Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Three-dimensional point cloud semantic segmentation method based on multi-neighborhood features of hybrid model

A technology of neighborhood features and semantic segmentation, applied in neural learning methods, biological neural network models, character and pattern recognition, etc., can solve problems such as poor robustness, and achieve autonomous high robustness 3D point cloud semantic segmentation prediction model Effect

Pending Publication Date: 2022-03-25
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above-mentioned deficiencies in the prior art, a 3D point cloud semantic segmentation method based on hybrid model multi-neighborhood features provided by the present invention solves the robustness of a single model based on traditional or deep learning in the 3D point cloud semantic segmentation method. poor problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Three-dimensional point cloud semantic segmentation method based on multi-neighborhood features of hybrid model
  • Three-dimensional point cloud semantic segmentation method based on multi-neighborhood features of hybrid model
  • Three-dimensional point cloud semantic segmentation method based on multi-neighborhood features of hybrid model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Such as figure 1 As shown, in one embodiment of the present invention, a kind of 3D point cloud semantic segmentation method based on mixed model multi-neighborhood feature, comprises the following steps:

[0056] S1. Collect point cloud data in three-dimensional space through laser radar, and extract features from the point cloud data to obtain global features of the point cloud, single point features and intermediate features of the network layer;

[0057] S2. Clustering the point cloud data through a clustering algorithm, saving the point indexes in each cluster point subset, and obtaining the intermediate feature cluster subset of the network layer through index classification;

[0058] S3. Perform feature mapping on the intermediate feature cluster subsets of the network layer to obtain high-dimensional multi-neighborhood features corresponding to the intermediate feature cluster subsets of each network layer;

[0059] S4. Splicing and merging point cloud global f...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a three-dimensional point cloud semantic segmentation method based on multi-neighborhood features of a hybrid model, solves the problem that a single model based on traditional or deep learning is poor in robustness in the three-dimensional point cloud semantic segmentation method, and fully realizes the mining of the relation between neighborhood points of point cloud data by a clustering algorithm. A deep learning network for effectively processing point cloud data is constructed to extract abundant point data features, and finally semantic segmentation of the three-dimensional point cloud is accurately and robustly realized.

Description

technical field [0001] The invention belongs to the technical field of three-dimensional point cloud recognition, and in particular relates to a three-dimensional point cloud semantic segmentation method based on mixed model multi-neighborhood features. Background technique [0002] In recent years, with the rapid development of IoT-related applications, the demand for scene understanding-based services has skyrocketed, which makes the demand for high-precision scene recognition and scene semantic segmentation increasingly urgent. A stable, accurate, and lightweight scene understanding system is an important guarantee for realizing IoT applications such as unmanned driving, robot control, virtual reality (VR) and 3D reconstruction. [0003] Among the various existing scene understanding technologies, 3D point cloud semantic segmentation technology is one of the important research tasks. The goal of 3D point cloud semantic segmentation technology is to distinguish the bounda...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06V10/762G06V10/764G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/23213G06F18/24
Inventor 肖卓凌宋濡君何汉覃昊洁阎波
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com