirectional camera. Because an omnidirectional camera consists of a nonlinear mirror and CCD camera, the optical flow pattern in omnidirectional image is different from the pattern in perspective camera. The geometry characteristic of an omnidirectional camera has influence on the optical flow in omnidirectional image. When a mobile robot with an omnidirectional camera moves, the optical flow is not only theoretically calculated in omnidirectional image, but also investigated in omnidirectional and panoramic images. In this paper, the panoramic image is generalized from an omnidirectional image using the geometry of an omnidirectional camera. In particular, Focus of expansion (FOE) and focus of contraction (FOC) vectors are defined from the estimated optical flow in omnidirectional and panoramic images. FOE and FOC vectors are used as reference vectors for the relative evaluation of optical flow. The moving obstacle is turned out through the relative evaluation of optical flows. The proposed algorithm is tested in four motions of a mobile robot including straight forward, left turn, right turn and rotation. The effectiveness of the proposed method is shown by the experimental results.

Keywords

References

  1. K. Yamazawa, Y. Yagi, and M. Yachida, 'Omnidirectional imaging with hyperboloidal projection,' Proc. of IEEE Int. Conf. on Intelligent Robots and Systems, vol. 2, pp. 1029-1034, July 1993
  2. Y. Yagi, 'Omnidirectional sensing and its application,' IEICE Trans. Information and Systems, vol. E82-D, no. 3, pp. 568-579, 1999
  3. J. Wolf, W. Burgard, and H. Burkhardt, 'Robust vision-based localization by combining an image-retrieval system with Monte Carlo localization,' IEEE Trans. on Robotcis, vol. 21, no. 2, pp. 208-216, 2005 https://doi.org/10.1109/TRO.2004.835453
  4. S. Baker and S. Nayar, 'A theory of singleviewpoint cata-viewpoint datadioptric image formation,' International Journal of Computer Vision, vol. 35, no. 2, pp. 1-22, 1999
  5. K. Daniilidis and C. Geyer, 'Omnidirectional vision: Theory and algorithms,' Proc. of Int. Conf. on Pattern Recognition, vol. 1, pp. 89-96, September 2000
  6. J. Gluckman and S. K. Nayer, 'Ego-motion and omnidirectional camera,' Proc. of Int. Conf. Computer Vision, pp. 999-1005, January 1998
  7. O. Shakernia, R. Vidal, and S. Sastry, 'Infinitesimal motion estimation from multiple central panoramic views,' Proc. of IEEE Workshop on Motion and Video Computing, pp. 229-234, December 2002
  8. R. Vassallo, J. Santos-Victor, and J. Schneebeli, 'A general approach for egomotion estimation with omnidirectional images,' Proc. of IEEE Workshop on Omnidirectional Vision, pp. 97-103, June 2002
  9. J. W. Lee, S. You, and U. Neumann, 'Large motion estimation for omnidirectional vision,' Proc. IEEE Workshop on Omnidirectional Vision, pp. 161-168, June 2000
  10. J. Kim, M. Muramatsu, U. Murata, and Y. Suga, 'Omnidirectional vision-based ego-pose estimation for an autonomus in-pipe mobile robot,' Advanced Robotics, vol. 21. no. 3-4, pp. 441-460, 2007 https://doi.org/10.1163/156855307780132027
  11. T. Gandhi and M. Trivedi, 'Motion based vehicle surround analysis using an omnidirectional camera,' Proc. of IEEE Intelligent Vehicles Symposium, pp. 560-565, June 2004
  12. R. Runschotem and B. Krose, 'Robust scene reconstruction from an omnidirectional vision system,' IEEE Trans. on Robotics and Automation, vol. 19, no. 2, pp. 351-357, 2003 https://doi.org/10.1109/TRA.2003.808850
  13. C. Drocourt, L. Delahoche, C. Pegard, and A. Clerentin, 'Mobile robot localization based on an omnidirectional stereoscopic vision perception system,' Proc. of Int. Conf. on Robotics and Automation, pp. 1329-1334, May 1999
  14. E. Menegatti, A. Pretto, and E. Pagello, 'A new omnidirectional vision sensor for Monte-Carlo localization,' Proc. of Int. RoboCup Symposium, LNAI, vol. 3276, pp. 97-109, 2005
  15. H. Koyasu, J. Miura, and Y. Shirai, 'Mobile robot navigation in dynamic environments using omnidirectional stereo,' Proc. of Int. Conf. on Robotics and Automation, vol. 1, pp. 893-898, Sep., 2003
  16. Y. Yagi, K. Imai, K. Tsuji, and M. Yachida, 'Iconic memory-based omnidirectional route panorama navigation,' IEEE Trans. on Pattern Analsis and Machine Intelligence, vol. 27. no. 1, pp. 78-87, 2005 https://doi.org/10.1109/TPAMI.2005.11
  17. N. Winters, J. Gaspar, G. Lacey, and J. Santos-Victor, 'Omni-directional vision for robot navigation,' Proc. of IEEE Workshop on Omnidirectional Vision, pp. 21-28, June 2000
  18. R. Nelson and Y. Aloimonous, 'Obstacle avoidance using flow field eivergence,' IEEE Trans. on Pattern Analsis and Machine Intelligence, vol. 11, no. 10, pp. 1102-1106, 1989 https://doi.org/10.1109/34.42840
  19. R. Sharma and J. Aloimonos, 'Early detection of independent motion from active control of normal image flow pattern,' IEEE Trans. on Systems, Man, and Cybanetics, vol. 26, no. 1, pp. 42-52, 1996
  20. S. Fejes and L. S. Davis, 'What can projections of flow fields tell us about the visual motion,' Proc. of Int. Conf. Computer Vision, pp. 979-986, 1998
  21. M. I. A. Lourakis, A. A. Argyros, and S. C. Orphanoudakis, 'Independent 3D motion detection using residual parallax normal flow fields,' Proc. of Int. Conf. Computer Vision, pp. 1012-1017, 1998
  22. M. Watanabae, N. Takeda, and K. Onoguchi, 'Moving obstacle detection and recognition by optical flow pattern analysis for mobile robots,' Advanced Robotics, vol. 12, no. 8, pp. 791-816, 1999 https://doi.org/10.1163/156855399X00144
  23. H. S. Sawhney and Y. G. R. Kumar, 'Independent motion detection in 3D scene,' Proc. of Int. Conf. Computer Vision, pp. 612-619, 1999
  24. Z. Hu and K. Uchimura, 'Motion detection from a moving observer using pure feature matching,' Int. Jour. Robotics and Automation, vol. 15, no. 1, pp. 21-26, 2000
  25. A. Talukder, S. Goldberg, L. Matthies, and A. Ansar, 'Real-time detection of moving objects in a dynamic sene from moving robotic vehicles,' Proc. of Int. Conf. Intelligent Robotics and systems, pp. 1308-1313, 2003
  26. I. Stratmann and E. Solda, 'Omnidirectional vision and inertial clues for robot navigation,' Journal of Robotic Systems, vol. 21, no. 1, pp. 33-39, 2004 https://doi.org/10.1002/rob.10126
  27. K. Yamazawa, Y. Yagi, and M. Yachida, 'Obstacle detection with omnidirectional image sensor hyperomni vision,' Proc. of International Conference on Robotics and Automation, pp. 1062-1067, 1995
  28. B. D. Lucas and T. Kanade, 'An iterative image registration technique with an application to stereo vision,' Proc. of the 7th International Joint Conference on Artificial Intelligence, pp. 674-679, April 1981