Robot Visual Localization Based on 4-DOF Ego-Motion Model and RANSAC

Abstract:

A robot monocular localization method based on 4-DOF ego-motion model and RANdom SAmple Consensus (RANSAC) in country road environment is introduced in this paper. The algorithm uses as input only those images provided by a single camera mounted on the roof of the vehicle. Given the image motion, the stable localization of vehicle is computed by the 4-DOF ego-motion model and RANSAC algorithm, which can efficiently estimate the instantaneous steering angle and traveling distance even if the vehicle runs on bumpy road. The proposed algorithms are successfully validated on videos from an automotive platform. Furthermore, the localization results from our method are compared to the ground truth measured with a GPS/INS joint system, and the trajectory recovered from the estimated localization parameters is superimposed onto a digital map. These experimental results indicate that the algorithms are efficient and encouraging.

• Periodical: Advanced Materials Research (Volumes 268-270)
• Pages: 1494-1499
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.268-270.1494
• Online since: July 2011
• Authors: Cai Ling Wang, Chun Xia Zhao, Jing Yu Yang
• Keywords: 4-DOF Ego-Motion Model, Hyper-Complex Wavelet, Monocular Localization, Multiscale Optical Flow, RANSAC

References

[1] Borenstein, J., Everett, H.R., Feng, L., and Wehe, D.: Mobile Robot Positioning: Sensors and Techniques. Journal of Robotic Systems Vol. 14, No. 4, pp.231-249, (1997).

DOI: 10.1002/(sici)1097-4563(199704)14:4<231::aid-rob2>3.0.co;2-r

[2] Jason, C., Rahul, S., Illah, N., and Aroon, P.: A Robust Visual Odometry and Precipice Detection System Using Consumer-grade Monocular Vision. In Proc. of Inter. Conf. on Robotics and Automation, pp.3421-3427, (2005).

DOI: 10.1109/robot.2005.1570639

[3] Davide S. and Roland S.: Appearance-Guided Monocular Omnidirectional Visual Odometry for Outdoor Ground Vehicles. IEEE Trans. on Robotics. Vol. 24, No. 5, p.1015 – 1026, (2008).

DOI: 10.1109/tro.2008.2004490

[4] Badino, H.: Binocular Ego-Motion Estimation for automotive application, Ph.D. thesis, Goethe Frankfurt University, Frankfurt am Main, Germany ( 2008).

[5] David, N. r, Oleg, N. and James, B.: Visual odometry for ground vehicle applications. Journal of Field Robotics. Vol. 23, No. 1, pp.3-20 (2006).

[6] Michal, I., Benny, R., and Shmuel, P.: Recovery of Egomotion Using Region Alignment. IEEE Trans. on Pattern analysis and machine intelligence. Vol. 19, No. 3, pp.268-272 (1997).

[7] Tardif, J.P., Pavlidis, Y., Daniilidis, K.: Monocular Visual Odometry in Urban Environments Using an Omnidirectional Camera. In Proc. of IEEE Inter. Conf. on Intelligent Robots and Systems, p.2531–2538, (2008).

DOI: 10.1109/iros.2008.4651205

[8] Andrew J.D., Ian D.R., Nicholas D.M. and Olivier S.: MonoSLAM: Real-Time Single Camera SLAM. IEEE Trans. on Pattern analysis and machine intelligence. Vol. 29 No. 6, p.1052–1067, (2007).

DOI: 10.1109/tpami.2007.1049

[9] David, N., Oleg, N., and James, B.: Visual odometry. In Proc. of IEEE Conf. on Computer Vision and Pattern Recognition, Vol. 1, pp.652-659, (2004).