Decision information acquisition method and device, terminal and storage medium

Abstract

The invention provides a decision information acquisition method and device, a terminal and a storage medium, and belongs to the field of automatic driving. The method comprises the following steps: acquiring a road image shot by a current vehicle in a driving process; in the road image, a first target area and lane line information are determined, the first target area is a non-driving area in the road image, and the lane line information is used for indicating each lane line in the road image; and determining decision information based on the lane line information and the first target area. According to the scheme, the first target area and the lane line information are determined from the road image shot in the current vehicle driving process, the position of the lane line on the road in the road image can be determined, the driving environment around the current vehicle can be determined based on the lane line and the non-driving area, and then the decision information is determined; therefore, the current vehicle is controlled to effectively avoid the obstacles on the road according to the decision information, and the control efficiency of the vehicle is improved.

Description

technical field [0001] The present application relates to the field of automatic driving, and in particular to a method, device, terminal and storage medium for acquiring decision information. Background technique [0002] With the development of driverless technology, driverless cars have been able to handle most traffic scenarios. However, in the process of automatic driving of the current vehicle, the game between the current vehicle and the obstacles on the lane is ubiquitous. Therefore, it is a very important research direction to detect and predict obstacles to control the safe driving of the current vehicle. [0003] At present, when detecting obstacles, the obstacles are usually simplified into a bounding box. This detection method ignores the actual shape of the obstacle, which will lead to inaccurate detection results and missed detection, which will affect the control decision of the current vehicle and cannot control the current vehicle to avoid obstacles effec...

AI Technical Summary

Problems solved by technology

This detection method ignores the actual shape of the obstacle, which will lead to inaccurate detection results and missed detection, which will affect the control decision of the current vehicle and cannot control the current vehicle to effectively avoid obstacles.

Images