Lightweight road defect detection method based on dynamic deformable attention mechanism
The invention discloses a lightweight road defect detection method based on a dynamic deformable attention mechanism. The lightweight road defect detection method comprises the following steps: selecting an open road defect data set containing longitudinal cracks, transverse cracks, net cracks and p...
Gespeichert in:
Hauptverfasser: | , , , , |
---|---|
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 | ZHANG DONGPING HU HAIMIAO LI ZHENG BU YUZHEN HE SHUJI |
description | The invention discloses a lightweight road defect detection method based on a dynamic deformable attention mechanism. The lightweight road defect detection method comprises the following steps: selecting an open road defect data set containing longitudinal cracks, transverse cracks, net cracks and pits as a training set, a verification set and a test set; building a lightweight road defect detection neural network model based on a dynamic deformable attention mechanism, using dynamic deformable convolution to improve the feature extraction capability of the network, and using a lightweight module to reduce the complexity of the whole network; training a road defect detection neural network model by using the training set and the verification set, storing weight parameters, performing final evaluation on the model under the weight parameter with the highest detection accuracy by using the test set, and finally determining the road defect detection model with the highest detection accuracy on the test set as an |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118279562A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118279562A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118279562A3</originalsourceid><addsrcrecordid>eNrjZIjwyUzPKClPBZEKRfmJKQopqWmpySVAqgRIZebnKeSmlmTkpygkJRanpigA-SmVeYm5mckghflFuYlJOakKiSUlqXlQxckZiXmZxbk8DKxpiTnFqbxQmptB0c01xNlDN7UgPz61uCAxOTUvtSTe2c_Q0MLI3NLUzMjRmBg1AM0sOr8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Lightweight road defect detection method based on dynamic deformable attention mechanism</title><source>esp@cenet</source><creator>ZHANG DONGPING ; HU HAIMIAO ; LI ZHENG ; BU YUZHEN ; HE SHUJI</creator><creatorcontrib>ZHANG DONGPING ; HU HAIMIAO ; LI ZHENG ; BU YUZHEN ; HE SHUJI</creatorcontrib><description>The invention discloses a lightweight road defect detection method based on a dynamic deformable attention mechanism. The lightweight road defect detection method comprises the following steps: selecting an open road defect data set containing longitudinal cracks, transverse cracks, net cracks and pits as a training set, a verification set and a test set; building a lightweight road defect detection neural network model based on a dynamic deformable attention mechanism, using dynamic deformable convolution to improve the feature extraction capability of the network, and using a lightweight module to reduce the complexity of the whole network; training a road defect detection neural network model by using the training set and the verification set, storing weight parameters, performing final evaluation on the model under the weight parameter with the highest detection accuracy by using the test set, and finally determining the road defect detection model with the highest detection accuracy on the test set as an</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&date=20240702&DB=EPODOC&CC=CN&NR=118279562A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,777,882,25545,76296</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240702&DB=EPODOC&CC=CN&NR=118279562A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG DONGPING</creatorcontrib><creatorcontrib>HU HAIMIAO</creatorcontrib><creatorcontrib>LI ZHENG</creatorcontrib><creatorcontrib>BU YUZHEN</creatorcontrib><creatorcontrib>HE SHUJI</creatorcontrib><title>Lightweight road defect detection method based on dynamic deformable attention mechanism</title><description>The invention discloses a lightweight road defect detection method based on a dynamic deformable attention mechanism. The lightweight road defect detection method comprises the following steps: selecting an open road defect data set containing longitudinal cracks, transverse cracks, net cracks and pits as a training set, a verification set and a test set; building a lightweight road defect detection neural network model based on a dynamic deformable attention mechanism, using dynamic deformable convolution to improve the feature extraction capability of the network, and using a lightweight module to reduce the complexity of the whole network; training a road defect detection neural network model by using the training set and the verification set, storing weight parameters, performing final evaluation on the model under the weight parameter with the highest detection accuracy by using the test set, and finally determining the road defect detection model with the highest detection accuracy on the test set as an</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>eNrjZIjwyUzPKClPBZEKRfmJKQopqWmpySVAqgRIZebnKeSmlmTkpygkJRanpigA-SmVeYm5mckghflFuYlJOakKiSUlqXlQxckZiXmZxbk8DKxpiTnFqbxQmptB0c01xNlDN7UgPz61uCAxOTUvtSTe2c_Q0MLI3NLUzMjRmBg1AM0sOr8</recordid><startdate>20240702</startdate><enddate>20240702</enddate><creator>ZHANG DONGPING</creator><creator>HU HAIMIAO</creator><creator>LI ZHENG</creator><creator>BU YUZHEN</creator><creator>HE SHUJI</creator><scope>EVB</scope></search><sort><creationdate>20240702</creationdate><title>Lightweight road defect detection method based on dynamic deformable attention mechanism</title><author>ZHANG DONGPING ; HU HAIMIAO ; LI ZHENG ; BU YUZHEN ; HE SHUJI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118279562A3</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>ZHANG DONGPING</creatorcontrib><creatorcontrib>HU HAIMIAO</creatorcontrib><creatorcontrib>LI ZHENG</creatorcontrib><creatorcontrib>BU YUZHEN</creatorcontrib><creatorcontrib>HE SHUJI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG DONGPING</au><au>HU HAIMIAO</au><au>LI ZHENG</au><au>BU YUZHEN</au><au>HE SHUJI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Lightweight road defect detection method based on dynamic deformable attention mechanism</title><date>2024-07-02</date><risdate>2024</risdate><abstract>The invention discloses a lightweight road defect detection method based on a dynamic deformable attention mechanism. The lightweight road defect detection method comprises the following steps: selecting an open road defect data set containing longitudinal cracks, transverse cracks, net cracks and pits as a training set, a verification set and a test set; building a lightweight road defect detection neural network model based on a dynamic deformable attention mechanism, using dynamic deformable convolution to improve the feature extraction capability of the network, and using a lightweight module to reduce the complexity of the whole network; training a road defect detection neural network model by using the training set and the verification set, storing weight parameters, performing final evaluation on the model under the weight parameter with the highest detection accuracy by using the test set, and finally determining the road defect detection model with the highest detection accuracy on the test set as an</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN118279562A |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
title | Lightweight road defect detection method based on dynamic deformable attention mechanism |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-19T01%3A32%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=ZHANG%20DONGPING&rft.date=2024-07-02&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118279562A%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 |