Point cloud detection method and device, computer equipment and storage medium

Abstract

The embodiment of the invention discloses a point cloud detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring multiple frames of point clouds and multiple frames of original image data which face the same visual range and are acquired at the same time; respectively projecting the multiple frames of point clouds onto the multiple frames of original image data to obtain multiple frames of target image data; performing semantic segmentation on point clouds and pixel points in the target image data according to the time sequence relationship among the multiple frames of target image data so as to identify the semantic information of the pixel points for the obstacle; and endowing the semantic information of the pixel points with point clouds corresponding to the pixel points. The visual features of the image data are combined with the spatial features of the point cloud, the target image data not only contains rich color features and texture features, but also contains the coordinates of the point cloud, the laser intensity and other features, the dimensionality of the features is greatly enriched, and semantic segmentation is carried out by considering the time sequence between frames, so that the accuracy of semantic information of an obstacle is improved.

Description

technical field [0001] Embodiments of the present invention relate to environment sensing technology, and in particular to a point cloud detection method, device, computer equipment and storage medium. Background technique [0002] In scenarios such as automatic driving of vehicles and automatic inspection of robots, lidar, as a commonly used sensor, can detect point clouds of the surrounding environment to identify obstacles. [0003] The point cloud detected by lidar is relatively sparse and has a lot of noise. Each point cloud contains information such as laser intensity and coordinates. Problems such as wrong categories, for example, confusing people with pillars, and misidentifying noise generated by dust, water splashes, flying insects, etc. as obstacles. Contents of the invention [0004] Embodiments of the present invention provide a point cloud detection method, device, computer equipment, and storage medium to solve the problems of less information and more nois...

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a point cloud detection method, device, computer equipment, and storage medium to solve the problems of less information and more noise in point clouds

Images