This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Efficient Lane Detection Using Deep Lane Feature Extraction Method

Journal Article
ISSN: 1946-4614, e-ISSN: 1946-4622
Published September 23, 2017 by SAE International in United States
Efficient Lane Detection Using Deep Lane Feature Extraction Method
Citation: Yu, G., Wang, Z., Wu, X., Ma, Y. et al., "Efficient Lane Detection Using Deep Lane Feature Extraction Method," SAE Int. J. Passeng. Cars – Electron. Electr. Syst. 11(1):57-66, 2018,
Language: English


In this paper, an efficient lane detection using deep feature extraction method is proposed to achieve real-time lane detection in diverse road environment. The method contains three main stages: 1) pre-processing, 2) deep lane feature extraction and 3) lane fitting. In pre-processing stage, the inverse perspective mapping (IPM) is used to obtain a bird's eye view of the road image, and then an edge image is generated using the canny operator. In deep lane feature extraction stage, an advanced lane extraction method is proposed. Firstly, line segment detector (LSD) is applied to achieve the fast line segment detection in the IPM image. After that, a proposed adaptive lane clustering algorithm is employed to gather the adjacent line segments generated by the LSD method. Finally, a proposed local gray value maximum cascaded spatial correlation filter (GMSF) algorithm is used to extract the target lane lines among the multiple lines. In lane fitting stage, Kalman filtering is used to improve the accuracy of extraction result, which is followed by RANSAC algorithm, who is applied to fit the extracted lane points to parabolic model. The experimental results illustrate that the proposed algorithm can achieve accurate lane detection under diverse conditions; meanwhile, the average processing rate is 38 fps, which meets the real-time application requirements.