Real-Time Traversable Surface Detection by Colour Space Fusion and Temporal Analysis

We present a real-time approach for traversable surface detection using a low-cost monocular camera mounted on an autonomous vehicle. The proposed methodology extracts colour and texture information from various channels of the HSL, YCbCr and LAB colourspaces by temporal analysis in order to create a "traversability map". On this map lighting and water artifacts are eliminated including shadows, reflections and water prints. Additionally, camera vibration is compensated by temporal filtering leading to robust path edge detection in blurry images. The performance of this approach is extensively evaluated over varying terrain and environmental conditions and the effect of colourspace fusion on the system's precision is analysed. The results show a mean accuracy of 97% over this comprehensive test set.

[1]  Rodney A. Brooks,et al.  Visually-guided obstacle avoidance in unstructured environments , 1997, Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97.

[2]  Gary R. Bradski,et al.  Detection of Drivable Corridors for Off-Road Autonomous Navigation , 2006, 2006 International Conference on Image Processing.

[3]  Fan Yang,et al.  Color Space Selection for Moving Shadow Elimination , 2007, Fourth International Conference on Image and Graphics (ICIG 2007).

[4]  Takeo Kanade,et al.  Vision and Navigation for the Carnegie-Mellon Navlab , 1987 .

[5]  Kurt Konolige,et al.  Large-Scale Visual Odometry for Rough Terrain , 2007, ISRR.

[6]  Rita Cucchiara,et al.  Improving shadow suppression in moving object detection with HSV color information , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[7]  Jun Wu,et al.  Virtual Line Group Based Video Vehicle Detection Algorithm Utilizing Both Luminance and Chrominance , 2007, 2007 2nd IEEE Conference on Industrial Electronics and Applications.

[8]  Larry Matthies,et al.  Stereo vision and rover navigation software for planetary exploration , 2002, Proceedings, IEEE Aerospace Conference.

[9]  Pei-Yung Hsiao,et al.  A Portable Real-Time Lane Departure Warning System based on Embedded Calculating Technique , 2006, 2006 IEEE 63rd Vehicular Technology Conference.

[10]  Avinash C. Kak,et al.  Vision for Mobile Robot Navigation: A Survey , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Amnon Shashua,et al.  Off-road Path Following using Region Classification and Geometric Projection Constraints , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[12]  Massimo Bertozzi,et al.  Vision-based intelligent vehicles: State of the art and perspectives , 2000, Robotics Auton. Syst..

[13]  B. Michaelis,et al.  Real-time vehicle and lane detection with embedded hardware , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[14]  Alberto Broggi,et al.  The Single Frame Stereo Vision System for Reliable Obstacle Detection Used during the 2005 DARPA Grand Challenge on TerraMax , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[15]  Ben J. A. Kröse,et al.  Heading direction of a mobile robot from the optical flow , 2000, Image Vis. Comput..

[16]  Sanjiv Singh,et al.  Obstacle detection in smooth high curvature terrain , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[17]  You Zhi-sheng,et al.  An Improved Video Compression Algorithm for Lane Surveillance , 2007, Fourth International Conference on Image and Graphics (ICIG 2007).