3D point cloud data semantic segmentation method based on deep learning and self-attention

A technology of point cloud data and semantic segmentation, which is applied in image data processing, image analysis, character and pattern recognition, etc., can solve the problem of low segmentation accuracy and achieve the effect of improving accuracy

Active Publication Date: 2019-09-17
XIDIAN UNIV
View PDF6 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to overcome the defects in the above-mentioned prior art, and propose a 3D point cloud data semantic segment

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
  • 3D point cloud data semantic segmentation method based on deep learning and self-attention
  • 3D point cloud data semantic segmentation method based on deep learning and self-attention
  • 3D point cloud data semantic segmentation method based on deep learning and self-attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0032] refer to figure 1 , the present invention comprises the following steps:

[0033] Step 1) Get the training set R 2 and validation set V 2 :

[0034] Step 1a) Get the labeled 3D point cloud data file F from the database: {F 1 ,F 2 ,...,F i ,...,F f ,}, and the ratio is n R The 3D point cloud data file as the initial training set R 0 , the remaining f(1-n R ) 3D point cloud data files as the initial verification set V 0 , F i Indicates the i-th 3D point cloud data file, f is the total number of 3D point cloud data files, f≥100, 0.6≤n R R = 0.8, so that 80% of the 3D point cloud data files will be randomly selected from the database as the initial training set R 0 , and the remaining 20% ​​of the 3D point cloud data files are used as the initial verification set V 0 ;

[0035] Step 1b) Add R 0 Input the PDAL library ...

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 provides a 3D point cloud data semantic segmentation method based on deep learning and a self-attention mechanism, which is used for solving the technical problem of low segmentation precision in the prior art, and comprises the following implementation steps of: (1) obtaining a training set and a verification set; (2) constructing a 3D point cloud data semantic segmentation network of deep learning and a self-attention mechanism; (3) setting a loss function required by the 3D point cloud data semantic segmentation network for training deep learning and a self-attention mechanism; (4) carrying out supervised training on the 3D point cloud data semantic segmentation network of deep learning and a self-attention mechanism; and (5) obtaining a semantic segmentation result of the 3D point cloud data test set. According to the method, the self-attention module is added to the deep learning network, the deep features containing the relations between the feature channels can be better extracted, and therefore the segmentation precision is improved.

Description

technical field [0001] The invention belongs to the technical field of radar 3D point cloud data processing, and relates to a 3D point cloud data segmentation method, in particular to a 3D point cloud data semantic segmentation method based on deep learning and a self-attention mechanism. It can be used in autonomous driving, robotics, 3D maps, land surveying and mapping, foreground segmentation, smart city construction, agricultural production estimation, forest resource census, ecological environment monitoring, disaster prevention and mitigation, etc. Background technique [0002] In recent years, with the development of depth sensors, point cloud processing has become one of the research hotspots. Point cloud data refers to: scanning data is recorded in the form of points, each point contains three-dimensional coordinates, and some may also contain information such as color information, reflection intensity information, gray value, depth or return times. Generally, it i...

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
IPC IPC(8): G06K9/62G06T7/10
CPCG06T7/10G06T2207/10028G06F18/211G06F18/214
Inventor 焦李成李玲玲张杰张格格马清华郭雨薇丁静怡张梦璇程曦娜王佳宁
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap