Attenuating stereo pixel-locking via affine window adaptation

For real-time stereo vision systems, the standard method for estimating sub-pixel stereo disparity given an initial integer disparity map involves fitting parabolas to a matching cost function aggregated over rectangular windows. This results in a phenomenon known as pixel-locking, which produces artificially-peaked histograms of sub-pixel disparity. These peaks correspond to the introduction of erroneous ripples or waves in the 3D reconstruction of truly flat surfaces. Since stereo vision is a common input modality for autonomous vehicles, these inaccuracies can pose a problem for safe, reliable navigation. This paper proposes a new method for sub-pixel stereo disparity estimation, based on ideas from Lucas-Kanade tracking and optical flow, which substantially reduces the pixel-locking effect. In addition, it has the ability to correct much larger initial disparity errors than previous approaches and is more general as it applies not only to the ground plane. We demonstrate the method on synthetic imagery as well as real stereo data from an autonomous outdoor vehicle

[1]  Larry H. Matthies,et al.  Error analysis of a real-time stereo system , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[3]  Roberto Manduchi,et al.  Bilateral filtering for gray and color images , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[4]  Yiannis Aloimonos,et al.  Stereo correspondence with slanted surfaces: critical implications of horizontal slant , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[5]  Simon Baker,et al.  Lucas-Kanade 20 Years On: A Unifying Framework , 2004, International Journal of Computer Vision.

[6]  Robert Mandelbaum,et al.  Real-time stereo processing, obstacle detection, and terrain estimation from vehicle-mounted stereo cameras , 1998, Proceedings Fourth IEEE Workshop on Applications of Computer Vision. WACV'98 (Cat. No.98EX201).

[7]  Richard Szeliski,et al.  Symmetric Sub-Pixel Stereo Matching , 2002, ECCV.

[8]  T. Williamson.  A high-performance stereo vision system for obstacle detection , 1998 .

[9]  Jonathan M. Garibaldi,et al.  Real-Time Correlation-Based Stereo Vision with Reduced Border Errors , 2002, International Journal of Computer Vision.

[10]  G. Salgian,et al.  Electronically directed "focal" stereo , 1995, Proceedings of IEEE International Conference on Computer Vision.

[11]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Olivier D. Faugeras,et al.  Computing differential properties of 3-D shapes from stereoscopic images without 3-D models , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Larry H. Matthies,et al.  Enhanced real-time stereo using bilateral filtering , 2004, Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004..

[14]  Carlo Tomasi,et al.  Surfaces with occlusions from layered stereo , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Masatoshi Okutomi,et al.  Precise subpixel estimation on area-based matching , 2002, Syst. Comput. Jpn..

[16]  Alan L. Yuille,et al.  Occlusions and binocular stereo , 1992, International Journal of Computer Vision.

[17]  Gregory D. Hager,et al.  Real-time tracking of image regions with changes in geometry and illumination , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Emanuele Trucco,et al.  Efficient stereo with multiple windowing , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.