Road surface pit detection method and readable storage medium
The invention provides a pavement pit detection method and a readable storage medium. The pavement pothole detection method comprises the following steps: acquiring a binocular image; the binocular image obtains a parallax estimation result based on a parallax estimation algorithm; the binocular ima...
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 | SU JIANYE SUN LIN LIU PENG LIN WANGCHENG YING DONGPING ZHANG CAN LU WEIJIA |
| description | The invention provides a pavement pit detection method and a readable storage medium. The pavement pothole detection method comprises the following steps: acquiring a binocular image; the binocular image obtains a parallax estimation result based on a parallax estimation algorithm; the binocular image obtains a pavement segmentation result based on a pavement segmentation algorithm; and obtaining a pavement pothole detection result based on the parallax estimation result and the pavement segmentation result. Wherein the parallax estimation algorithm and the pavement segmentation algorithm at least share one part of the neural network. Through the configuration, on one hand, the problems of training data and application thresholds are solved through binocular images, on the other hand, through the shared neural network, the two algorithms can share intermediate data in the training and calculation process, the training and calculation speed is increased, and the overall size of the neural network participating |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116645335A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116645335A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116645335A3</originalsourceid><addsrcrecordid>eNrjZLANyk9MUSguLUpLTE5VKMgsUUhJLUlNLsnMz1PITS3JyE9RSMxLUShKTUxJTMpJVSguyS9KTE8FyqVklubyMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4gKgmXmpJfHOfoaGZmYmpsbGpo7GxKgBAAVGL_0</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Road surface pit detection method and readable storage medium</title><source>esp@cenet</source><creator>SU JIANYE ; SUN LIN ; LIU PENG ; LIN WANGCHENG ; YING DONGPING ; ZHANG CAN ; LU WEIJIA</creator><creatorcontrib>SU JIANYE ; SUN LIN ; LIU PENG ; LIN WANGCHENG ; YING DONGPING ; ZHANG CAN ; LU WEIJIA</creatorcontrib><description>The invention provides a pavement pit detection method and a readable storage medium. The pavement pothole detection method comprises the following steps: acquiring a binocular image; the binocular image obtains a parallax estimation result based on a parallax estimation algorithm; the binocular image obtains a pavement segmentation result based on a pavement segmentation algorithm; and obtaining a pavement pothole detection result based on the parallax estimation result and the pavement segmentation result. Wherein the parallax estimation algorithm and the pavement segmentation algorithm at least share one part of the neural network. Through the configuration, on one hand, the problems of training data and application thresholds are solved through binocular images, on the other hand, through the shared neural network, the two algorithms can share intermediate data in the training and calculation process, the training and calculation speed is increased, and the overall size of the neural network participating</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&date=20230825&DB=EPODOC&CC=CN&NR=116645335A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230825&DB=EPODOC&CC=CN&NR=116645335A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SU JIANYE</creatorcontrib><creatorcontrib>SUN LIN</creatorcontrib><creatorcontrib>LIU PENG</creatorcontrib><creatorcontrib>LIN WANGCHENG</creatorcontrib><creatorcontrib>YING DONGPING</creatorcontrib><creatorcontrib>ZHANG CAN</creatorcontrib><creatorcontrib>LU WEIJIA</creatorcontrib><title>Road surface pit detection method and readable storage medium</title><description>The invention provides a pavement pit detection method and a readable storage medium. The pavement pothole detection method comprises the following steps: acquiring a binocular image; the binocular image obtains a parallax estimation result based on a parallax estimation algorithm; the binocular image obtains a pavement segmentation result based on a pavement segmentation algorithm; and obtaining a pavement pothole detection result based on the parallax estimation result and the pavement segmentation result. Wherein the parallax estimation algorithm and the pavement segmentation algorithm at least share one part of the neural network. Through the configuration, on one hand, the problems of training data and application thresholds are solved through binocular images, on the other hand, through the shared neural network, the two algorithms can share intermediate data in the training and calculation process, the training and calculation speed is increased, and the overall size of the neural network participating</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>eNrjZLANyk9MUSguLUpLTE5VKMgsUUhJLUlNLsnMz1PITS3JyE9RSMxLUShKTUxJTMpJVSguyS9KTE8FyqVklubyMLCmJeYUp_JCaW4GRTfXEGcP3dSC_PjU4gKgmXmpJfHOfoaGZmYmpsbGpo7GxKgBAAVGL_0</recordid><startdate>20230825</startdate><enddate>20230825</enddate><creator>SU JIANYE</creator><creator>SUN LIN</creator><creator>LIU PENG</creator><creator>LIN WANGCHENG</creator><creator>YING DONGPING</creator><creator>ZHANG CAN</creator><creator>LU WEIJIA</creator><scope>EVB</scope></search><sort><creationdate>20230825</creationdate><title>Road surface pit detection method and readable storage medium</title><author>SU JIANYE ; SUN LIN ; LIU PENG ; LIN WANGCHENG ; YING DONGPING ; ZHANG CAN ; LU WEIJIA</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116645335A3</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>SU JIANYE</creatorcontrib><creatorcontrib>SUN LIN</creatorcontrib><creatorcontrib>LIU PENG</creatorcontrib><creatorcontrib>LIN WANGCHENG</creatorcontrib><creatorcontrib>YING DONGPING</creatorcontrib><creatorcontrib>ZHANG CAN</creatorcontrib><creatorcontrib>LU WEIJIA</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SU JIANYE</au><au>SUN LIN</au><au>LIU PENG</au><au>LIN WANGCHENG</au><au>YING DONGPING</au><au>ZHANG CAN</au><au>LU WEIJIA</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Road surface pit detection method and readable storage medium</title><date>2023-08-25</date><risdate>2023</risdate><abstract>The invention provides a pavement pit detection method and a readable storage medium. The pavement pothole detection method comprises the following steps: acquiring a binocular image; the binocular image obtains a parallax estimation result based on a parallax estimation algorithm; the binocular image obtains a pavement segmentation result based on a pavement segmentation algorithm; and obtaining a pavement pothole detection result based on the parallax estimation result and the pavement segmentation result. Wherein the parallax estimation algorithm and the pavement segmentation algorithm at least share one part of the neural network. Through the configuration, on one hand, the problems of training data and application thresholds are solved through binocular images, on the other hand, through the shared neural network, the two algorithms can share intermediate data in the training and calculation process, the training and calculation speed is increased, and the overall size of the neural network participating</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN116645335A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Road surface pit detection method and readable storage medium |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T03%3A49%3A03IST&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=SU%20JIANYE&rft.date=2023-08-25&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116645335A%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 |