Distance estimation and vehicle position detection based on monocular camera

This paper describes systematically two methods used in intelligent transportation systems: Distance Estimation using an onboard camera and car position detection. Distance estimation is a method for detecting distance for the preceding vehicles based on monocular camera. Vehicle position detection is a method of specifying the vehicle position relative to the road that can serve as Lane Departure Warning system. These two approaches have been discussed and implemented in this article. For lane detection and tracking, Hough Transform and Kalman filter were adopted. A brief introduction about both lane detection system and object detection is given. Finally, both approaches have been evaluated on a large dataset of videos.

[1]  Paul A. Viola,et al.  Rapid object detection using a boosted cascade of simple features , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[2]  Wang Rongben,et al.  Study on method of detecting preceding vehicle based on monocular camera , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[3]  S. Khan,et al.  Real time lane detection for autonomous vehicles , 2008, 2008 International Conference on Computer and Communication Engineering.

[4]  Yingfeng Cai,et al.  A Lane Departure Warning System Based on Machine Vision , 2008, 2008 IEEE Pacific-Asia Workshop on Computational Intelligence and Industrial Application.

[5]  Anton Kummert,et al.  A warning algorithm for Lane Departure Warning system , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[6]  Wei Wang,et al.  A multiple object tracking method using Kalman filter , 2010, The 2010 IEEE International Conference on Information and Automation.

[7]  F. Mariut,et al.  Lane mark detection using Hough transform , 2012, 2012 International Conference and Exposition on Electrical and Power Engineering.