A point cloud matching method and device, electronic equipment and storage medium
By deleting scan points that do not meet the direction matching conditions during point cloud matching, the problem of mismatching scan points on different surfaces of the same object by the ICP algorithm is solved, resulting in more accurate map data and location positioning.
CN116310445BActive Publication Date: 2026-06-23AUTONAVI SOFTWARE CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- AUTONAVI SOFTWARE CO LTD
- Filing Date
- 2023-03-31
- Publication Date
- 2026-06-23
AI Technical Summary
Technical Problem
Existing point cloud matching algorithms, such as ICP, may identify scan points on different surfaces of the same object as the same scan point when collecting point clouds multiple times, resulting in point cloud matching position offset and affecting the accuracy of high-precision maps and vehicle positioning.
Method used
By acquiring point cloud data collected by LiDAR at different times, the system finds scanning points with matching positions and calculates their directions. If the direction matching condition is not met, the scanning points are deleted as noise, and the ICP algorithm is used for matching.
Benefits of technology
It improves the accuracy of point cloud matching, ensuring the precision of the generated map data and location information.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN116310445B_ABST
Abstract
The application provides a point cloud matching method, a map data generation method, a position positioning method, a device, an electronic device and a storage medium. According to the embodiment of the application, the first point cloud data and the second point cloud data collected by the laser radar at different times for the entity object are obtained as the point cloud data to be matched, then the second scanning point having a position matching relationship with the first scanning point in the first point cloud data is searched in the second point cloud data, the scanning point directions corresponding to the first scanning point and the second scanning point are obtained, finally, whether the scanning point directions corresponding to the first scanning point and the second scanning point satisfy the direction matching condition is determined, and if the direction matching condition is not satisfied, the first scanning point is deleted from the first point cloud data as a noise point. The above scheme can effectively delete the noise point in the point cloud matching process, so that the point cloud matching result is more accurate, and the generated map data and position positioning information are more accurate.
Need to check novelty before this filing date? Find Prior Art