Intelligent terrain recognition method fusing pixel-level image segmentation and reinforcement learning

The invention provides a terrain intelligent identification method fusing pixel-level image segmentation and reinforcement learning, and the method comprises the following steps: S1, building an unstructured BIM three-dimensional terrain model based on a BIM technology by means of a digital three-di...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHEN XINGYUN, CHEN XIANG, WANG XIANRI, CHENG JIANPING, LIU ZHIWEI, CHEN YUANHAO, LI XIAOGANG, LIN JIANHAO, WEI ZHEN, FU BENZHAO, NIE KEJIAN, SHI XIAOLIN, YU XINMIN, LIN RUIZONG
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 CHEN XINGYUN
CHEN XIANG
WANG XIANRI
CHENG JIANPING
LIU ZHIWEI
CHEN YUANHAO
LI XIAOGANG
LIN JIANHAO
WEI ZHEN
FU BENZHAO
NIE KEJIAN
SHI XIAOLIN
YU XINMIN
LIN RUIZONG
description The invention provides a terrain intelligent identification method fusing pixel-level image segmentation and reinforcement learning, and the method comprises the following steps: S1, building an unstructured BIM three-dimensional terrain model based on a BIM technology by means of a digital three-dimensional design platform; classifying the BIM three-dimensional topographic map, arranging topographic edge information tags, and obtaining various types of topographic target data sets; s2, separating and identifying various terrains in a target scene by adopting an image segmentation task type convolutional neural network, and obtaining a terrain segmentation map; and S3, inputting the original image and the terrain segmentation map into a reinforcement learning module, and outputting a finer-grained terrain segmentation map by the evaluation network. And S4, visualizing an algorithm result, and providing an external interface. And the specific terrain condition of the planning area can be analyzed in a finer-gr
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116934773A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116934773A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116934773A3</originalsourceid><addsrcrecordid>eNqNyzEKwkAQheE0FqLeYTxAihAxWIagaGNlH4bkZR2YzIbdVTy-UTyA1YPH_y0zd7EEVXGwRAkhsBgFdN6ZJPFGI9Ld9zQ8opijSV7QXPGEkozsQBFunC1_Y7Z-xmKDDx0-Nyk42CzX2WJgjdj8dpVtT8dbc84x-RZx4g6G1DbXotgfyl1VlXX5T_MGYDNBLg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Intelligent terrain recognition method fusing pixel-level image segmentation and reinforcement learning</title><source>esp@cenet</source><creator>CHEN XINGYUN ; CHEN XIANG ; WANG XIANRI ; CHENG JIANPING ; LIU ZHIWEI ; CHEN YUANHAO ; LI XIAOGANG ; LIN JIANHAO ; WEI ZHEN ; FU BENZHAO ; NIE KEJIAN ; SHI XIAOLIN ; YU XINMIN ; LIN RUIZONG</creator><creatorcontrib>CHEN XINGYUN ; CHEN XIANG ; WANG XIANRI ; CHENG JIANPING ; LIU ZHIWEI ; CHEN YUANHAO ; LI XIAOGANG ; LIN JIANHAO ; WEI ZHEN ; FU BENZHAO ; NIE KEJIAN ; SHI XIAOLIN ; YU XINMIN ; LIN RUIZONG</creatorcontrib><description>The invention provides a terrain intelligent identification method fusing pixel-level image segmentation and reinforcement learning, and the method comprises the following steps: S1, building an unstructured BIM three-dimensional terrain model based on a BIM technology by means of a digital three-dimensional design platform; classifying the BIM three-dimensional topographic map, arranging topographic edge information tags, and obtaining various types of topographic target data sets; s2, separating and identifying various terrains in a target scene by adopting an image segmentation task type convolutional neural network, and obtaining a terrain segmentation map; and S3, inputting the original image and the terrain segmentation map into a reinforcement learning module, and outputting a finer-grained terrain segmentation map by the evaluation network. And S4, visualizing an algorithm result, and providing an external interface. And the specific terrain condition of the planning area can be analyzed in a finer-gr</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2023</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=20231024&amp;DB=EPODOC&amp;CC=CN&amp;NR=116934773A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76419</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20231024&amp;DB=EPODOC&amp;CC=CN&amp;NR=116934773A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN XINGYUN</creatorcontrib><creatorcontrib>CHEN XIANG</creatorcontrib><creatorcontrib>WANG XIANRI</creatorcontrib><creatorcontrib>CHENG JIANPING</creatorcontrib><creatorcontrib>LIU ZHIWEI</creatorcontrib><creatorcontrib>CHEN YUANHAO</creatorcontrib><creatorcontrib>LI XIAOGANG</creatorcontrib><creatorcontrib>LIN JIANHAO</creatorcontrib><creatorcontrib>WEI ZHEN</creatorcontrib><creatorcontrib>FU BENZHAO</creatorcontrib><creatorcontrib>NIE KEJIAN</creatorcontrib><creatorcontrib>SHI XIAOLIN</creatorcontrib><creatorcontrib>YU XINMIN</creatorcontrib><creatorcontrib>LIN RUIZONG</creatorcontrib><title>Intelligent terrain recognition method fusing pixel-level image segmentation and reinforcement learning</title><description>The invention provides a terrain intelligent identification method fusing pixel-level image segmentation and reinforcement learning, and the method comprises the following steps: S1, building an unstructured BIM three-dimensional terrain model based on a BIM technology by means of a digital three-dimensional design platform; classifying the BIM three-dimensional topographic map, arranging topographic edge information tags, and obtaining various types of topographic target data sets; s2, separating and identifying various terrains in a target scene by adopting an image segmentation task type convolutional neural network, and obtaining a terrain segmentation map; and S3, inputting the original image and the terrain segmentation map into a reinforcement learning module, and outputting a finer-grained terrain segmentation map by the evaluation network. And S4, visualizing an algorithm result, and providing an external interface. And the specific terrain condition of the planning area can be analyzed in a finer-gr</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyzEKwkAQheE0FqLeYTxAihAxWIagaGNlH4bkZR2YzIbdVTy-UTyA1YPH_y0zd7EEVXGwRAkhsBgFdN6ZJPFGI9Ld9zQ8opijSV7QXPGEkozsQBFunC1_Y7Z-xmKDDx0-Nyk42CzX2WJgjdj8dpVtT8dbc84x-RZx4g6G1DbXotgfyl1VlXX5T_MGYDNBLg</recordid><startdate>20231024</startdate><enddate>20231024</enddate><creator>CHEN XINGYUN</creator><creator>CHEN XIANG</creator><creator>WANG XIANRI</creator><creator>CHENG JIANPING</creator><creator>LIU ZHIWEI</creator><creator>CHEN YUANHAO</creator><creator>LI XIAOGANG</creator><creator>LIN JIANHAO</creator><creator>WEI ZHEN</creator><creator>FU BENZHAO</creator><creator>NIE KEJIAN</creator><creator>SHI XIAOLIN</creator><creator>YU XINMIN</creator><creator>LIN RUIZONG</creator><scope>EVB</scope></search><sort><creationdate>20231024</creationdate><title>Intelligent terrain recognition method fusing pixel-level image segmentation and reinforcement learning</title><author>CHEN XINGYUN ; CHEN XIANG ; WANG XIANRI ; CHENG JIANPING ; LIU ZHIWEI ; CHEN YUANHAO ; LI XIAOGANG ; LIN JIANHAO ; WEI ZHEN ; FU BENZHAO ; NIE KEJIAN ; SHI XIAOLIN ; YU XINMIN ; LIN RUIZONG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116934773A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHEN XINGYUN</creatorcontrib><creatorcontrib>CHEN XIANG</creatorcontrib><creatorcontrib>WANG XIANRI</creatorcontrib><creatorcontrib>CHENG JIANPING</creatorcontrib><creatorcontrib>LIU ZHIWEI</creatorcontrib><creatorcontrib>CHEN YUANHAO</creatorcontrib><creatorcontrib>LI XIAOGANG</creatorcontrib><creatorcontrib>LIN JIANHAO</creatorcontrib><creatorcontrib>WEI ZHEN</creatorcontrib><creatorcontrib>FU BENZHAO</creatorcontrib><creatorcontrib>NIE KEJIAN</creatorcontrib><creatorcontrib>SHI XIAOLIN</creatorcontrib><creatorcontrib>YU XINMIN</creatorcontrib><creatorcontrib>LIN RUIZONG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN XINGYUN</au><au>CHEN XIANG</au><au>WANG XIANRI</au><au>CHENG JIANPING</au><au>LIU ZHIWEI</au><au>CHEN YUANHAO</au><au>LI XIAOGANG</au><au>LIN JIANHAO</au><au>WEI ZHEN</au><au>FU BENZHAO</au><au>NIE KEJIAN</au><au>SHI XIAOLIN</au><au>YU XINMIN</au><au>LIN RUIZONG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Intelligent terrain recognition method fusing pixel-level image segmentation and reinforcement learning</title><date>2023-10-24</date><risdate>2023</risdate><abstract>The invention provides a terrain intelligent identification method fusing pixel-level image segmentation and reinforcement learning, and the method comprises the following steps: S1, building an unstructured BIM three-dimensional terrain model based on a BIM technology by means of a digital three-dimensional design platform; classifying the BIM three-dimensional topographic map, arranging topographic edge information tags, and obtaining various types of topographic target data sets; s2, separating and identifying various terrains in a target scene by adopting an image segmentation task type convolutional neural network, and obtaining a terrain segmentation map; and S3, inputting the original image and the terrain segmentation map into a reinforcement learning module, and outputting a finer-grained terrain segmentation map by the evaluation network. And S4, visualizing an algorithm result, and providing an external interface. And the specific terrain condition of the planning area can be analyzed in a finer-gr</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116934773A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Intelligent terrain recognition method fusing pixel-level image segmentation and reinforcement learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T00%3A02%3A32IST&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=CHEN%20XINGYUN&rft.date=2023-10-24&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116934773A%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