Semantic contour-based vehicle positioning method and device, equipment and storage medium

The invention relates to the field of intelligent driving, and discloses a semantic contour-based vehicle positioning method and device, equipment and a storage medium. The method comprises the steps that an initial prior pose and ground prior information of a vehicle are acquired, a target road ima...

Full description

Saved in:
Bibliographic Details
Main Authors HAN XU, QIAN CHENGLONG
Format Patent
LanguageChinese
English
Published 26.05.2023
Subjects
CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:The invention relates to the field of intelligent driving, and discloses a semantic contour-based vehicle positioning method and device, equipment and a storage medium. The method comprises the steps that an initial prior pose and ground prior information of a vehicle are acquired, a target road image is collected, and the target road image comprises at least one lane mark; extracting a semantic contour image of each lane mark in the target road image, and calculating initial feature depth information of each semantic contour image according to ground prior information; constructing a target optimization function, and optimizing the initial feature depth information of each semantic contour image and the initial prior pose of the vehicle based on the target optimization function; and based on the target feature depth information of each semantic contour image obtained after optimization and the target prior pose of the vehicle, constructing an SLAM map to determine the position of the vehicle. According to th
Bibliography:Application Number: CN202211476420