Road extraction algorithm based on intrinsic image and vanishing point for unstructured road image

Abstract Road region extraction is one of the key technologies to support the safe operation of vehicle intelligent system. Aiming at the current demands and difficulties of extracting unstructured roads in the field, a new road extraction algorithm based on vanishing point location is proposed in this paper. Based on the improvement of the vanishing point detection method with road border region estimation, the proposed method comprehends the spatial structure of the road image, and combines the color and edge information of the intrinsic image which extracted based on regression analysis. Then the road region can be extracted. The proposed method makes full use of the intermediate information in calculation process to improve the computational efficiency while ensuring the accuracy of the result. Besides, the algorithm performs well for road images under different environments.

[1]  Li Bai,et al.  Robust Road Modeling and Tracking Using Condensation , 2008, IEEE Transactions on Intelligent Transportation Systems.

[2]  Yong Li,et al.  Fast vanishing point detection method based on road border region estimation , 2018, IET Image Process..

[3]  Theo Gevers,et al.  Combining Priors, Appearance, and Context for Road Detection , 2014, IEEE Transactions on Intelligent Transportation Systems.

[4]  Bo Zhang,et al.  Color-based road detection in urban traffic scenes , 2004, IEEE Transactions on Intelligent Transportation Systems.

[5]  Yong Li,et al.  Road detection algorithm for Autonomous Navigation Systems based on dark channel prior and vanishing point in complex road scenes , 2016, Robotics Auton. Syst..

[6]  Wen-hui Zuo,et al.  Road model prediction based unstructured road detection , 2013, Journal of Zhejiang University SCIENCE C.

[7]  Honghai Liu,et al.  Efficient vanishing point detection method in unstructured road environments based on dark channel prior , 2016, IET Comput. Vis..

[8]  Hui Kong,et al.  Generalizing Laplacian of Gaussian Filters for Vanishing-Point Detection , 2013, IEEE Transactions on Intelligent Transportation Systems.

[9]  Jinxiang Wang,et al.  Fast and Robust Vanishing Point Detection for Unstructured Road Following , 2016, IEEE Transactions on Intelligent Transportation Systems.

[10]  Yuan Yan Tang,et al.  Fast and accurate vanishing point detection in complex scenes , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[11]  N. Otsu A threshold selection method from gray level histograms , 1979 .

[12]  Ronen Lerner,et al.  Recent progress in road and lane detection: a survey , 2012, Machine Vision and Applications.

[13]  Dawei Zhao,et al.  Monocular Road Detection Using Structured Random Forest , 2016 .