Three-dimensional point cloud segmentation method and system based on bidirectional fusion of point cloud and aerial view

By designing the BEV-point cloud joint encoder and bidirectional fusion attention module, the problems of missing information and insufficient accuracy in 3D point cloud segmentation are solved, and efficient and high-precision 3D point cloud segmentation is achieved, which is suitable for autonomous driving and intelligent monitoring.

CN120783050APending Publication Date: 2025-10-14BEIJING JIAOTONG UNIV +1
0 Cites 2 Cited by

Patent Information

Application Number
CN202510890844.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-30
Publication Date
2025-10-14

AI Technical Summary

Technical Problem

Existing 3D point cloud segmentation methods have a contradiction between computational efficiency and accuracy. In particular, the bird's-eye view-based methods suffer from information compression and structural distortion during the projection process, resulting in poor segmentation accuracy and making it difficult to meet the needs of real-time autonomous driving and intelligent monitoring.

Method used

A BEV-point cloud joint encoder is designed to achieve bidirectional fusion of point cloud and bird's-eye view through feature projection and back-projection operations. Combined with the bidirectional fusion attention module and multi-loss supervision mechanism, the interaction and fusion of point cloud and bird's-eye view features are improved, thereby enhancing the segmentation accuracy and boundary perception ability of the model.

Benefits of technology

While ensuring efficient inference speed, it greatly improves segmentation accuracy, especially the recognition ability of small objects and boundary areas, making it suitable for real-time autonomous driving and intelligent monitoring systems.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a three-dimensional point cloud segmentation method and system based on bidirectional fusion of a point cloud and an aerial view, and belongs to the technical field of three-dimensional scene environment perception, and the method comprises the steps: obtaining to-be-segmented original point cloud data; processing the obtained original point cloud data by using a pre-trained segmentation model to obtain a segmentation result; wherein the segmentation model comprises an encoder module, a backbone network and a fusion segmentation head. According to the method, a bidirectional fusion mechanism of the point cloud and the aerial view is provided, through interactive fusion of the point cloud and the BEV features in multiple stages, the expression ability of the model for local and global features is improved, the problems of fuzzy semantic boundary, difficulty in small target recognition and the like are remarkably improved, and the segmentation precision is obviously superior to that of an existing BEV method. Compared with a voxel method and a multi-representation fusion method, the method has the advantages that the weight of a calculation graph is kept light in structural design, compared with the voxel method and the multi-representation fusion method, the method has remarkable advantages in the aspects of parameter quantity and reasoning speed, precision and real-time performance are better considered, and the method is suitable for scenes with extremely high efficiency requirements such as automatic driving.
Need to check novelty before this filing date? Find Prior Art