Obstacle detection method and device, electronic equipment and storage medium

Abstract

This disclosure presents an obstacle detection method, apparatus, electronic device, and storage medium, relating to the field of artificial intelligence, particularly to intelligent transportation, autonomous driving, and vehicle-road cooperative technologies. The specific solution involves: performing obstacle detection on a currently acquired image to determine a first dataset corresponding to the obstacles in the image, wherein the first dataset contains the two-dimensional coordinates corresponding to multiple first key points; determining a second dataset corresponding to the obstacles based on a transformation equation and the first dataset, wherein the second dataset contains the initial three-dimensional coordinates of each first key point and the initial three-dimensional coordinates of at least one second key point; determining a search area based on the second dataset; and searching for the three-dimensional coordinate values ​​of obstacles within the search area based on a preset loss function, thereby improving the reliability and accuracy of obstacle detection.

Images