On the Analysis of the Depth Error on the Road Plane for Monocular Vision-Based Robot Navigation

  • Dezhen Song
  • Hyunnam Lee
  • Jingang Yi
Part of the Springer Tracts in Advanced Robotics book series (STAR, volume 57)

Abstract

A mobile robot equipped with a single camera can take images at different locations to obtain the 3D information of the environment for navigation. The depth information perceived by the robot is critical for obstacle avoidance. Given a calibrated camera, the accuracy of depth computation largely depends on locations where images have been taken. For any given image pair, the depth error in regions close to the camera baseline can be excessively large or even infinite due to the degeneracy introduced by the triangulation in depth computation. Unfortunately, this region often overlaps with the robot’s moving direction, which could lead to collisions. To deal with the issue, we analyze depth computation and propose a predictive depth error model as a function of motion parameters. We name the region where the depth error is above a given threshold as an untrusted area. Note that the robot needs to know how its motion affect depth error distribution beforehand, we propose a closed-form model predicting how the untrusted area is distributed on the road plane for given robot/camera positions. The analytical results have been successfully verified in the experiments using a mobile robot.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chaumette, F., Boukir, S., Bouthemy, P., Juvin, D.: Structure from controlled motion. IEEE Transactions on Pattern Analysis and Machine Intelligence 18(5), 492–504 (1996)Google Scholar
  2. 2.
    Bajcsy, R.: Active perception. Proceedings of the IEEE 76(8), 996–1005 (1988)CrossRefGoogle Scholar
  3. 3.
    Zavidovique, B.: First steps of robotic perception: The turning point of the 1990s. Proceedings of the IEEE 90(7), 1094–1112 (2002)CrossRefGoogle Scholar
  4. 4.
    Tarabanis, K., Allen, P., Tsai, R.: A survey of sensor planning in computer vision. IEEE Transactions on Robotics and Automation 11(1), 86–104 (1995)CrossRefGoogle Scholar
  5. 5.
    Mouragnon, E., Lhuillier, M., Dhome, M., Dekeyser, F., Sayd, P.: Monocular vision based slam for mobile robots. In: The 18th International Conference on Pattern Recognition, August 2006, pp. 1027–1031 (2006)Google Scholar
  6. 6.
    Chen, Z., Rodrigo, R., Samarabandu, J.: Implementation of an update scheme for monocular visual slam. In: International Conference on Information and Automation, December 2006, pp. 212–217 (2006)Google Scholar
  7. 7.
    Mortard, E., Raducanu, B., Cadenat, V., Vitria, J.: Incremental on-line topological map learning for a visual homing application. In: IEEE International Conference on Robotics and Automation, April 2007, pp. 2049–2054 (2007)Google Scholar
  8. 8.
    Lemaire, T., Lacroix, S.: Monocular-vision based slam using line segments. In: IEEE International Conference on Robotics and Automation, April 2007, pp. 2791–2796 (2007)Google Scholar
  9. 9.
    Royer, E., Bom, J., Michel Dhome, B.T., Lhuillier, M., Marmoiton, F.: Outdoor autonomous navigation using monocular vision. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, August 2005, pp. 1253–1258 (2005)Google Scholar
  10. 10.
    Chen, Z., Birchfield, S.T.: Qualitative vision-based mobile robot navigation. In: IEEE International Conference on Robotics and Automation, Olrando, FL, May 2006, pp. 2686–2692 (2006)Google Scholar
  11. 11.
    Michels, J., Saxena, A., Ng, A.: High speed obstacle avoidance using monocular vision and reinforcement learning. In: 22nd International Conference on Machine Learning, August 2005, pp. 593–600 (2005)Google Scholar
  12. 12.
    Song, D., Lee, H., Yi, J., Levandowski, A.: Vision-based motion planning for an autonomous motorcycle on ill-structured roads. Autonomous Robots 23(3), 197–212 (2007)CrossRefGoogle Scholar
  13. 13.
    Azarbayejani, A., Pentland, A.: Recursive estimation of motion, structure, and focal length. IEEE Transactions on Pattern Analysis and Machine Intelligence 17(6), 562–575 (1995)CrossRefGoogle Scholar
  14. 14.
    Jebara, T., Azarbayejani, A., Pentland, A.: 3D structure from 2D motion. IEEE Signal Processing Magazine 16(3), 66–84 (1999)CrossRefGoogle Scholar
  15. 15.
    Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography: a factorization method. International Journal of Computer Vision 9(2), 137–154 (1992)CrossRefGoogle Scholar
  16. 16.
    Martinec, D., Pajdla, T.: 3D recontruction by fitting low-rank matrices with missing data. In: IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, June 2005, pp. 198–205 (2005)Google Scholar
  17. 17.
    Brandt, S.: Closed-form solutions for affine reconstruction under missing data. In: 7th European Conference on Computer Vision, Copenhagen, Denmark, May 2002, pp. 109–114 (2002)Google Scholar
  18. 18.
    Hartley, R., Schaffalizky, F.: Powerfactorization: 3D reconstruction with missing or uncertain data. In: Australia-Japan Advanced Workshop on Computer Vision (September 2003)Google Scholar
  19. 19.
    Guilbert, N., Bartoli, A.: Batch recovery of multiple views with missing data using direct sparse solvers. In: British Machine Vision Conference, Norwich, UK (September 2003)Google Scholar
  20. 20.
    Anandan, P., Irani, M.: Factorization with uncertainty. International Journal of Computer Vision 49(3), 101–116 (2002)MATHCrossRefGoogle Scholar
  21. 21.
    Triggs, B.: Plane+parallax, tensors and factorization. In: 6th European Conference on Computer Vision, Dublin, Ireland, June 2000, pp. 522–538 (2000)Google Scholar
  22. 22.
    Irani, M., Anandan, P., Cohen, M.: Direct recovery of planar-parallax from multiple frames. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(11), 1528–1534 (2002)CrossRefGoogle Scholar
  23. 23.
    Rother, C., Carlsson, S.: Linear multi view reconstruction and camera recovery using a reference plane. International Journal of Computer Vision 49(3), 117–141 (2002)MATHCrossRefGoogle Scholar
  24. 24.
    Bartoli, A., Sturm, P.: Contrained structure and motion from multiple uncalibrated views of a piecewise planar scene. International Journal of Computer Vision 52(1), 45–64 (2003)Google Scholar
  25. 25.
    Dellaert, F., Seitz, S.M., Thorpe, C.E., Thrun, S.: Structure from motion without correspondence. In: IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head, SC, June 2000, pp. 557–564 (2000)Google Scholar
  26. 26.
    Chowdhury, A.K.R., Chellappa, R.: Statistical bias in 3-D reconstruction from a monocular video. IEEE Transactions on Image Processing 14(8), 1057–1062 (2005)Google Scholar
  27. 27.
    Hartley, R., Zisserman, A.: Multiple View Geometry in computer vision. Cambridge University Press, Cambridge (2003)Google Scholar
  28. 28.
    Bouguet, J.-Y.: Camera calibration toolbox for matlab (2007), http://www.vision.caltech.edu/bouguetj/calib_doc/index.html

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Dezhen Song
    • 1
  • Hyunnam Lee
    • 2
  • Jingang Yi
    • 3
  1. 1.CSE Dept.Texas A&M University 
  2. 2.Samsung Techwin Robot Business 
  3. 3.MAE Dept.Rutgers University 

Personalised recommendations