Using pano-mapping tables for unwarping of omni-images into panoramic and perspective-view images

Buy article PDF

Abstract

A unified approach to unwarping of omni-images into panoramic or perspective-view images is proposed. The approach does not adopt the conventional technique of calibrating the related parameters of an omni-camera. Instead, it is based on a new concept of a pano-mapping table, which is created once forever, by a simple learning process for an omni-camera of any kind, as a summary of the information conveyed by all the camera parameters. The learning process takes, as input, a set of landmark point pairs, in the world space and in a given image. With the help of the pano-mapping table, any panoramic or perspective-view image can be created from an input omni-image taken by the omni-camera, according to an analytic computation process proposed in the paper. Experimental results show the feasibility of the proposed approach.

References

    1. 1)
    2. 2)
      • Morita, S., Yamazawa, K., Yokoya, N.: `Networked video surveillance using multiple omnidirectional cameras', Proc., IEEE Int. Symp. Comput. Intell. Robot. Autom., Kobe, 16–20 July 2003, Japan, p. 1245–1250
    3. 3)
      • Tang, L., Yuta, S.: `Indoor navigation for mobile robots using memorized omni-directional images and robot's motion', Proc. IEEE/RSJ Int. Conf. Intell. Robots Syst., 30 September–5 October 2002, 1, p. 269–274
    4. 4)
      • Winter, N., Gaspar, J., Lacey, G., Santos-Victor, J.: `Omnidirectional vision for robot navigation', Proc. IEEE Workshop Omnidirectional Vision, OMNIVIS, June 2000, South Carolina, USA, p. 21–28
    5. 5)
    6. 6)
      • Nayar, S.K.: `Catadioptric omni-directional camera', Proc. IEEE Conf. Comput. Vis. Pattern Recognit., June 1997, San Juan, Puerto Rico, p. 482–488
    7. 7)
      • Onoe, Y., Yokoya, N., Yamazawa, K., Takemura, H.: `Visual surveillance and monitoring system using an omni-directional video camera', Proc. 14th Int. Conf. Pattern Recognit., 16–20 August 1998, 1, Brisbane, Australia, p. 588–592
    8. 8)
      • Jeng, S.W., Tsai, W.H.: `Precise image unwarping of omni-directional cameras with hyperbolic-shaped mirrors', Proc. 16th IPPR Conf. Comput. Vis., Graphics Image Process., Kinmen, Taiwan, 17–19 August 2003, p. 414–422
    9. 9)
      • Jeng, S.W., Tsai, W.H.: `Construction of perspective and panoramic images from omni-images taken from hypercatadioptric cameras for visual surveillance', Proc. 2004 IEEE Int. Conf. on Netw. Sensing, Control, Taipei, Taiwan, 21–23 March 2004, p. 204–209
    10. 10)
    11. 11)
      • Mundhenk, T.N., Rivett, M.J., Liao, X., Hall, E.L.: `Techniques for fisheye lens calibration using a minimal number of measurements', Proc. SPIE Intell. Robot. Comput. Vis. Conf. XIX, 2000, Boston, MA
    12. 12)
    13. 13)
      • Geyer, C., Daniilidis, K.: `Catadioptric camera calibration', Proc. IEEE 7th Int. Conf. Comput. Vis., September 1999, p. 398–404
    14. 14)
    15. 15)
      • Strelow, D., Mishler, J., Koes, D., Singh, S.: `Precise omnidirectional camera calibration,', Proc. IEEE Conf. Comput. Vis. Pattern Recognit., December 2001, 1, p. 689–694, (CVPR 2001) Kauai, HI
    16. 16)
      • Scaramuzza, D., Martinelli, A., Siegwart, R.: `A flexible technique for accurate omnidirectional camera calibration and structure from motion', Proc. Fourth IEEE Int. Conf. Comput. Vis. Syst., 2006
    17. 17)
      • Burden, R.L., Faires, J.D.: Numerical analysis, 1993 (PWS PublishingBoston)
    18. 18)
    19. 19)
      • Kerbyson, D.J., Atherton, T.J.: `Circle detection using Hough transform filters', Fifth Int. Conf. Image Process. Appl., 4–6 July 1995, Edinburgh, UK, p. 370–374
    20. 20)
      • Chen, X., Tang, J.: `Towards monitoring human activities using an omnidirectional camera', Int. Conf. Multimodal Interfaces, Pittsburgh, 2002, p. 423–428
This is a required field
Please enter a valid email address