Lane Detection System for Night Scenes Chongqing University of Technology

Format:

Conference/Event

Author/Creator:

Hu, Hu, author.

Contributor:

Chi, Wenchao

Gao, Song

Liu, Junsheng

Shen, Zhiang

Conference Name:

Intelligent and Connected Vehicles Symposium (2018-08-14 : Kunshan City, Jiangsu, China)

Language:

English

Physical Description:

1 online resource

Place of Publication:

Warrendale, PA SAE International 2018

Summary:

Most of algorithms of lane detection mainly aim at the scenes of daytime. However, those algorithms are unstable for the lane detection at night because the camera is very sensitive to the light change. This paper proposed a lane detection algorithm that largely improves the detection system's performance when it is used at night. The algorithm has two main stage: Image processing and Kalman filter (KF). The key process steps of Stage 1 are: extracting the Region of Interesting (ROI)Edge Detection BinarizationHough Lane SelectionLane fitting. First step, a ROI could be extracted according to the relatively fixed location of lanes. In step of edge detection, we use a creative filter named Correlation filter to remove image noise and remain the feature of lane. The filter matrix looks like "[0 1 1, 1 0 1; 1 1 0]". Next, the candidate lines are detected by the Hough transform, then, the equations of lane are acquired by fitting spots obtained from Hough. In Stage 2, we used the Kalman filter to trace the lane, which improving the efficiency and the accuracy of lane detection. In the KF unit, we use an innovative methodthe Deep ROI extraction, to eliminate the mass of disturbances and select which region of current frame needs to be detected. The experiment showed that the method is very effective in clearing distractions. Finally, we test this algorithm on the platform of Matlab. By the way, the test datasets were built by collecting plenty of scenes, including urban roads and highway as well as countryside roads. This algorithm's image processing rate approximately keeps on 13 frames per second and average accuracy of the detection reaches at 96.2%. For further verifying the algorithm, we will code it in C++ and test in a real vehicle

Notes:

Vendor supplied data

Publisher Number:

2018-01-1617

Access Restriction:

Restricted for use by site license