Obstacle detection method, device, vehicle, computer equipment and storage medium

Abstract

The invention discloses an obstacle detection method, device, vehicle, computer equipment and computer-readable storage medium. Wherein, the method includes: acquiring the first frame of image and the second frame of image captured by the image acquisition device for the same scene; determining all the pixels in the first frame of image as points on the ground of the road, and obtaining the ground depth of the scene Image; based on the camera pose changes between frames, project the ground depth image onto the second frame image; generate a distorted image based on the projected ground depth image and the second frame image; detect the depth information in the distorted image and determine obstacles in the scene. Thereby solving the technical problem that the image detection algorithm of a single image cannot detect accurate depth information, and the image detection method of multi-camera is affected by the inaccurate matching of image features of multiple images, which affects the accuracy of detection results.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to an obstacle detection method, device, vehicle, computer equipment and computer-readable storage medium. Background technique [0002] In the field of autonomous driving, obstacle detection in images is one of the most important algorithms, which helps autonomous vehicles model the environment and influences the decision-making of downstream control modules. In related technologies, there are two methods of image obstacle detection for automatic driving: the first method can use a single image to detect obstacles using monocular vision detection or tracking algorithms; the second method can use Multi-cameras take multiple pictures, perform a matching algorithm on each pixel in the multiple pictures, and calculate the depth of obstacles, so as to achieve a general obstacle detection effect. [0003] However, the current problem is that the image detection algorit...

AI Technical Summary

Problems solved by technology

This method can solve the technical problem that the image detection algorithm of a single image cannot detect accurate depth information in the prior art, and the detection method of multi-camera is affected by the inaccurate matching of image features of multiple images, which affects the accuracy of detection results.

Images