Skip to main content
SpringerLink
Log in

Visual odometry based on a Bernoulli filter

  • Special Section on Advanced Control Theory and Techniques based on Data Fusion
  • Published:
International Journal of Control, Automation and Systems Aims and scope Submit manuscript

Abstract

In this paper, we propose a Bernoulli filter for estimating a vehicle’s trajectory under random finite set (RFS) framework. In contrast to other approaches, ego-motion vector is considered as the state of an extended target while the features are considered as multiple measurements that originated from the target. The Bernoulli filter estimates the state of the extended target instead of tracking individual features, which presents a recursive filtering framework in the presence of high association uncertainty. Experimental results illustrate that the proposed approach exhibits good robustness under real traffic scenarios.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. D. Scaramuzza, F. Fraundorfer, M. Pollefeys, and R. Siegwart, “Absolute scale in structure from motion from a single vehicle mounted camera by exploiting nonholonomic constraints,” Proc. of International Conference on Computer Vision, pp. 1413–1419, October 2009.

    Google Scholar 

  2. G. Garcia, M. A. Sotelo, I. Parra, D. Fernandez, and M. Gavilan, “2D visual odometry method for global positioning measurement,” Proc. of International Symposium on Intelligent Signal Processing, pp. 1–6, October 2007.

    Google Scholar 

  3. A. Davison, “Real-time simultaneous localization and mapping with a single camera,” Proc. of International Conference on Computer Vision, pp. 1403–1410, 2003.

    Chapter  Google Scholar 

  4. D. Burschka and G. D. Hager, “V-GPS (SLAM): vision-based inertial system for mobile robots,” Proc. of International Conference on Robotics and Automation, pp. 409–415, May 2004.

    Google Scholar 

  5. K. Konolige, M. Agrawal, and J. Sola, “Large-scale visual odometry for rough terrain,” Proc. of International Symposium on Research in Robotics, pp. 201–212, November 2007.

    Google Scholar 

  6. D. Scaramuzza and R. Siegwart, “Appearanceguided monocular omnidirectional visual odometry for outdoor ground vehicles,” IEEE Trans. on Robotics, vol. 24, no. 5, pp. 1015–1026, October 2008.

    Article  Google Scholar 

  7. D. Scaramuzza, F. Fraundorfer, and R. Siegwart, “Real-time monocular visual odometry for on-road vehicles with 1-point RANSAC,” Proc. of International Conference on Robotics and Automation, pp. 4293–4299, May 2009.

    Google Scholar 

  8. C. McCarthy and N. Barnes, “Performance of optical flow techniques for indoor navigation with a mobile robot,” Proc. of International Conference on Robotics and Automation, pp. 5093–5098, May 2004.

    Google Scholar 

  9. J. Campbell, R. Sukthankar, and I. Nourbakhsh, “Techniques for evaluating optical flow for visual odometry in extreme terrain,” Proc. of International Conference on Intelligent Robots and Systems, pp. 3704–3711, October 2004.

    Google Scholar 

  10. P. Corke, D. Strelow, and S. Singh, “Omnidirectional visual odometry for a planetary rover,” Proc. of International Conference on Intelligent Robots and Systems, pp. 4007–4012, October 2004

    Google Scholar 

  11. F. Zhang, H. Stähle, A. Gaschler, C. Buckl, and A. Knoll, “Single camera visual odometry based on Random Finite Set Statistics,” Proc. of International Conference on Intelligent Robots and Systems, pp. 559–566, October 2012.

    Google Scholar 

  12. F. Zhang, H. Stähle, G. Chen, C. Buckl, and A. Knoll, “Visual odometry based on random finite set statistics in urban environment,” Proc. of Intelligent Vehicles Symposium, pp. 69–74, June 2012.

    Google Scholar 

  13. B.-T. Vo, C. See, N. Ma, and W. T. Ng, “Multisensor joint detection and tracking with the Bernoulli filter,” IEEE Trans. on Aerospace and Electronic Systems, vol. 48, no. 2, pp. 1385–1402, April 2012.

    Article  Google Scholar 

  14. B.-N. Vo and W.-K. Ma, “The Gaussian mixture probability hypothesis density filter,” IEEE Trans. on Signal Processing, vol. 54, no. 11, pp. 4091–4104, November 2006.

    Article  Google Scholar 

  15. W. Yang, Y. Fu, J. Long, and X. Li, “Joint detection, tracking, and classification of multiple targets in clutter using the PHD filter,” IEEE Trans. on Aerospace and Electronic Systems, vol. 48, no. 4, pp. 3594–3609, October 2012

    Article  Google Scholar 

  16. B. Ristic, B.-T. Vo, B.-N. Vo, and A. Farina, “A tutorial on Bernoulli filters: theory, implementation and applications,” IEEE Trans. on Signal Processing, vol. 61, no. 13, pp. 3406–3430, July 2013.

    Article  MathSciNet  Google Scholar 

  17. M. S. Arulampalam, S. Maskell, N. Gordon, and T. Clapp, “A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking,” IEEE Trans. on Signal Processing, vol. 50, no. 2, pp. 174–188, February 2002.

    Article  Google Scholar 

  18. B. Kitt, A. Geiger, and H. Lategahn, “Visual odometry based on stereo image sequences with RANSAC-based outlier rejection scheme,” Proc. of Intelligent Vehicles Symposium, pp. 486–492, June 2010.

    Google Scholar 

  19. C. Harris and M. J. Stephens, “A combined corner and edge detector,” Proc. of Alvey Vision Conference, pp. 147–152, 1988.

    Google Scholar 

  20. D. G. Lowe, “Object recognition from local scaleinvariant features,” Proc. of IEEE International Conference on Computer Vision, pp. 1150–1157, 1999.

    Chapter  Google Scholar 

  21. H. Bay, T. Tuytelaars, and L. V. Gool, “SURF: speeded up robust features,” Proc. of European Conference on Computer Vision, pp. 404–417, May 2006.

    Google Scholar 

  22. C. Tomasi and T. Kanade, Detection and Tracking of Point Features, Carnegie Mellon, April 1991.

    Google Scholar 

  23. R. P. S. Mahler, “Multitarget Bayes filtering via first-order multitarget moments,” IEEE Trans. on Aerospace and Electronic Systems, no. 4, pp. 1152–1178, October 2003.

    Article  Google Scholar 

  24. N. Houshangi and F. Azizi, “Mobile robot position determination using data integration of odometry and gyroscope,” Proc. of Automation Congress, pp. 1–8, July 2006.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Robotics and Embedded Systems, Technische Universität München, 85748, Garching bei München, Germany

    Feihu Zhang & Alois Knoll

  2. Cranfield University, Defense Academy of the United Kindom, Shrivenham SN6 8LA, UK

    Daniel Clarke

Authors
  1. Feihu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Daniel Clarke
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Alois Knoll
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Feihu Zhang.

Additional information

Feihu Zhang received his B.Sc. degree in Automation and his M.Sc. degree in Control Theory and Application from Graduate School of Xi’an Jiaotong University, Xi’an, China, 2010. He is currently a Ph.D. candidate at Technical University of Munich. His main research interests are intelligent vehicle and robotics.

Daniel Clarke received his Ph.D. from the University of Innsbruck in 2009. Between 2013 and 2014 he joined fortiss as a leader in Data and Sensor Fusion research group. From 2015 he is a lecture at Cranfield University, at the Defense Academy of the United Kingdom. His research interests include the development of the techniques and methodologies necessary to realize the integration of homogeneous and heterogeneous sensor networks. Alois Kno

Alois Knoll received the diploma M.Sc. in Electrical/Communications Engineering from the University of Stuttgart, Germany, in 1985 and his Ph.D. (summa cum laude) in computer science from the Technical University of Berlin, Germany, in 1988. He served on the faculty of the computer science department of TU Berlin until 1993, when he qualified for teaching computer science at a university (habilitation). He then joined the Technical Faculty of the University of Bielefeld, where he was a full professor and the director of the research group Technical Informatics until 2001. Between May 2001 and April 2004 he was a member of the board of directors of the Fraunhofer-Institute for Autonomous Intelligent Systems. At AIS he was head of the research group Robotics Construction Kits, dedicated to research and development in the area of educational robotics. Since autumn 2001 he has been a professor of Computer Science at the Computer Science Department of the Technische Universität München. He is also on the board of directors of the Central Institute of Medical Technology at TUM (IMETUM-Garching); between April 2004 and March 2006 he was Executive Director of the Institute of Computer Science at TUM.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, F., Clarke, D. & Knoll, A. Visual odometry based on a Bernoulli filter. Int. J. Control Autom. Syst. 13, 530–538 (2015). https://doi.org/10.1007/s12555-014-0192-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12555-014-0192-3

Keywords

Search

Navigation