Advertisement

Subtraction-Based Forward Obstacle Detection Using Illumination Insensitive Feature for Driving-Support

  • Haruya Kyutoku
  • Daisuke Deguchi
  • Tomokazu Takahashi
  • Yoshito Mekada
  • Ichiro Ide
  • Hiroshi Murase
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7584)

Abstract

This paper proposes a method for detecting general obstacles on a road by subtracting present and past in-vehicle camera images. The image-subtraction-based object detection approach can be applied to detect any kind of obstacles although the existing learning-based methods detect only specific obstacles. To detect general obstacles, the proposed method first computes a frame-by-frame correspondence between the present and the past in-vehicle camera image sequences, and then registrates road surfaces between the frames. Finally, obstacles are detected by applying image subtraction to the registrated road surface regions with an illumination insensitive feature for robust detection. Experiments were conducted by using several image sequences captured by an actual in-vehicle camera to confirm the effectiveness of the proposed method. The experimental results shows that the proposed method can detect general obstacles accurately at a distance enough to avoid them safely even in situations with different illuminations.

Keywords

Road Surface Illumination Condition Dynamic Time Warping Stereo Match Obstacle Detection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    Kyutoku, H., Deguchi, D., Takahashi, T., Mekada, Y., Ide, I., Murase, H.: On-road obstacle detection by comparing present and past in-vehicle camera images. In: Proc. 12th IAPR Conf. on Machine Vision Applications, pp. 357–360 (2011)Google Scholar
  2. 2.
    Liu, F., Sparbert, J., Stiller, C.: IMMPDA vehicle tracking system using asynchronous sensor fusion of radar and vision. In: Proc. 2008 IEEE Intelligent Vehicles Symposium, pp. 168–173 (2008)Google Scholar
  3. 3.
    Nishida, K., Kurita, T.: Boosting with cross-validation based feature selection for pedestrian detection. In: Proc. 2008 IEEE World Congress on Computational Intelligence, pp. 1251–1257 (2008)Google Scholar
  4. 4.
    Mitsui, T., Fujiyoshi, H.: Object detection by joint features based on two-stage boosting. In: Proc. 9th IEEE Int. Workshop on Visual Surveillance 2009, pp. 1169–1176 (2009)Google Scholar
  5. 5.
    Collado, J.M., Hilario, C., de la Escalera, A., Armingol, J.M.: Self-calibration of an on-board stereo-vision system for driver assistance systems. In: Proc. 2006 IEEE Intelligent Vehicles Symposium, pp. 156–162 (2006)Google Scholar
  6. 6.
    Kawanishi, Y., Mitsugami, I., Mukunoki, M., Minoh, M.: Background image generation by preserving lighting condition of outdoor scenes. Procedia—Social and Behavioral Sciences 2, 129–136 (2010)CrossRefGoogle Scholar
  7. 7.
    Sato, J., Takahashi, T., Ide, I., Murase, H.: Change detection in streetscapes from GPS coordinated omni-directional image sequences. In: Proc. 18th IAPR Int. Conf. on Pattern Recognition, vol. 4, pp. 935–938 (2006)Google Scholar
  8. 8.
    Boehm, J.: Multi-image fusion for occlusion-free facade texturing. Int. Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences 35, 867–872 (2004)Google Scholar
  9. 9.
    Uchiyama, H., Deguchi, D., Takahashi, T., Ide, I., Murase, H.: Removal of moving objects from a street-view image by fusing multiple image sequences. In: Proc. 20th IAPR Int. Conf. on Pattern Recognition, pp. 3456–3459 (2010)Google Scholar
  10. 10.
    Zabih, R., Woodfill, J.: Non-parametric Local Transforms for Computing Visual Correspondence. In: Eklundh, J.-O. (ed.) ECCV 1994, Part II. LNCS, vol. 801, pp. 151–158. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  11. 11.
    Ojala, T., Pietikainen, M., Harwood, D.: A comparative study of texture measures with classifcation based on featured distributions. Int. Journal on Computer Vision 29, 51–59 (1996)Google Scholar
  12. 12.
    Hirschmuller, H., Scharstein, D.: Evaluation of stereo matching costs on images with radiometric differences. IEEE Trans. on Pattern Analysis and Machine Intelligence 31, 1582–1599 (2009)CrossRefGoogle Scholar
  13. 13.
    Tan, X., Triggs, B.: Enhanced local texture feature sets for face recognition under difficult lighting conditions. IEEE Trans. on Image Processing 19, 1635–1650 (2010)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Haruya Kyutoku
    • 1
  • Daisuke Deguchi
    • 2
  • Tomokazu Takahashi
    • 3
  • Yoshito Mekada
    • 4
  • Ichiro Ide
    • 1
  • Hiroshi Murase
    • 1
  1. 1.Graduate School of Information ScienceNagoya UniversityNagoyaJapan
  2. 2.Information and Communications HeadquartersNagoya UniversityNagoyaJapan
  3. 3.Faculty of Economics and InformationGifu Shotoku Gakuen UniversityGifuJapan
  4. 4.School of Information Science and TechnologyChukyo UniversityToyotaJapan

Personalised recommendations