Three-dimensional point cloud data segmentation method and system based on multi-scale point features

By constructing a three-dimensional hash index table, extracting local maximum values ​​of the density distribution curve, adaptively hierarchical division and identification of noise points, combining three-branch spatial attention network and multi-level geometric feature extraction network, the problem of insensitive density and distribution in point cloud segmentation in the existing technology is solved, and a more accurate and robust point cloud segmentation effect is achieved.

CN119648536AActive Publication Date: 2025-03-18YUNTURING ARTIFICIAL INTELLIGENCE TECHNOLOGY (SUZHOU) CO LTD
5 Cites 27 Cited by

Patent Information

Application Number
CN202411657429.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-19
Publication Date
2025-03-18
Estimated Expiration
2044-11-19

AI Technical Summary

Technical Problem

The prior art has problems in point cloud segmentation that are insensitive to point cloud density and distribution, lack of multi-scale feature representation, and are susceptible to noise and outliers.

Method used

The three-dimensional point cloud data segmentation method based on multi-scale point features is adopted. By constructing a three-dimensional hash index table, calculating point cloud density histogram, extracting local maximum value of the density distribution curve, adaptive hierarchical division, calculating regional density count values ​​and geometric distribution coefficients, identifying and eliminating noise points, building enhanced feature vectors, using three-branch spatial attention networks and multi-level geometric feature extraction networks to extract multi-scale features, and computing propagation features through bidirectional feature propagation networks, and finally segmentation is achieved through segmentation energy functions and variational inference.

Benefits of technology

It improves the quality and reliability of point cloud data, enhances the representation ability and discriminantity of features, achieves more accurate and consistent segmentation results, adapts to segmentation tasks of different scenarios and objects, and has stronger robustness and adaptability.

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

Abstract

The invention provides a three-dimensional point cloud data segmentation method and system based on multi-scale point features, and relates to the technical field of point cloud processing, and the method comprises the steps: obtaining original point cloud data, constructing a three-dimensional Hash index table, carrying out the self-adaptive hierarchical division through a local maximum value of a density distribution curve, and obtaining a local maximum value of a density distribution curve; noise point elimination is carried out based on a region density count value and a geometric distribution coefficient, an enhanced feature vector containing a main feature direction, a main curvature value and the like is constructed for non-eliminated points, a local geometric descriptor is constructed by adopting four spherical search regions with increasing radiuses, a three-branch space attention network is input to extract spatial features, and the spatial features are extracted; and fused feature data are obtained through a multi-level geometric feature extraction network and a bidirectional feature propagation network. And obtaining a final segmentation result through segmentation energy function optimization and a region merging strategy.
Need to check novelty before this filing date? Find Prior Art