Hostname: page-component-76fb5796d-45l2p Total loading time: 0 Render date: 2024-04-25T18:17:36.777Z Has data issue: false hasContentIssue false
  • English
  • Français

Robust visual odometry for vehicle localization in urban environments

Published online by Cambridge University Press:  22 May 2009

I. Parra ,
M. A. Sotelo ,
D. F. Llorca  and
M. Ocaña
I. Parra
Affiliation:
Department of Electronics, Escuela Politécnica Superior, University of Alcalá. Alcalá de Henares, Madrid, Spain
M. A. Sotelo*
Affiliation:
Department of Electronics, Escuela Politécnica Superior, University of Alcalá. Alcalá de Henares, Madrid, Spain
D. F. Llorca
Affiliation:
Department of Electronics, Escuela Politécnica Superior, University of Alcalá. Alcalá de Henares, Madrid, Spain
M. Ocaña
Affiliation:
Department of Electronics, Escuela Politécnica Superior, University of Alcalá. Alcalá de Henares, Madrid, Spain
*
*Corresponding author. E-mail: sotelo@depeca.uah.es
Get access Rights & Permissions [Opens in a new window]

Summary

This paper describes a new approach for estimating the vehicle motion trajectory in complex urban environments by means of visual odometry. A new strategy for robust feature extraction and data post-processing is developed and tested on-road. Images from scale-invariant feature transform (SIFT) features are used in order to cope with the complexity of urban environments. The obtained results are discussed and compared to previous works. In the prototype system, the ego-motion of the vehicle is computed using a stereo-vision system mounted next to the rear view mirror of the car. Feature points are matched between pairs of frames and linked into 3D trajectories. The distance between estimations is dynamically adapted based on re-projection and estimation errors. Vehicle motion is estimated using the non-linear, photogrametric approach based on RAndom SAmple Consensus (RANSAC). The final goal is to provide on-board driver assistance in navigation tasks, or to provide a means of autonomously navigating a vehicle. The method has been tested in real traffic conditions without using prior knowledge about the scene or the vehicle motion. An example of how to estimate a vehicle's trajectory is provided along with suggestions for possible further improvement of the proposed odometry algorithm.

Keywords

3D visual odometryGlobal localizationVisionSIFT
Type
Article
Information
Robotica , Volume 28 , Issue 3 , May 2010 , pp. 441 - 452
Copyright
Copyright © Cambridge University Press 2009

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

1.Zhang, Z. and Faugeras, O. D., “Estimation of displacements from two 3-d frames obtained from stereo,” IEEE Trans. Pattern Analysis and Mach. Intell. 14 (12) (Dec. 1992).CrossRefGoogle Scholar
2.Nister, D., Narodistsky, O. and Beren, J., “Visual Odometry,” Proceedings IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC, USA (June, 2004). Vol. 1, pp. 652–659.Google Scholar
3.Hagnelius, A., Visual, OdometryMasters Thesis (Umea, Sweden: Umea University, Apr. 2005).Google Scholar
4.Forsyth, D. A. and Ponce, J., Computer Vision: A Modern Approach (Prentice Hall, 2003).Google Scholar
5.Agrawal, M. and Konolige, K., “Real-Time Localization in Outdoor Environments Using Stereo Vision and Inexpensive GPS,” Eighteenth International Conference on Pattern Recognition (ICPR06), Hong Kong, China (2006) pp. 1063–1068.Google Scholar
6.Simond, N. and Parent, M., “Free Space in Front of an Autonomous Guided Vehicle in Inner-City Conditions,” European Computer Aided Systems Theory Conference (Eurocast 2007). Las Palmas de Gran Canaria, Spain (2007) pp. 362–363.Google Scholar
7.Harris, C. and Stephens, M., “A Combined Corner and Edge Detector,” Proceedings of the Fourth Alvey Vision Conference. Manchester, UK (1988) pp. 147–151.Google Scholar
8.Lucas, B. and Kanade, T., “An Iterative Image Registration Technique with an Aplication to Stereo Vision,” Proceedings of the International Joint Conference on Artifial Intelligence. Vancouver, Canada (1981) pp. 674–679.Google Scholar
9.Schmid, C., Mohr, R. and Bauckhage, C., “Evaluation of interest point detectors.” Int. J. Comput. Vis. 37 (2)151–172 (2000).CrossRefGoogle Scholar
10.Boufama, B., Reconstruction tridimensionnelle en vision par ordinateur: Cas des cameras non etalonnees PhD Thesis (France, INP de Grenoble, 1994).Google Scholar
11.Se, S., Lowe, D. and Little, J., “Vision-Based Mobile Robot Localization and Mapping Using Scale-Invariant Features,” Proceedings of the IEEE ICRA. Seoul, Korea (2001) pp. 2051–2058.Google Scholar
12.Murray, D. and Little, J., “Using Real-Time Stereo Vision for Mobile Robot Navigation,” Proceedings of the IEEE Workshop on Perception for Mobile Agents. Santa Barbara, CA, USA (1998).Google Scholar
13.Lowe, D. G., “Object Recognition from Local Scale-Invariant Features,” Proceedings of the Seventh ICCV. Kerkyra, Greece (1999) pp. 1150–1157.Google Scholar
14.Gordon, I. and Lowe, D. G., “What and Where: 3D Object Recognition with Accurate Pose,” International Symposium on Mixed and Augmented Reality. Santa Barbara, CA, USA (2006). pp. 67–82.Google Scholar
15.Beis, J. S. and Lowe, D. G., “Shape Indexing Using Approximate Nearest-Neightbour Search in High-Dimensional Spaces,” Proceedings of the IEEE Conference on CVPR. San Juan, Puerto Rico (1997) pp. 1000–1006.Google Scholar
16.García-García, R., Sotelo, M. A., Parra, I., Fernández, D., Naranjo, J. E. and Gavilán, M., “3D visual odometry for road vehicles,” J. Intell. Robot. Syst. 51, 113–134 (2008).CrossRefGoogle Scholar
17.Fischler, M. A. and Bolles, R. C., “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,” Commun. ACM. 24 (6), 381–395 (June, 1981).CrossRefGoogle Scholar
18.Hartley, R. and Zisserman, A., Multiple View Geometry in Computer Vision. (Cambridge University Press, 2004).CrossRefGoogle Scholar
19.Matlab, “Camera calibration toolbox for matlab,” (2007), http://www.vision.caltech.edu/bouguetj/calib_doc/.Google Scholar
20.Parra, I., Fernández, D., Sotelo, M. A., Bergasa, L. M., Revenga, P., Nuevo, J., Ocana, M. and García, M. A., “Combination of feature extraction methods for svm pedestrian detection,” IEEE Trans. Intell. Transp. Syst. 8 (2), (June, 2007).Google Scholar