Vehicle obstacle avoidance method and device, electronic equipment, and storage medium

Abstract

The invention discloses a vehicle obstacle avoidance method and apparatus, an electronic device and a storage medium. The method comprises steps of obtaining continuous multiple frames of images; determining the motion information of a target object in the images based on the continuous multiple frames of images, and extracting the current pose information of the vehicle; determining the motion information of each pixel in a pixel set corresponding to the current image based on the current image in the continuous multiple frames of images; correcting the current pose information according to the motion information of each pixel in the pixel set; updating the motion information of each pixel based on the corrected pose information and the motion information of the target object to obtain the updated motion information of each pixel; determining dangerous pixels from the pixel set based on the driving space information of the vehicle and the space information of each pixel; and indicating the vehicle to perform obstacle avoidance reaction based on the motion information of the dangerous pixels. The method is advantaged in that more effective obstacle avoidance indication can be obtained by combining the motion information of the target object and the pixel, and safety of the vehicle can be improved.

Description

technical field [0001] The present application relates to the technical field of vehicles, in particular to a vehicle obstacle avoidance method, device, electronic equipment and storage medium. Background technique [0002] In recent years, the autonomous driving industry has flourished, and machine vision has played an important role in providing environmental awareness for autonomous vehicles. Environmental perception generally includes the recognition and detection of regular targets in the environment, including vehicle detection, pedestrian detection, and so on. On the basis of recognition and detection, the position estimation and motion estimation of the detected target are performed to perform collision warning, automatic braking and other obstacle avoidance functions. [0003] In the prior art, only by identifying and classifying easily identifiable target objects, the distance between the target object and the vehicle is determined, and then the distance is used t...

AI Technical Summary

Problems solved by technology

[0003] In the prior art, only by identifying and classifying easily identifiable target objects, the distance between the target object and the vehicle is determined, and then the distance is used to determine whether an obstacle avoidance response is required for the target object. However, in reality, In the process of warning the vehicle, it is not enough to only consider the impact of the target object on the vehicle, and the results obtained are also inaccurate

Images