A point cloud data processing method and device, electronic equipment, and storage medium

By processing data synchronously from the camera and LiDAR, a dense fused point cloud is generated, which solves the problem of insufficient accuracy in detecting small objects at long distances by LiDAR and improves the accuracy of obstacle detection.

CN115661014BActive Publication Date: 2026-06-12ZHIDAO NETWORK TECH (BEIJING) CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ZHIDAO NETWORK TECH (BEIJING) CO LTD
Filing Date
2022-11-07
Publication Date
2026-06-12

AI Technical Summary

⚠Technical Problem

LiDAR has insufficient ability to perceive objects at long distances, especially for small objects at long distances, resulting in sparse point clouds of obstacles.

⚗Method used

By synchronizing images acquired by a camera with the original point cloud acquired by a LiDAR in time and space, virtual points are generated using depth information and fused with the original point cloud to generate a dense fused point cloud.

🎯Benefits of technology

It improves the ability of lidar to perceive objects at a distance, solves the problem of sparse point clouds for small objects at a distance, and improves the accuracy of obstacle detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115661014B_ABST
    Figure CN115661014B_ABST
Patent Text Reader

Abstract

The application discloses a point cloud data processing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring an image through a camera and acquiring an original point cloud through a laser radar, the original point cloud being spatiotemporally synchronized with the image; acquiring a region of each target object in the image; generating a plurality of virtual points in the region of each target object; acquiring depth information corresponding to each virtual point by using depth information of the original point cloud; and fusing the virtual points with the acquired depth information and the original point cloud to obtain a fused point cloud. The technical scheme can effectively solve the problem of point cloud sparseness of small objects at a long distance and improve the perception ability of the laser radar for objects at a long distance.
Need to check novelty before this filing date? Find Prior Art