Obstacle detection method and device based on prior map information and storage medium

Abstract

The invention relates to an obstacle detection method and device based on priori map information and a storage medium. The method comprises: acquiring priori map information of a target road, whereinthe priori map information comprises multiple pieces of priori position information acquired when the unmanned vehicle drives on the target road without obstacles and multiple pieces of priori map picture information corresponding to the priori position information; when the unmanned vehicle runs on a target road, repeatedly executing the following steps: acquiring current position information ofthe unmanned vehicle on the target road and current map picture information corresponding to the current position information; acquiring target prior position information which is the same as the current position information from the prior map information; obtaining target priori map picture information corresponding to the target priori position information from the priori map information; obtaining difference information between the current map picture information and the target prior map picture information; and obtaining feature information of the obstacle based on the difference information.

Description

technical field [0001] The present disclosure belongs to the technical field of image processing, and in particular relates to an obstacle detection method, device and storage medium based on prior map information. Background technique [0002] In recent years, unmanned driving technology has received extensive attention from scholars in various fields. Tesla is the first company to use unmanned driving technology on mass-produced vehicles. It uses cameras and millimeter-wave radar to perceive the surrounding environment. Numerous fatal accidents have demonstrated that solutions are not sufficiently accurate in detecting target obstacles. And lidar can solve this problem very well, so the unmanned solution based on lidar is being favored by more and more scholars. [0003] In the related art, most of the data obtained by lidar is to process a certain frame of point cloud data obtained by the radar to obtain the relevant feature information of obstacles, but for complex scen...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the main purpose of the present disclosure is to provide an obstacle detection method, device and storage medium based on prior map information, which is used to solve the problem of missing or false detection of obstacles in complex scenes in related technologies. technical problem

Images