Advertisement

International Journal of Computer Vision

, Volume 95, Issue 1, pp 74–85 | Cite as

1-Point-RANSAC Structure from Motion for Vehicle-Mounted Cameras by Exploiting Non-holonomic Constraints

  • Davide ScaramuzzaEmail author
Article

Abstract

This paper presents a new method to estimate the relative motion of a vehicle from images of a single camera. The computational cost of the algorithm is limited only by the feature extraction and matching process, as the outlier removal and the motion estimation steps take less than a fraction of millisecond with a normal laptop computer. The biggest problem in visual motion estimation is data association; matched points contain many outliers that must be detected and removed for the motion to be accurately estimated. In the last few years, a very established method for removing outliers has been the “5-point RANSAC” algorithm which needs a minimum of 5 point correspondences to estimate the model hypotheses. Because of this, however, it can require up to several hundreds of iterations to find a set of points free of outliers. In this paper, we show that by exploiting the nonholonomic constraints of wheeled vehicles it is possible to use a restrictive motion model which allows us to parameterize the motion with only 1 point correspondence. Using a single feature correspondence for motion estimation is the lowest model parameterization possible and results in the two most efficient algorithms for removing outliers: 1-point RANSAC and histogram voting. To support our method we run many experiments on both synthetic and real data and compare the performance with a state-of-the-art approach. Finally, we show an application of our method to visual odometry by recovering a 3 Km trajectory in a cluttered urban environment and in real-time.

Keywords

Outlier removal Ransac Structure from motion 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Clemente, L. A., Davison, A. J., Reid, I., Neira, J., & Tardos, J. D. (2007). Mapping large loops with a single hand-held camera. In Robotics science and systems. Google Scholar
  2. Corke, P. I., Strelow, D., & Singh, S. (2004). Omnidirectional visual odometry for a planetary rover. In IROS. Google Scholar
  3. Davison, A. (2003). Real-time simultaneous localisation and mapping with a single camera. In International conference on computer vision. Google Scholar
  4. Deans, M. C. (2002). Bearing-only localization and mapping. PhD thesis, Carnegie Mellon University. Google Scholar
  5. Faugeras, O., & Maybank, S. (1990). Motion from point matches: multiplicity of solutions. International Journal of Computer Vision, 4, 225–246. CrossRefGoogle Scholar
  6. Fischler, M. A., & Bolles, R. C. (1981). RANSAC random sampling concensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of ACM, 26, 381–395. CrossRefMathSciNetGoogle Scholar
  7. Goecke, R., Asthana, A., Pettersson, N., & Petersson, L. (2007). Visual vehicle egomotion estimation using the Fourier-Mellin transform. In IEEE intelligent vehicles symposium. Google Scholar
  8. Harris, C., & Stephens, M. (1988). A combined corner and edge detector. In Fourth alvey vision conference (pp. 147–151). Google Scholar
  9. Hartley, R., & Zisserman, A. (2004). Multiple view geometry in computer vision (2nd ed.). Cambridge: Cambridge University Press ISBN:0521540518. zbMATHGoogle Scholar
  10. Jung, I., & Lacroix, S. (2005). Simultaneous localization and mapping with stereovision. In Robotics research: the 11th international symposium. Google Scholar
  11. Kruppa, E. (1913). Zur ermittlung eines objektes aus zwei perspektiven mit innerer orientierung. In Abt. IIa.: Vol. 122. Sitz.-Ber. Akad. Wiss., Wien, Math. Naturw. Kl. (pp. 1939–1948). Google Scholar
  12. Lacroix, S., Mallet, A., Chatila, R., & Gallo, L. (1999). Rover self localization in planetary-like environments. In International symposium on articial intelligence, robotics, and automation for space (i-SAIRAS) (pp. 433–440). Google Scholar
  13. Lemaire, T., & Lacroix, S. (2007). Slam with panoramic vision. Journal of Field Robotics, 24, 91–111. CrossRefGoogle Scholar
  14. Lhuillier, M. (2005). Automatic structure and motion using a catadioptric camera. In IEEE workshop on omnidirectional vision. Google Scholar
  15. Longuet-Higgins, H. (1981). A computer algorithm for reconstructing a scene from two projections. Nature, 293, 133–135. CrossRefGoogle Scholar
  16. Maimone, M., Cheng, Y., & Matthies, L. (2007). Two years of visual odometry on the mars exploration rovers: Field reports. Journal of Field Robotics, 24, 169–186. CrossRefGoogle Scholar
  17. Milford, M. J., & Wyeth, G. (2008). Single camera vision-only slam on a suburban road network. In IEEE international conference on robotics and automation, ICRA’08. Google Scholar
  18. Milford, M., Wyeth, G., & Prasser, D. (2004). Ratslam: A hippocampal model for simultaneous localization and mapping. In International conference on robotics and automation, ICRA’04. Google Scholar
  19. Moravec, H. (1980). Obstacle avoidance and navigation in the real world by a seeing robot rover. PhD thesis, Stanford University. Google Scholar
  20. Nister, D. (2003). An efficient solution to the five-point relative pose problem. In CVPR03. Google Scholar
  21. Nister, D. (2005). Preemptive ransac for live structure and motion estimation. Machine Vision and Applications, 16, 321–329. CrossRefGoogle Scholar
  22. Nister, D., Naroditsky, O., & Bergen, J. (2006). Visual odometry for ground vehicle applications. Journal of Field Robotics Google Scholar
  23. Oliensis, J. (2002). Exact two-image structure from motion. PAMI. Google Scholar
  24. Ortin, D., & Montiel, J. M. M. (2001). Indoor robot motion based on monocular images. Robotica, 19, 331–342. CrossRefGoogle Scholar
  25. Philip, J. (1996). A non-iterative algorithm for determining all essential matrices corresponding to five point pairs. Photogrammetric Record, 15, 589–599. CrossRefGoogle Scholar
  26. Pizarro, O., Eustice, R., & Singh, H. (2003). Relative pose estimation for instrumented, calibrated imaging platforms. In DICTA. Google Scholar
  27. Scaramuzza, D., & Siegwart, R. (2008). Appearance-guided monocular omnidirectional visual odometry for outdoor ground vehicles. IEEE Transactions on Robotics, Special Issue on Visual SLAM, 24. Google Scholar
  28. Scaramuzza, D., Martinelli, A., & Siegwart, R. (2006). A toolbox for easy calibrating omnidirectional cameras. In IEEE international conference on intelligent robots and systems (IROS 2006). Google Scholar
  29. Scaramuzza, D., Fraundorfer, F., Pollefeys, M., & Siegwart, R. (2008). Closing the loop in appearance-guided structure-from-motion for omnidirectional cameras. In Eighth workshop on omnidirectional vision (OMNIVIS’08). Google Scholar
  30. Scaramuzza, D., Fraundorfer, F., Pollefeys, M., & Siegwart, R. (2009). Absolute scale in structure from motion from a single vehicle mounted camera by exploiting nonholonomic constraints. In International conference on computer vision. Google Scholar
  31. Siegwart, R., Nourbakhsh, I., & Scaramuzza, D. (2011). Introduction to autonomous mobile robots (2nd ed.). Cambridge: MIT Press. Google Scholar
  32. Stewenius, H., Engels, C., & Nister, D. (2006). Recent developments on direct relative orientation. ISPRS Journal of Photogrammetry and Remote Sensing, 60, 284–294. CrossRefGoogle Scholar
  33. Tardif, J., Pavlidis, Y., & Daniilidis, K. (2008). Monocular visual odometry in urban environments using an omnidirectional camera. In IEEE IROS’08. Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  1. 1.Autonomous Systems LabETH ZurichZurichSwitzerland

Personalised recommendations