Biologically inspired 3D scene depth recovery from stereo images

This paper proposes a biologically inspired method for depth recovery from stereo rectified images. Two principles are used in order to speed-up the image matching phase: the photoreceptor information transmission (spike generation) principle and convenient coding of neuron (pixel) neighbourhood data. This latter provides the robustness to match and reduces its calculation time. The proposed method has been validated via Julesz's random dot stereograms. Any autonomous vision-guided system such as autonomous robots, walkers, electronic travel aids, ETA (for elderly, visually impaired, blind, etc.) can take benefit from the proposed depth recovery method: a new ETA, named intelligent glasses (IGI, for visually impaired assistance in their secure and independent displacements in non-cooperating environment, which will integrate the proposed method, is presented as well. The IG system is under design at the Robotics Laboratory of Paris (LRP), University Paris 6, and National Nuclear Testing Commission (CEA).

[1]  Jens Månsson,et al.  Stereovision: a model of human stereopsis , 1998 .

[2]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[3]  G. DeAngelis.  Seeing in three dimensions: the neurophysiology of stereopsis , 2000, Trends in Cognitive Sciences.

[4]  Carlo Tomasi,et al.  Depth Discontinuities by Pixel-to-Pixel Stereo , 1999, International Journal of Computer Vision.

[5]  Changming Sun,et al.  Fast Stereo Matching Using Rectangular Subregioning and 3D Maximum-Surface Techniques , 2002, International Journal of Computer Vision.

[6]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[7]  W. Eric L. Grimson,et al.  Computational Experiments with a Feature Based Stereo Algorithm , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[9]  Edwige Pissaloux,et al.  A parallel algorithm for a very fast 2D velocity field estimation , 1997, Proceedings of International Conference on Image Processing.

[10]  Oliver. Faugeras,et al.  Real time correlation based stereo algorithm and application , 1993 .

[11]  Malek Adjouadi,et al.  A similarity measure for stereo feature matching , 1997, IEEE Trans. Image Process..

[12]  Stephen M. Smith,et al.  SUSAN—A New Approach to Low Level Image Processing , 1997, International Journal of Computer Vision.

[13]  B. Julesz.  Binocular depth perception of computer-generated patterns , 1960 .

[14]  Takeo Kanade,et al.  Development of a video-rate stereo machine , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[15]  Carlo Tomasi,et al.  Depth Discontinuities by Pixel-to-Pixel Stereo , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).