TOWARDS REAL-TIME NEURONAL DISPARITY MAP ESTIMATION

Nadia Baha, Slimane Larabi

2010

Abstract

We propose in this paper a new approach for fast disparity map estimation from pair of stereo images. The disparity map computing is divided into two main steps. The first one deals with computing the initial disparity map using a neuronal DSI (Disparity Space Image) method. Whereas, the second one is a simple and fast method to refine the initial disparity map. New strategies and improvements are introduced so an accurate and fast result can be acquired. In order to reduce the computing time, we implemented some steps of the proposed algorithm on FPGA. Experimental results on real data sets were conducted for evaluating the solutions proposed and comparative evaluation of our method with two others methods is presented.

References

  1. Alvarez, L., Deriche, R., Sanchez, J., Weickert, J., (2002). Dense disparity map estimation respecting image discontinuities: a PDE and scalespace based approach.. J. of Visual Commun. Image Represent 13, 3-21.
  2. Baha, N., Larabi, S., (2008). Obstacle Detection from Uncalibrated Cameras. In Proc of PCI'2008, Greece, pp. 152-157.
  3. Binaghi,, E., Gallo,I., Fornasier, C., Raspanti, M., (2006). Growing aggregation algorithm for dense two-frame stereo correspondence. In 1st Int.Conf. on Computer Vision Theory and Application, 326-332.
  4. Binaghi,, E., Gallo,I., Fornasier, C., Raspanti, M., (2004). Neural adaptative stereo matching. Pattern Recognition Letters25,1743-1758.
  5. Bobik,A., Intille,S., (1999). Large occlusion stereo. Intern. Journal on computer vision 33, 181-200.
  6. Di Stefano, L., Marchionni, M., Mattoccia,S., (2004). A fast area-based stereo matching algorithm. Image and vision computing, 22(12), 983-1005.
  7. Goulermas,J., Liatsis,P., (2001). Hybrid symbiotic genetic optimisation for robust edge-based stereo correspondence. Pattern Recognition. 34, 2477-2496.
  8. Gutierrez, S., Marroquin,J., (2004). Robust approach for disparity estimation in stereo vision. Image and Vision Computing, 83-195.
  9. Kumar, S., Chatterji, B., (2002). Stereo matching algorithms based on fuzzy approach. Int. Journal in Pattern Recognit. Artif. Intell. 16,7, 883-899.
  10. Maas, R.,Haar Romeny, B., Viergever, M., (1999). Areabased computation of stereo disparity with model based window size selection. Computer Vision and Pattern Recognition (CVPR), 106-112.
  11. Miled, W.and Pesquet, J., (2006). Dense Disparity estimation from stereo images. Int. Symposium on Image/Video Communication.
  12. Nalpantidis, L., Sirakoulis, G.,and Gasteratos, A., (2008). Review of stereo vision algorithms: from Software to Hardware. International Journal of Optomechatronics, 2:435-462, 2008
  13. Ogale, A., Aloimonos, Y., (2005). Shape and the stereo Correspondence Problem. Int. Journal of Computer Vision, 65,3,147-1758.
  14. Scharstein, D., Szeliski,R., (2002). A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. Int. Journal on Computer Vision, 47,7-42.
  15. Veksler, O., (2003). Extracting dense features for visual correspondence with graph cuts. Proc. Of the IEEE Computer Society Conference on Computer Vision and pattern Recognition.
  16. Yoon,K., Kweon,I., (2006). Adaptive Support Weight Approach for Correspondence Search. IEEE Tran. On Pattern Analysis and Machine Intelligence, vol. 28.
Download


Paper Citation


in Harvard Style

Baha N. and Larabi S. (2010). TOWARDS REAL-TIME NEURONAL DISPARITY MAP ESTIMATION . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010) ISBN 978-989-674-028-3, pages 355-360. DOI: 10.5220/0002833803550360


in Bibtex Style

@conference{visapp10,
author={Nadia Baha and Slimane Larabi},
title={TOWARDS REAL-TIME NEURONAL DISPARITY MAP ESTIMATION},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)},
year={2010},
pages={355-360},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002833803550360},
isbn={978-989-674-028-3},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2010)
TI - TOWARDS REAL-TIME NEURONAL DISPARITY MAP ESTIMATION
SN - 978-989-674-028-3
AU - Baha N.
AU - Larabi S.
PY - 2010
SP - 355
EP - 360
DO - 10.5220/0002833803550360