Road patrol result duplicate removal method based on similarity measurement

The invention provides a road patrol result deduplication method based on similarity measurement, which belongs to the technical field of road engineering, and comprises the following steps: 1, collecting a road patrol result; 2, preprocessing the converted data of the road patrol result; 3, dividin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WU DIFEI, YANG YINGHAO, DU YUCHUAN, LI RUIXU, LI YISHUN, WANG WENXUAN, LIU CHENGLONG, ZHU SHUAI
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 WU DIFEI
YANG YINGHAO
DU YUCHUAN
LI RUIXU
LI YISHUN
WANG WENXUAN
LIU CHENGLONG
ZHU SHUAI
description The invention provides a road patrol result deduplication method based on similarity measurement, which belongs to the technical field of road engineering, and comprises the following steps: 1, collecting a road patrol result; 2, preprocessing the converted data of the road patrol result; 3, dividing the preprocessed data set into a training set and a test set; 4, extracting image features by adopting a twin network model to obtain feature vectors of the input image; 5, calculating the distance between the feature vectors of the input image group to obtain the similarity; 6, dividing a threshold value according to the distribution condition of the similarity in the test set, and determining whether the input picture group is the same disease or not according to the threshold value; 7, gathering and clustering inspection results for multiple times; according to the method, the uniqueness and the accuracy of the road disease data are improved, the road disease patrol result can be provided for a road management
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117893985A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117893985A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117893985A3</originalsourceid><addsrcrecordid>eNrjZPAOyk9MUShILCnKz1EoSi0uzSlRSCktyMlMTixJBQrk5pcl5ijkppZk5KcoJCUWp6Yo5OcpFGfmZuYkFmWWVAKlEotLgepS80p4GFjTEnOKU3mhNDeDoptriLOHbmpBfnxqcUFicmpeakm8s5-hobmFpbGlhamjMTFqAKAnNio</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Road patrol result duplicate removal method based on similarity measurement</title><source>esp@cenet</source><creator>WU DIFEI ; YANG YINGHAO ; DU YUCHUAN ; LI RUIXU ; LI YISHUN ; WANG WENXUAN ; LIU CHENGLONG ; ZHU SHUAI</creator><creatorcontrib>WU DIFEI ; YANG YINGHAO ; DU YUCHUAN ; LI RUIXU ; LI YISHUN ; WANG WENXUAN ; LIU CHENGLONG ; ZHU SHUAI</creatorcontrib><description>The invention provides a road patrol result deduplication method based on similarity measurement, which belongs to the technical field of road engineering, and comprises the following steps: 1, collecting a road patrol result; 2, preprocessing the converted data of the road patrol result; 3, dividing the preprocessed data set into a training set and a test set; 4, extracting image features by adopting a twin network model to obtain feature vectors of the input image; 5, calculating the distance between the feature vectors of the input image group to obtain the similarity; 6, dividing a threshold value according to the distribution condition of the similarity in the test set, and determining whether the input picture group is the same disease or not according to the threshold value; 7, gathering and clustering inspection results for multiple times; according to the method, the uniqueness and the accuracy of the road disease data are improved, the road disease patrol result can be provided for a road management</description><language>chi ; eng</language><subject>CALCULATING ; 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=20240416&amp;DB=EPODOC&amp;CC=CN&amp;NR=117893985A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240416&amp;DB=EPODOC&amp;CC=CN&amp;NR=117893985A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WU DIFEI</creatorcontrib><creatorcontrib>YANG YINGHAO</creatorcontrib><creatorcontrib>DU YUCHUAN</creatorcontrib><creatorcontrib>LI RUIXU</creatorcontrib><creatorcontrib>LI YISHUN</creatorcontrib><creatorcontrib>WANG WENXUAN</creatorcontrib><creatorcontrib>LIU CHENGLONG</creatorcontrib><creatorcontrib>ZHU SHUAI</creatorcontrib><title>Road patrol result duplicate removal method based on similarity measurement</title><description>The invention provides a road patrol result deduplication method based on similarity measurement, which belongs to the technical field of road engineering, and comprises the following steps: 1, collecting a road patrol result; 2, preprocessing the converted data of the road patrol result; 3, dividing the preprocessed data set into a training set and a test set; 4, extracting image features by adopting a twin network model to obtain feature vectors of the input image; 5, calculating the distance between the feature vectors of the input image group to obtain the similarity; 6, dividing a threshold value according to the distribution condition of the similarity in the test set, and determining whether the input picture group is the same disease or not according to the threshold value; 7, gathering and clustering inspection results for multiple times; according to the method, the uniqueness and the accuracy of the road disease data are improved, the road disease patrol result can be provided for a road management</description><subject>CALCULATING</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>eNrjZPAOyk9MUShILCnKz1EoSi0uzSlRSCktyMlMTixJBQrk5pcl5ijkppZk5KcoJCUWp6Yo5OcpFGfmZuYkFmWWVAKlEotLgepS80p4GFjTEnOKU3mhNDeDoptriLOHbmpBfnxqcUFicmpeakm8s5-hobmFpbGlhamjMTFqAKAnNio</recordid><startdate>20240416</startdate><enddate>20240416</enddate><creator>WU DIFEI</creator><creator>YANG YINGHAO</creator><creator>DU YUCHUAN</creator><creator>LI RUIXU</creator><creator>LI YISHUN</creator><creator>WANG WENXUAN</creator><creator>LIU CHENGLONG</creator><creator>ZHU SHUAI</creator><scope>EVB</scope></search><sort><creationdate>20240416</creationdate><title>Road patrol result duplicate removal method based on similarity measurement</title><author>WU DIFEI ; YANG YINGHAO ; DU YUCHUAN ; LI RUIXU ; LI YISHUN ; WANG WENXUAN ; LIU CHENGLONG ; ZHU SHUAI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117893985A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WU DIFEI</creatorcontrib><creatorcontrib>YANG YINGHAO</creatorcontrib><creatorcontrib>DU YUCHUAN</creatorcontrib><creatorcontrib>LI RUIXU</creatorcontrib><creatorcontrib>LI YISHUN</creatorcontrib><creatorcontrib>WANG WENXUAN</creatorcontrib><creatorcontrib>LIU CHENGLONG</creatorcontrib><creatorcontrib>ZHU SHUAI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WU DIFEI</au><au>YANG YINGHAO</au><au>DU YUCHUAN</au><au>LI RUIXU</au><au>LI YISHUN</au><au>WANG WENXUAN</au><au>LIU CHENGLONG</au><au>ZHU SHUAI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Road patrol result duplicate removal method based on similarity measurement</title><date>2024-04-16</date><risdate>2024</risdate><abstract>The invention provides a road patrol result deduplication method based on similarity measurement, which belongs to the technical field of road engineering, and comprises the following steps: 1, collecting a road patrol result; 2, preprocessing the converted data of the road patrol result; 3, dividing the preprocessed data set into a training set and a test set; 4, extracting image features by adopting a twin network model to obtain feature vectors of the input image; 5, calculating the distance between the feature vectors of the input image group to obtain the similarity; 6, dividing a threshold value according to the distribution condition of the similarity in the test set, and determining whether the input picture group is the same disease or not according to the threshold value; 7, gathering and clustering inspection results for multiple times; according to the method, the uniqueness and the accuracy of the road disease data are improved, the road disease patrol result can be provided for a road management</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN117893985A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
PHYSICS
title Road patrol result duplicate removal method based on similarity measurement
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T08%3A11%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=WU%20DIFEI&rft.date=2024-04-16&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117893985A%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