Reference Plane based Fisheye Stereo Epipolar Rectification

Nobuyuki Kita, Yasuyo Kita

2017

Abstract

When a humanoid robot walks through or performs a task in a very narrow space, it sometimes touches the environment with its hand or arm to retain its balance. To do this the robot must identify a flat surface of appropriate size with which it can make sufficient contact; the surface must also be within reach of robot's upper body. Using fisheye stereo vision, it is possible to obtain image information for a field of view wider than that of a hemisphere whose central axis is the optical axes; thus, three dimensional distances to the possible contact spaces can be evaluated at a glance. To realize it, stereo correspondence is crucial. However, the short distance between the stereo cameras and the target space causes differences in the apparent shapes of the targets in the left and right images, which can make stereo correspondence difficult. Therefore, we propose a novel method which rectifies stereo images so that the targets have the same apparent shapes in the left and right images when the targets are close to a reference plane. Actual fisheye stereo image pairs were rectified, and three dimensional measurements were performed. Better results were obtained using the proposed rectification method than using other rectification methods.

References

  1. Sentis, L., 2010. Compliant control of whole-body multicontact behaviors in humanoid robots. Motion Planning for Humanoid Robots, Springer: 29-66.
  2. Escande, A., A. Kheddar, et al., 2013. Planning contact points for humanoid robots. Robotics and Autonomous Systems 61(5): 428-442.
  3. Henze, B., M. A. Roa, et al., 2016. Passivity-based wholebody balancing for torque-controlled humanoid robots in multi-contact scenarios. The International Journal of Robotics Research: 0278364916653815.
  4. Brossette, S., J. Vaillant, et al., 2013. Point-cloud multicontact planning for humanoids: Preliminary results. 6th IEEE Conference on Robotics, Automation and Mechatronics (RAM), IEEE.
  5. Khatib, O. and S.-Y. Chung, 2014. SupraPeds: Humanoid contact-supported locomotion for 3D unstructured environments. IEEE International Conference on Robotics and Automation (ICRA), IEEE.
  6. Schmid, C. and A. Zisserman, 1997. Automatic line matching across views. Computer Vision and Pattern Recognition..
  7. Baumberg, A., 2000. Reliable feature matching across widely separated views. Computer Vision and Pattern Recognition.
  8. Matas, J., O. Chum, et al., 2004. Robust wide-baseline stereo from maximally stable extremal regions. Image and vision computing 22(10): 761-767.
  9. Bay, H., V. Ferrari, et al., 2005. Wide-baseline stereo matching with line segments. Computer Vision and Pattern Recognition.
  10. Scharstein, D. and R. Szeliski, 2002. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision 47(1-3): 7-42.
  11. Hartley, R. and A. Zisserman, 2003. Multiple view geometry in computer vision, Cambridge university press.
  12. Ayache, N. and C. Hansen, 1988. Rectification of images for binocular and trinocular stereovision. 9th International Conference on Pattern Recognition.
  13. Courtney, P., N. A. Thacker, et al., 1992. A Hardware Architecture for Image Rectification and Ground Plane Obstacle Avoidance. Proc. 11th ICPR 1992.
  14. Loop, C. and Z. Zhang, 1999. Computing rectifying homographies for stereo vision. Computer Vision and Pattern Recognition.
  15. Hartley, R. I., 1999. Theory and Practice of Projective Rectification. Int. J. Comput. Vision 35(2): 115-127.
  16. Hirschmuller, H. and D. Scharstein, 2009. Evaluation of stereo matching costs on images with radiometric differences. IEEE Transactions on Pattern Analysis and Machine Intelligence 31(9): 1582-1599.
  17. Zabih, R. and J. Woodfill, 1994. Non-parametric local transforms for computing visual correspondence. European conference on computer vision, Springer.
  18. Geiger, A., M. Roser, et al., 2010. Efficient large-scale stereo matching. Asian conference on computer vision, Springer.
  19. Hirschmuller, H., 2008. Stereo processing by semiglobal matching and mutual information. IEEE Transactions on Pattern Analysis and Machine Intelligence 30(2): 328-341.
  20. Devernay, F. and O. D. Faugeras, 1994. Computing differential properties of 3-D shapes from stereoscopic images without 3-D models. Computer Vision and Pattern Recognition.
  21. Tola, E., V. Lepetit, et al., 2010. Daisy: An efficient dense descriptor applied to wide-baseline stereo. Pattern Analysis and Machine Intelligence, IEEE Transactions on 32(5): 815-830.
  22. Kita, N., 2011. Direct floor height measurement for biped walking robot by fisheye stereo. 11th IEEE-RAS International Conference on Humanoid Robots.
  23. Pollefeys, M., R. Koch, et al., 1999. A simple and efficient rectification method for general motion. The Proceedings of the Seventh IEEE International Conference on Computer Vision.
  24. Abraham, S. and W. Förstner, 2005. Fish-eye-stereo calibration and epipolar rectification. ISPRS Journal of Photogrammetry and Remote Sensing 59(5): 278-288.
  25. Davison, A., 1998. Mobile Robot Navigation Using Active Vision. D. Phil Thesis, University of Oxford.
Download


Paper Citation


in Harvard Style

Kita N. and Kita Y. (2017). Reference Plane based Fisheye Stereo Epipolar Rectification . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-227-1, pages 308-320. DOI: 10.5220/0006261003080320


in Bibtex Style

@conference{visapp17,
author={Nobuyuki Kita and Yasuyo Kita},
title={Reference Plane based Fisheye Stereo Epipolar Rectification},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={308-320},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006261003080320},
isbn={978-989-758-227-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 6: VISAPP, (VISIGRAPP 2017)
TI - Reference Plane based Fisheye Stereo Epipolar Rectification
SN - 978-989-758-227-1
AU - Kita N.
AU - Kita Y.
PY - 2017
SP - 308
EP - 320
DO - 10.5220/0006261003080320