Point cloud scene semantic instance joint segmentation method based on adaptive feature fusion

By constructing the LPR-AFFN network, which combines the Local Polar Coordinate Representation Module (LPR), the Feature Representation Module (GPM), and the Adaptive Feature Fusion Module (AFF), the problem of insufficient local and global context awareness in 3D point cloud segmentation is solved, and more efficient point cloud segmentation results are achieved.

CN116758287BActive Publication Date: 2025-12-05XIAN UNIV OF TECH
1 Cites 0 Cited by

Patent Information

Application Number
CN202310779043.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-06-29
Publication Date
2025-12-05
Estimated Expiration
2043-06-29

AI Technical Summary

Technical Problem

Existing deep learning-based 3D point cloud instance segmentation methods have poor local and global context awareness in complex scenes, making it difficult to achieve accurate and efficient point cloud segmentation.

Method used

A joint segmentation method for point cloud scene semantic instances based on adaptive feature fusion is adopted. By constructing an LPR-AFFN network, combining the local polar coordinate representation module (LPR), the feature representation module (GPM), and the adaptive feature fusion module (AFF), local and global feature information is integrated to improve segmentation accuracy.

Benefits of technology

It improves the ability to perceive local contextual features, integrates instance and semantic information, enriches global perception capabilities, and enhances the accuracy and efficiency of point cloud segmentation.

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

Abstract

The application discloses a point cloud scene semantic instance joint segmentation method based on adaptive feature fusion, and specifically comprises the following steps: constructing an LPR-AFFN network; constructing a local polar representation module LPR, and performing LPR operation on the original point cloud; performing coordinate conversion according to Z-axis rotation invariance, calculating a neighborhood centroid point matrix, updating a polar angle, and combining the polar coordinates, geometric distances and original point cloud information to obtain a feature matrix; constructing a feature representation module, inputting the feature matrix into the feature representation module, defining a local centroid point, finding the neighborhood points of the centroid point to construct a local group; preliminarily performing feature extraction on the input point cloud; constructing a feature extraction module, obtaining new discriminative features after the extracted features pass through the feature extraction module; and constructing an adaptive feature fusion module, and using the adaptive feature fusion module to integrate the new discriminative feature information to construct the global perception ability of the point cloud.
Need to check novelty before this filing date? Find Prior Art