Point cloud segmentation method and device

Point cloud segmentation method and device

The invention provides a point cloud segmentation method and device, and the method comprises the steps: carrying out the local clustering of a point cloud, obtaining a plurality of patches, and constructing a homogeneous graph structure based on the plurality of patches; the homogeneous graph struc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: XIONG BIAO, WANG JIAXIN, ZHU RUISHU
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator XIONG BIAO
WANG JIAXIN
ZHU RUISHU
description The invention provides a point cloud segmentation method and device, and the method comprises the steps: carrying out the local clustering of a point cloud, obtaining a plurality of patches, and constructing a homogeneous graph structure based on the plurality of patches; the homogeneous graph structure comprises a plurality of nodes, node feature embedding vectors and high-dimensional edge features; performing dimension reduction on the high-dimensional edge features based on an auto-encoder to obtain low-dimensional edge features, and constructing a heterogeneous graph structure based on the low-dimensional edge features; the heterogeneous graph structure comprises a plurality of nodes, a plurality of clusters and an edge feature embedding vector of each cluster, and each cluster comprises at least one low-dimensional edge feature; based on the edge feature embedding vector, determining an aggregation node feature of each node; and inputting the aggregated node features into a classifier, determining node t
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117496161A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117496161A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117496161A3</originalsourceid><addsrcrecordid>eNrjZNAKyM_MK1FIzskvTVEoTk3PTc0rSSzJzM9TyE0tychPUUjMS1FISS3LTE7lYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxzn6GhuYmlmaGZoaOxsSoAQAzQCkM</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Point cloud segmentation method and device</title><source>esp@cenet</source><creator>XIONG BIAO ; WANG JIAXIN ; ZHU RUISHU</creator><creatorcontrib>XIONG BIAO ; WANG JIAXIN ; ZHU RUISHU</creatorcontrib><description>The invention provides a point cloud segmentation method and device, and the method comprises the steps: carrying out the local clustering of a point cloud, obtaining a plurality of patches, and constructing a homogeneous graph structure based on the plurality of patches; the homogeneous graph structure comprises a plurality of nodes, node feature embedding vectors and high-dimensional edge features; performing dimension reduction on the high-dimensional edge features based on an auto-encoder to obtain low-dimensional edge features, and constructing a heterogeneous graph structure based on the low-dimensional edge features; the heterogeneous graph structure comprises a plurality of nodes, a plurality of clusters and an edge feature embedding vector of each cluster, and each cluster comprises at least one low-dimensional edge feature; based on the edge feature embedding vector, determining an aggregation node feature of each node; and inputting the aggregated node features into a classifier, determining node t</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240202&amp;DB=EPODOC&amp;CC=CN&amp;NR=117496161A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76419</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240202&amp;DB=EPODOC&amp;CC=CN&amp;NR=117496161A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>XIONG BIAO</creatorcontrib><creatorcontrib>WANG JIAXIN</creatorcontrib><creatorcontrib>ZHU RUISHU</creatorcontrib><title>Point cloud segmentation method and device</title><description>The invention provides a point cloud segmentation method and device, and the method comprises the steps: carrying out the local clustering of a point cloud, obtaining a plurality of patches, and constructing a homogeneous graph structure based on the plurality of patches; the homogeneous graph structure comprises a plurality of nodes, node feature embedding vectors and high-dimensional edge features; performing dimension reduction on the high-dimensional edge features based on an auto-encoder to obtain low-dimensional edge features, and constructing a heterogeneous graph structure based on the low-dimensional edge features; the heterogeneous graph structure comprises a plurality of nodes, a plurality of clusters and an edge feature embedding vector of each cluster, and each cluster comprises at least one low-dimensional edge feature; based on the edge feature embedding vector, determining an aggregation node feature of each node; and inputting the aggregated node features into a classifier, determining node t</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZNAKyM_MK1FIzskvTVEoTk3PTc0rSSzJzM9TyE0tychPUUjMS1FISS3LTE7lYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxzn6GhuYmlmaGZoaOxsSoAQAzQCkM</recordid><startdate>20240202</startdate><enddate>20240202</enddate><creator>XIONG BIAO</creator><creator>WANG JIAXIN</creator><creator>ZHU RUISHU</creator><scope>EVB</scope></search><sort><creationdate>20240202</creationdate><title>Point cloud segmentation method and device</title><author>XIONG BIAO ; WANG JIAXIN ; ZHU RUISHU</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117496161A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>XIONG BIAO</creatorcontrib><creatorcontrib>WANG JIAXIN</creatorcontrib><creatorcontrib>ZHU RUISHU</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>XIONG BIAO</au><au>WANG JIAXIN</au><au>ZHU RUISHU</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Point cloud segmentation method and device</title><date>2024-02-02</date><risdate>2024</risdate><abstract>The invention provides a point cloud segmentation method and device, and the method comprises the steps: carrying out the local clustering of a point cloud, obtaining a plurality of patches, and constructing a homogeneous graph structure based on the plurality of patches; the homogeneous graph structure comprises a plurality of nodes, node feature embedding vectors and high-dimensional edge features; performing dimension reduction on the high-dimensional edge features based on an auto-encoder to obtain low-dimensional edge features, and constructing a heterogeneous graph structure based on the low-dimensional edge features; the heterogeneous graph structure comprises a plurality of nodes, a plurality of clusters and an edge feature embedding vector of each cluster, and each cluster comprises at least one low-dimensional edge feature; based on the edge feature embedding vector, determining an aggregation node feature of each node; and inputting the aggregated node features into a classifier, determining node t</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117496161A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Point cloud segmentation method and device
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T20%3A56%3A07IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=XIONG%20BIAO&rft.date=2024-02-02&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117496161A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true