Enhancement performance of road recognition system of autonomous robots in shadow scenario

Road region recognition is a main feature that is gaining increasing attention from intellectuals because it helps autonomous vehicle to achieve a successful navigation without accident. However, different techniques based on camera sensor have been used by various researchers and outstanding results have been achieved. Despite their success, environmental noise like shadow leads to inaccurate recognition of road region which eventually leads to accident for autonomous vehicle. In this research, we conducted an investigation on shadow and its effects, optimized the road region recognition system of autonomous vehicle by introducing an algorithm capable of detecting and eliminating the effects of shadow. The experimental performance of our system was tested and compared using the following schemes: Total Positive Rate (TPR), False Negative Rate (FNR), Total Negative Rate (TNR), Error Rate (ERR) and False Positive Rate (FPR). The performance result of the system improved on road recognition in shadow scenario and this advancement has added tremendously to successful navigation approaches for autonomous vehicle.

[1]  Matthew Turk,et al.  VITS-A Vision System for Autonomous Land Vehicle Navigation , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Guangming Xiong,et al.  Road detection using support vector machine based on online learning and evaluation , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[3]  Pierre Charbonnier,et al.  Road boundaries detection using color saturation , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

[4]  Jon Atli Benediktsson,et al.  Advanced directional mathematical morphology for the detection of the road network in very high resolution remote sensing images , 2010, Pattern Recognit. Lett..

[5]  G. Bebis,et al.  On-road vehicle detection using optical sensors: a review , 2004, Proceedings. The 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749).

[6]  Antonio M. López,et al.  Road Detection Based on Illuminant Invariance , 2011, IEEE Transactions on Intelligent Transportation Systems.

[7]  Woojin Chung,et al.  Drivable road region detection using a single laser range finder for outdoor patrol robots , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[8]  Qinghua Wen,et al.  Road Boundary Detection in Complex Urban Environment based on Low-Resolution Vision , 2008 .

[9]  Jae-Soo Cho,et al.  Effective Lane Detection and Tracking Method Using Statistical Modeling of Color and Lane Edge-Orientation , 2009, 2009 Fourth International Conference on Computer Sciences and Convergence Information Technology.

[10]  Dibo Hou,et al.  A Novel Lane Detection Algorithm Based on Support Vector Machine , 2005 .

[11]  Mokhtar M. Hasan,et al.  Improving Morphology Operation for 2D Hole Filling Algorithm , 2012 .

[12]  D. Civco,et al.  Road Extraction Using SVM and Image Segmentation , 2004 .

[13]  M. J. Nigam,et al.  Shadow Detection and Removal from Remote Sensing Images using NDI and Morphological Operators , 2012 .

[14]  Pilar Bachiller Burgos,et al.  Multi-cue visual obstacle detection for mobile robots , 2010 .

[15]  Yann LeCun,et al.  Road Scene Segmentation from a Single Image , 2012, ECCV.