Model structure, model training method, monomer method, equipment and medium

The invention discloses a model structure, a model training method, a monomer method, equipment and a medium. The model training method comprises the following steps: acquiring original three-dimensional point cloud data of a large-scene ground feature; making the original three-dimensional point cl...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: HE WEI, TAN KECHENG, XU QIANGHONG, LIU HAO, LIU CHENGZHAO
Format: Patent
Sprache:chi ; eng
Schlagworte:
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 HE WEI
TAN KECHENG
XU QIANGHONG
LIU HAO
LIU CHENGZHAO
description The invention discloses a model structure, a model training method, a monomer method, equipment and a medium. The model training method comprises the following steps: acquiring original three-dimensional point cloud data of a large-scene ground feature; making the original three-dimensional point cloud data into a standard sample format file; preprocessing the point cloud sample in the standard sample format file to generate a PKL format sample file; the method comprises the following steps: constructing a large-scene ground feature monomerization model, wherein the large-scene ground feature monomerization model comprises a coding module, a backbone network, a target generation module, a feature fusion module, a Point-RoIAlign module and an instance prediction network; and training the large-scale scene ground feature monomerization model by using the point cloud sample in the PKL format sample file to obtain a trained large-scale scene ground feature monomerization model. According to the method, prediction
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN114882224A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN114882224A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN114882224A3</originalsourceid><addsrcrecordid>eNrjZPDxzU9JzVEoLikqTS4pLUrVUcgFC5QUJWbmZealK-SmlmTkp4CE8_JzU4vg_NTC0syC3NS8EoXEvBSgaEpmaS4PA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTs1LLYl39jM0NLGwMDIyMnE0JkYNAJDsNbE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Model structure, model training method, monomer method, equipment and medium</title><source>esp@cenet</source><creator>HE WEI ; TAN KECHENG ; XU QIANGHONG ; LIU HAO ; LIU CHENGZHAO</creator><creatorcontrib>HE WEI ; TAN KECHENG ; XU QIANGHONG ; LIU HAO ; LIU CHENGZHAO</creatorcontrib><description>The invention discloses a model structure, a model training method, a monomer method, equipment and a medium. The model training method comprises the following steps: acquiring original three-dimensional point cloud data of a large-scene ground feature; making the original three-dimensional point cloud data into a standard sample format file; preprocessing the point cloud sample in the standard sample format file to generate a PKL format sample file; the method comprises the following steps: constructing a large-scene ground feature monomerization model, wherein the large-scene ground feature monomerization model comprises a coding module, a backbone network, a target generation module, a feature fusion module, a Point-RoIAlign module and an instance prediction network; and training the large-scale scene ground feature monomerization model by using the point cloud sample in the PKL format sample file to obtain a trained large-scale scene ground feature monomerization model. According to the method, prediction</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2022</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=20220809&amp;DB=EPODOC&amp;CC=CN&amp;NR=114882224A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220809&amp;DB=EPODOC&amp;CC=CN&amp;NR=114882224A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>HE WEI</creatorcontrib><creatorcontrib>TAN KECHENG</creatorcontrib><creatorcontrib>XU QIANGHONG</creatorcontrib><creatorcontrib>LIU HAO</creatorcontrib><creatorcontrib>LIU CHENGZHAO</creatorcontrib><title>Model structure, model training method, monomer method, equipment and medium</title><description>The invention discloses a model structure, a model training method, a monomer method, equipment and a medium. The model training method comprises the following steps: acquiring original three-dimensional point cloud data of a large-scene ground feature; making the original three-dimensional point cloud data into a standard sample format file; preprocessing the point cloud sample in the standard sample format file to generate a PKL format sample file; the method comprises the following steps: constructing a large-scene ground feature monomerization model, wherein the large-scene ground feature monomerization model comprises a coding module, a backbone network, a target generation module, a feature fusion module, a Point-RoIAlign module and an instance prediction network; and training the large-scale scene ground feature monomerization model by using the point cloud sample in the PKL format sample file to obtain a trained large-scale scene ground feature monomerization model. According to the method, prediction</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZPDxzU9JzVEoLikqTS4pLUrVUcgFC5QUJWbmZealK-SmlmTkp4CE8_JzU4vg_NTC0syC3NS8EoXEvBSgaEpmaS4PA2taYk5xKi-U5mZQdHMNcfbQTS3Ij08tLkhMTs1LLYl39jM0NLGwMDIyMnE0JkYNAJDsNbE</recordid><startdate>20220809</startdate><enddate>20220809</enddate><creator>HE WEI</creator><creator>TAN KECHENG</creator><creator>XU QIANGHONG</creator><creator>LIU HAO</creator><creator>LIU CHENGZHAO</creator><scope>EVB</scope></search><sort><creationdate>20220809</creationdate><title>Model structure, model training method, monomer method, equipment and medium</title><author>HE WEI ; TAN KECHENG ; XU QIANGHONG ; LIU HAO ; LIU CHENGZHAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN114882224A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>HE WEI</creatorcontrib><creatorcontrib>TAN KECHENG</creatorcontrib><creatorcontrib>XU QIANGHONG</creatorcontrib><creatorcontrib>LIU HAO</creatorcontrib><creatorcontrib>LIU CHENGZHAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>HE WEI</au><au>TAN KECHENG</au><au>XU QIANGHONG</au><au>LIU HAO</au><au>LIU CHENGZHAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Model structure, model training method, monomer method, equipment and medium</title><date>2022-08-09</date><risdate>2022</risdate><abstract>The invention discloses a model structure, a model training method, a monomer method, equipment and a medium. The model training method comprises the following steps: acquiring original three-dimensional point cloud data of a large-scene ground feature; making the original three-dimensional point cloud data into a standard sample format file; preprocessing the point cloud sample in the standard sample format file to generate a PKL format sample file; the method comprises the following steps: constructing a large-scene ground feature monomerization model, wherein the large-scene ground feature monomerization model comprises a coding module, a backbone network, a target generation module, a feature fusion module, a Point-RoIAlign module and an instance prediction network; and training the large-scale scene ground feature monomerization model by using the point cloud sample in the PKL format sample file to obtain a trained large-scale scene ground feature monomerization model. According to the method, prediction</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN114882224A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
HANDLING RECORD CARRIERS
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
title Model structure, model training method, monomer method, equipment and medium
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T10%3A48%3A02IST&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=HE%20WEI&rft.date=2022-08-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN114882224A%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