Journal of Mathematical Imaging and Vision

, Volume 38, Issue 2, pp 119–131 | Cite as

A Space Variant Gradient Based Corner Detector for Sparse Omnidirectional Images



Omnidirectional cameras are useful in applications requiring rapid capture of image data representing the complete local environment. Feature detection from such image data is thus a prominent research issue. Transforming an omnidirectional image to a panoramic image may result in a sparse panoramic image with missing image data. Whilst image reconstruction techniques have been developed that enable the subsequent use of standard image processing algorithms, the development of image processing algorithms that can be applied directly to sparse image data has received less attention. We address the problem of corner point detection for sparse panoramic images by developing an algorithmic approach that can be applied directly to sparse unwarped omnidirectional images without the requirement of image reconstruction, and we illustrate the accurate performance of the algorithm through visual results and receiver operating characteristic curves.


Image features Corner detection Incomplete data 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Andreasson, H., Duckett, T.: Topological localization for mobile robots using omni-directional vision and local features. In: Proc. of the 5th Symposium on Intelligent Autonomous Vehicles (IAV2004), Lisbon, Portugal (2004) Google Scholar
  2. 2.
    Argyros, A., Bekris, K., Orphanoudakis, S.: Robot homing based on corner tracking in a sequence of panoramic images. In: Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2001), vol. 2, pp. 3–10 (2001) Google Scholar
  3. 3.
    Arnau Ramisa David Aldavert, R.T.: A panorama based localization system. In: 1st CVC Internal Workshop (CVCRD06), Computer Vision: Progress of Research and Development, pp. 36–41. Bellaterra, Spain (2006) Google Scholar
  4. 4.
    Atwood, G., Davis, W.: Image expansion using interpolation and heuristic edge following. In: Proc. of the Third International Conference on Image Processing and its Applications, pp. 664–668 (1989) Google Scholar
  5. 5.
    Baker, S., Nayar, S.: Single Viewpoint Catadioptric Cameras. In: Benosman, R., Kang, S.B. (eds.) Panoramic Vision: Sensors, Theory and Applications, pp. 39–72. Springer, New York (2001) Google Scholar
  6. 6.
    Bay, H., Tuytelaars, T., Van Gool, L.: Surf: Speeded up robust features. In: European Conference on Computer Vision, vol. 1, pp. 404–417 (2006) Google Scholar
  7. 7.
    Gaspar, J., Winters, N., Santos-Victor, J.: Vision-based navigation and environmental representations with an omnidirectional camera. IEEE Trans. Robot. Autom. 16(6), 890–898 (2000) CrossRefGoogle Scholar
  8. 8.
    Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, vol. 15, pp. 147–151 (1988) Google Scholar
  9. 9.
    Jain, A.: Fundamentals of Digital Image Processing. Prentice-Hall, Upper Saddle River (1989) MATHGoogle Scholar
  10. 10.
    Jeng, S., Tsai, W.: Construction of perspective and panoramic images from omni-images taken from hypercatadioptric cameras for visual surveillance. In: Proc. of the IEEE International Conference on Networking, Sensing and Control (ICNSC ’04), vol. 1, pp. 204–209 (2004) Google Scholar
  11. 11.
    Jeng, S., Tsai, W.: Improving quality of unwarped omni-images with irregularly-distributed unfilled pixels by a new edge-preserving interpolation technique. Pattern Recogn. Lett. 28(15), 1926–1936 (2007) CrossRefGoogle Scholar
  12. 12.
    Knutsson, H., Westin, C.: Normalized and differential convolution. In: Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 515–523 (1993) Google Scholar
  13. 13.
    Krose, B., Bunschoten, R., Hagen, S., 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
  14. 14.
    Li, J., Allinson, N.: A comprehensive review of current local features for computer vision. Tech. rep., University of Sheffield (2007) Google Scholar
  15. 15.
    Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004) CrossRefGoogle Scholar
  16. 16.
    Mashita, T., Iwai, Y., Yachida, M.: Calibration method for misaligned catadioptric camera. IEICE Trans. Inf. Syst. 89(7), 1984–1993 (2006) Google Scholar
  17. 17.
    Matsumoto, Y., Ikeda, K., Inaba, M., Inoue, H.: Visual navigation using omnidirectional view sequence. In: Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS ’99), vol. 1, pp. 317–322 (1999) Google Scholar
  18. 18.
    Mikolajczyk, K., Schmid, C.: Scale & affine invariant interest point detectors. Int. J. Comput. Vis. 60(1), 63–86 (2004) CrossRefGoogle Scholar
  19. 19.
    Mikolajczyk, K., Tuytelaars, T., Schmid, C., Zisserman, A., Matas, J., Schaffalitzky, F., Kadir, T., Gool, L.: A comparison of affine region detectors. Int. J. Comput. Vis. 65(1), 43–72 (2005) CrossRefGoogle Scholar
  20. 20.
    Moravec, H.: Towards automatic visual obstacle avoidance. In: Proc. of the 5th International Joint Conference on Artificial Intelligence (IJCAI77), vol. 584 (1977) Google Scholar
  21. 21.
    Murillo, A., Guerrero, J., Sagues, C.: Surf features for efficient robot localization with omnidirectional images. In: Proc. of the IEEE International Conference on Robotics & Automation (ICRA07), pp. 3901–3907 (2007) Google Scholar
  22. 22.
    Onoe, Y., Yokoya, N., Yamazawa, K., Takemura, H.: Visual surveillance and monitoring system using an omnidirectional video camera. In: Proc. of the Fourteenth International Conference on Pattern Recognition (ICPR98), vol. 1, pp. 588–592 (1998) Google Scholar
  23. 23.
    Peri, V., Nayar, S.: Generation of perspective and panoramic video from omnidirectional video. In: Proc. of the DARPA Image Understanding Workshop, pp. 243–246 (1997) Google Scholar
  24. 24.
    Pham, T., van Vliet, L.: Normalized averaging using adaptive applicability functions with applications in image reconstruction from sparsely and randomly sampled data. Lect. Not. Comput. Sci. 2749, 485–492 (2003) CrossRefGoogle Scholar
  25. 25.
    Piroddi, R., Petrou, M.: Dealing with irregular samples. Adv. Imaging Electron Phys. 132, 109–165 (2004) Google Scholar
  26. 26.
    Pratt, W.K.: Digital Image Processing. Wiley, New York (1978) Google Scholar
  27. 27.
    Rockett, P.: Performance assessment of feature detection algorithms: a methodology and case study on corner detectors. IEEE Trans. Image Process. 12(12), 1668–1676 (2003) CrossRefGoogle Scholar
  28. 28.
    Schmid, C., Mohr, R., Bauckhage, C.: Comparing and evaluating interest points. In: International Conference on Computer Vision (ICCV98), pp. 230–235 (1998) Google Scholar
  29. 29.
    Shewchuk, J.: Triangle: engineering a 2D quality mesh generator and Delaunay triangulator. Lect. Not. Comput. Sci. 1148, 203–222 (1996) CrossRefGoogle Scholar
  30. 30.
    Shi, J., Tomasi, C.: Good features to track. In: Proc. of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’94), pp. 593–600 (1994) Google Scholar
  31. 31.
    Svoboda, T., Pajdla, T.: Matching in catadioptric images with appropriate windows, and outliers removal. Lect. Not. Comput. Sci. 2124, 733–740 (2001) CrossRefGoogle Scholar
  32. 32.
    Swaminathan, R., Grossberg, M., Nayar, S.: A perspective on distortions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’03), vol. 2, pp. 594–601 (2003). doi: 10.1109/CVPR.2003.1211521
  33. 33.
    Vlassis, N., Motomura, Y., Hara, I., Asoh, H., Matsui, T.: Edge-based features from omnidirectional images for robot localization. In: Proc. of the IEEE International Conference on Robotics and Automation (ICRA’01), vol. 2, pp. 1579–1584 (2001) Google Scholar
  34. 34.
    Yagi, Y., Hamada, H., Benson, N., Yachida, M.: Generation of stationary environmental map under unknown robot motion. In: Proc. of the IEEE/RSJ International Conference on Intelligent Robots and Systems, vol. 2 (2000) Google Scholar
  35. 35.
    Ying, X., Hu, Z.: Catadioptric camera calibration using geometric invariants. IEEE Trans. Pattern Anal. Mach. Intel. 26(10), 1260–1271 (2004) CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

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