International Journal of Automotive Technology

, Volume 20, Issue 6, pp 1245–1254 | Cite as

Drift Compensation of Mono-Visual Odometry and Vehicle Localization Using Public Road Sign Database

  • Chanhee Jang
  • Young-Keun KimEmail author


This paper proposes a novel localization method based on a camera that can estimate the absolute position of a vehicle using a public online database of road signs. The estimated absolute position near a road sign is used to compensate the drift error of visual odometry (VO). In the first phase, the relative position between a road sign and a vehicle is estimated by matching a detected road sign image with the reference image from a public online database. Subsequently, the absolute position of the vehicle is calculated using the data from the database. Once the absolute position of the vehicle is estimated near a road sign, the current position of VO is updated to compensate the accumulated error. From a 24-km driving road test, it is validated that the proposed algorithm can estimate the absolute position of a vehicle within an error of 1.5 m. Moreover, a test of trajectory 3 km showed that it can maintain the drift error of VO within tens of meters. Our method is easy to be deployed, has low computation cost, and is accessible to a wide range of driving environments such as highways.


Vision ADAS Vehicle localization Road sign detection Visual odometry Drift compensation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Agarwal, P., Burgard, W. and Spinello, L. (2015). Metric localization using google street view. Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems (IROS), Hamburg, Germany.Google Scholar
  2. Agrawal, M. and Konolige, K. (2006). Real-time localization in outdoor environments using stereo vision and inexpensive GPS. Proc. 18th Int. Conf. Pattern Recognition (ICPR'06), Hong Kong, China.Google Scholar
  3. Dornhege, C. and Kleiner, A. (2006). Visual odometry for tracked vehicles. Proc. IEEE Int. Workshop on Safety, Security and Rescue Robotics (SSRR), Gaithersburg, Maryland, USA.Google Scholar
  4. Durrant-Whyte, H. and Bailey, T. (2006). Simultaneous localization and mapping: Part I. IEEE Robotics & Automation Magazine 13, 2, 99–110.CrossRefGoogle Scholar
  5. Fuentes-Pacheco, J., Ruiz-Ascencio, J. and Rendon- Mancha, J. M. (2015). Visual simultaneous localization and mapping: A survey. Artificial Intelligence Review 43, 1, 55–81.CrossRefGoogle Scholar
  6. Geiger, A., Ziegler, J. and Stiller, C. (2011). StereoScan: Dense 3d reconstruction in real-time. Proc. IEEE Intelligent Vehicles Symp. (IV), Baden-Baden, Germany.Google Scholar
  7. Howard, A. (2008). Real-time stereo visual odometry for autonomous ground vehicles. Proc. IEEE/RSJ Int. Conf. Intelligent Robots and Systems, Nice, France.Google Scholar
  8. Jang, C., Park, J. E. and Kim, Y. K. (2017). Compensating drift of mono-visual odometry using road direction sign database. Proc. IEEE 20th Int. Conf. Intelligent Transportation Systems (ITSC), Yokohama, Japan.Google Scholar
  9. Jang, G., Lee, S. and Kweon, I. (2002). Color landmark based self-localization for indoor mobile robots. Proc. IEEE Int. Conf. Robotics and Automation, Washington, D.C., USA.Google Scholar
  10. Karami, E., Prasad, S. and Shehata, M. (2017). Image matching using SIFT, SURF, BRIEF and ORB: Performance comparison for distorted images. arXiv: 1710.02726.Google Scholar
  11. Kitt, B., Rehder, J., Chambers, A., Schönbein, M., Lategahn, H. and Singh, S. (2011). Monocular visual odometry using a planar road model to solve scale ambiguity. Proc. European Conf. Mobile Robots, Örebro, Sweden.Google Scholar
  12. Korea Institute of Civil Engineering and Building Technology (KICT. (2016). Roadsign Management System, Google Scholar
  13. Moré, J. J. (1978). The levenberg-marquardt algorithm: Implementation and theory. Numerical Analysis, 105–116.CrossRefGoogle Scholar
  14. Olson, E. (2011). AprilTag: A robust and flexible visual fiducial system. Proc. IEEE Int. Conf. Robotics and Automation, Shanghai, China.Google Scholar
  15. Pagel, F. (2009). Robust monocular egomotion estimation based on an IEKF. Proc. Canadian Conf. Computer and Robot Vision, Kelowna, BC, Canada.Google Scholar
  16. Radwan, N., Tipaldi, G. D., Spinello, L. and Burgard, W. (2016). Do you see the bakery? Leveraging geo-referenced texts for global localization in public maps. Proc. IEEE Int. Conf. Robotics and Automation (ICRA), Stockholm, Sweden.Google Scholar
  17. Redmon, J., Diwala, S., Girshick, R. and Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proc. IEEE Conf. Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA.Google Scholar
  18. Rublee, E., Rabaud, V., Konolige, K. and Bradski, G. (2011). ORB: An efficient alternative to SIFT or SURF. Proc. Int. Conf. Computer Vision, Barcelona, Spain.Google Scholar
  19. Scaramuzza, D., Fraundorfer, F., Pollefeys, M. and Siegwart, R. (2009). Absolute scale in structure from motion from a single vehicle mounted camera by exploiting nonholonomic constraints. Proc. IEEE 12th Int. Conf. Computer Vision, Kyoto, Japan.Google Scholar
  20. Scaramuzza, D. and Fraundorfer, F. (2011). Visual odometry [Tutorial]. IEEE Robotics & Automation Magazine 18, 4, 80–92.CrossRefGoogle Scholar
  21. Strelow, D. and Singh, S. (2004). Motion estimation from image and inertial measurements. The Int. J. Robotics Research 23, 12, 1157–1195.CrossRefGoogle Scholar
  22. Tao, Z., Bonnifait, P., Fremont, V. and Ibanez-Guzman, J. (2013). Lane marking aided vehicle localization. Proc. 16th Int. IEEE Conf. Intelligent Transportation Systems (ITSC 2013), The Hague, Netherlands.Google Scholar
  23. Triggs, B., McLauchlan, P. F., Hartley, R. I. and Fitzgibbon, A. W. (1999). Bundle adjustment - A modern synthesis. Proc. Int. Workshop on Vision Algorithms, Corfu, Greece.Google Scholar
  24. Zamir, A. R. and Shah, M. (2010). Accurate image localization based on google maps street view. Proc. European Conf. Computer Vision, Crete, Greece.Google Scholar

Copyright information

© KSAE/ 111-16 2019

Authors and Affiliations

  1. 1.Data Science & AI Team, Advanced Technology Inc.IncheonKorea
  2. 2.Department of Mechnical and Control EngineeringHandong Global UnibersiryGyeongbukKorea

Personalised recommendations