Open AccessVehicle Pose Estimation Method for Lane Line Detection Through Monocular Camera
Author(s) -
Xingxing Li,
Chao Duan,
Zhi Yan,
Panpan Yin,
Ningxing Wang
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/769/4/042012
Subject(s) - computer vision , artificial intelligence , homography , sobel operator , line (geometry) , computer science , position (finance) , vanishing point , affine transformation , hough transform , edge detection , frame (networking) , monocular , point (geometry) , enhanced data rates for gsm evolution , image (mathematics) , mathematics , image processing , telecommunications , statistics , geometry , projective test , finance , projective space , pure mathematics , economics
Lane detection algorithm is widely used in the field of driverless. In this paper, a lane detection method is proposed to estimate the vehicle’s driving position and attitude. Firstly, a frame of image is transmitted from monocular camera. In this paper, each frame image is pre-processed. After Sobel edge detection, the x-direction edge features of the single frame image are obtained. Then, the region of interest in the image is demarcated, and the line segment in the image is found through Hough transform, and the line ends are filtered, and two are selected respectively for vehicle calculation According to the position line and angle line of pose, the current angle of the camera is calculated by vanishing point, and then the homography matrix is obtained by using the external parameters of the camera, and the image is affine transformed, and the current position of the monocular camera is finally obtained.