Journal of Mathematical Imaging and Vision

, Volume 32, Issue 3, pp 349–361 | Cite as

Processing Sparse Panoramic Images via Space Variant Operators

Article

Abstract

The use of omni-directional cameras has become increasingly popular in vision systems for video surveillance and autonomous robot navigation. However, to date most of the research relating to omni-directional cameras has focussed on the design of the camera or the way in which to project the omni-directional image to a panoramic view rather than the processing of such images after capture. Typically images obtained from omni-directional cameras are transformed to sparse panoramic images that are interpolated to obtain a complete panoramic view prior to low level image processing. This interpolation presents a significant computational overhead with respect to real-time vision.

We present an efficient design procedure for space variant feature extraction operators that can be applied to a sparse panoramic image and directly processes this sparse image. This paper highlights the reduction of the computational overheads of directly processing images arising from omni-directional cameras through efficient coding and storage, whilst retaining accuracy sufficient for application to real-time robot vision.

Keywords

Sparse images Space variant operators Omni-directional images 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Antoine, J., Vandergheynst, P.P.: Wavelets on the 2-sphere: A group-theoretical approach. Appl. Comput. Harmon. Anal. 7, 1–30 (1999) CrossRefMathSciNetGoogle Scholar
  2. 2.
    Argyros, A.A., Tsakiris, D.P., Groyer, C.: Biomimetic centering behavior (mobile robots with panoramic sensors). IEEE Robot. Autom. Mag. 11(4), 21–30 (2004) CrossRefGoogle Scholar
  3. 3.
    Baker, S., Nayar, S.: Single viewpoint catadioptric cameras. In: Vision: Sensors, Theory and Applications, Monographs in Computer Science Panoramic, pp. 39–72. Springer, New York (2001) Chap. 4 Google Scholar
  4. 4.
    Barreto, J.P., Araujo, H.: Direct least square fitting of paracatadioptric line images. In: Proc. IEEE Workshop on Omnidirectional Vision and Camera Networks (2003) Google Scholar
  5. 5.
    Barreto, J.P., Araujo, H.: Fitting conics to paracatadioptric projections of lines. Comput. Vis. Image Underst. 101(3), 151–165 (2006) CrossRefGoogle Scholar
  6. 6.
    Bazin, J.-C., Kweon, I., Demonceaux, C., Vasseur, P.: Rectangle extraction in catadioptric images. In: Proc. IEEE Int. Conf. on Computer Vision (ICCV), pp. 1–7 (2007) Google Scholar
  7. 7.
    Becker, E.B., Carey, G.F., Oden, J.T.: Finite Elements: An Introduction. Prentice Hall, New York (1981) MATHGoogle Scholar
  8. 8.
    Bradski, G.R., Pisarevsky, V.: Intel’s Computer Vision Library: applications in calibration, stereo segmentation, tracking, gesture, face and object recognition. In: Proceedings IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 796–797 (2000) Google Scholar
  9. 9.
    Briggs, A.J., Detweiler, C., Li, Y., Mullen, P., Scharstein, D.: Matching scale-space features in 1D panoramas. Comput. Vis. Image Underst. 103, 184–195 (2006) CrossRefGoogle Scholar
  10. 10.
    Briggs, A., Li, Y., Scharstein, D.: Feature matching across 1D panoramas. In: Proc. IEEE Workshop on Omnidirectional Vision and Camera Networks (2005) Google Scholar
  11. 11.
    Bulow, T.: Multiscale image processing on the sphere. In: Proc. of DAGM. LNCS, vol. 2449, pp. 609–617. Springer, Berlin (2002) Google Scholar
  12. 12.
    Cauchois, C., Brassart, E., Delahoche, L., Delhommelle, T.: Reconstruction with the calibrated SYCLOP sensor. In: Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2000), vol. 2, pp. 1493–1498 (2000) Google Scholar
  13. 13.
    Coleman, S.A., Scotney, B.W., Kerr, D.: Direct feature extraction on range image data. In: Proc. of Irish Machine Vision and Image Processing Conference, The Queen’s University, Belfast, August 2005 Google Scholar
  14. 14.
    Coleman, S.A., Scotney, B.W.: Autonomous operators for direct use on irregular image data. In: Proceeding of the 2005 International Conference on Image Analysis and Processing. LNCS, vol. 3617, pp. 296–303. Springer, Berlin (2005) Google Scholar
  15. 15.
    Cummins, M., Newman, P.: Probabilistic appearance based navigation and loop closing. In: ICRA 2007, Rome (2007) Google Scholar
  16. 16.
    Daniilidis, K., Makadia, A., Bulow, T.: Image processing in catadioptric planes: spatiotemporal derivatives and optical flow computation. In: Proc. IEEE Workshop on Omnidirectional Vision, pp. 3–10 (2002) Google Scholar
  17. 17.
    Demanet, L., Vandergheynst, P.P.: Directional wavelets on the sphere. Technical Report R-2001-2, Signal Processing Laboratory, Lausanne (2001) Google Scholar
  18. 18.
    Demonceaux, C., Vasseur, P.: Markov random fields for catadioptric image processing. Pattern Recogn. Lett. 27(16), 1957–1967 (2006) CrossRefGoogle Scholar
  19. 19.
    Fabrizio, J., Tarel, J., Benosman, R.: Calibration of panoramic catadioptric sensors made easier. In: IEEE Workshop on Omnidirectional Vision, pp. 45–52 (2002) Google Scholar
  20. 20.
    Gaspar, J., Winters, N., Santos-Victor, J.: Vision-based navigation and environmental representation with an omni-directional camera. IEEE Trans. Robot. Autom. 16(6), 890–898 (2000) CrossRefGoogle Scholar
  21. 21.
    Geyer, C., Daniilidis, K.: Catadioptric projective geometry. Int. J. Comput. Vis. 43(3), 223–243 (2001) CrossRefGoogle Scholar
  22. 22.
    Geyer, C., Daniilidis, K.: Paracatadioptric camera calibration. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 687–695 (2002) CrossRefGoogle Scholar
  23. 23.
    Ieng, S.-H., Benosman, R., Devars, J.: An efficient dynamic multi-angular feature points matcher for catadioptric views. In: Proc. IEEE Workshop on Omnidirectional Vision and Camera Networks (2003) Google Scholar
  24. 24.
    Kang, S.B.: Catadioptric self-calibration. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 201–207 (2000) Google Scholar
  25. 25.
    Krose, B., Bunschoten, R., Hagen, S.T., Terwijn, B., Vlassis, N.: Household robots look and learn: environment modeling and localization from an omnidirectional vision system. IEEE Robot. Autom. Mag. 11(4), 45–52 (2004) CrossRefGoogle Scholar
  26. 26.
    Matsumoto, Y., Ikeda, Y., Inaba, M., Inoue, H.: Visual navigation using omnidirectional view sequence. In: Proc. of IEEE Int. Conf. on Intelligent Robots and Systems, pp. 317–322 (1999) Google Scholar
  27. 27.
    Nayar, S.K.: Omnidirectional vision. In: Proc. 8th Int. Symp. Robotics Research, Japan (1997) Google Scholar
  28. 28.
    Peri, V., Nayar, S.K.: Generation of perspective and panoramic video from omnidirectional video. In: Proc. of 1997 DARPA Image Understanding Workshop, New Orleans (1997) Google Scholar
  29. 29.
    Ramponi, G., Carrato, S.: An adaptive irregular sampling algorithm and its application to image coding. Image Vis. Comput. 19, 451–460 (2001) CrossRefGoogle Scholar
  30. 30.
    Scotney, B.W., Coleman, S.A., Kerr, D.: A graph theoretic approach to direct processing of sparse unwarped panoramic images. In: Proceedings of IEEE Int. Conf. Image Processing, Atlanta, pp. 1557–1560 (2006) Google Scholar
  31. 31.
    Sorgi, L., Daniilidis, K.: Normalized cross-correlation for spherical images. In: Proc. of ECCV. LNCS, vol. 3022 pp. 542–553. Springer, Berlin (2004) Google Scholar
  32. 32.
    Stasinski, R., Konrad, J.: POCS-based image reconstruction from irregularly-spaced samples, In: Proceedings of IEEE International Conference on Image Processing, pp. 315–318 (2000) Google Scholar
  33. 33.
    Svoboda, T., Pajdla, T.: Matching in catadioptric images with appropriate windows, and outliers removal. In: Proc. of CAIP. LNCS, vol. 2124, pp. 733–740. Springer, Berlin (2001) Google Scholar
  34. 34.
    Svoboda, T., Pajdla, T., Hlavac, V.: Central panoramic cameras: Geometry and design. Research report, Czech Technical University-Center for Machine Perception, Praha, Czech Republic, December 1997 Google Scholar
  35. 35.
    Torii, A., Imiya, A.: Panoramic image transform of omnidirectional images using discrete geometry techniques. In: Second International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT’04), pp. 608–615 (2004) Google Scholar
  36. 36.
    Vandeportaele, B., Cattoen, M., Marthon, P.: A fast detector of line images acquired by an uncalibrated paracatadioptric camera. In: Proc. Int. Conf. on Pattern Recognition (ICPR), pp. 1042–1045 (2006) Google Scholar
  37. 37.
    Vasseur, P., Mouaddib, E.M.: Central catadioptric line detection, In: Proc. of the British Machine Vision Conference (2004) Google Scholar
  38. 38.
    Vazquz, C., Dubois, E., Konrad, J.: Reconstruction of irregularly-sampled images by regularization in spline spaces. In: Proceedings of IEEE International Conference on Image Processing, pp. 405–408 (2002) Google Scholar
  39. 39.
    Vazquz, C., Konrad, J., Dubois, E.: Wavelet-based reconstruction of irregularly-sampled images: application to stereo imaging. In: Proceedings of IEEE International Conference on Image Processing, pp. 319–322 (2000) Google Scholar
  40. 40.
    Vlassis, N., Motomura, Y., Hara, I., Asoh, H., Matsui, T.: Edge-based features from omnidirectional images for robot localization. In: Proc. IEEE ICRA, pp. 1579–1584 (2001) Google Scholar
  41. 41.
    Wei, S.-K., Urban, M., Pajdla, T.: Stereo matching of catadioptric panoramic images. Technical Report, CMP, August 2000 Google Scholar
  42. 42.
    Winters, N., Gaspar, J., Lacey, G., Santos-Victor, J.: Omni-directional vision for robot navigation. In: IEEE Workshop on Omnidirectional Vision, p. 21 (2000) Google Scholar
  43. 43.
    Yagi, Y., Hamada, H., Benson, N., Yachida, M.: Generation of stationary environmental map under unknown robot motion. In: Proc. 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems, vol. 2, pp. 1487–1492. Japan (2000) Google Scholar
  44. 44.
    Zhang, Z., Deriche, R., Faugeras, O., Luong, Q.-T.: A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry. Technical Report RR-2273, Inria, October 1995 Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  1. 1.School of Computing and Intelligent SystemsUniversity of UlsterLondonderryNorthern Ireland
  2. 2.School of Computing and Information EngineeringUniversity of UlsterColeraineNorthern Ireland

Personalised recommendations