Contact network detection method
The invention provides a contact network detection method, which belongs to the technical field of electrified railway equipment state performance detection, and comprises the following steps: obtaining contact network detection data; performing color correction on the contact network detection imag...
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 | ZHAO JINGJIAN WANG XUEZHU JIA MINGYONG WU CHUNSHENG ZHAO JIANFENG XIA ZHIYUAN ZHAO JIANJUN SONG XINJIANG YAN YUXIN WANG QUAN LI ZHAOYU LI ZHONGHUI |
| description | The invention provides a contact network detection method, which belongs to the technical field of electrified railway equipment state performance detection, and comprises the following steps: obtaining contact network detection data; performing color correction on the contact network detection image; performing contrast enhancement on the color correction image; performing weighting processing on pixel features and channel features by using a convolutional neural network for constructing space attention and channel attention calculation branches; extracting an effective edge of the image by using a Canny operator; carrying out image annotation, and making a sample data set; and carrying out detection model training by using the positive sample data set and the negative sample data set, and carrying out detection to obtain a detection result. According to the method, the detection image data obtained in a severe environment can be enhanced in a targeted manner, the use efficiency of the detection data is impr |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118071752A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118071752A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118071752A3</originalsourceid><addsrcrecordid>eNrjZFBwzs8rSUwuUchLLSnPL8pWSEktSU0uyczPU8hNLcnIT-FhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqUCt8c5-hoYWBuaG5qZGjsbEqAEAa_clfQ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Contact network detection method</title><source>esp@cenet</source><creator>ZHAO JINGJIAN ; WANG XUEZHU ; JIA MINGYONG ; WU CHUNSHENG ; ZHAO JIANFENG ; XIA ZHIYUAN ; ZHAO JIANJUN ; SONG XINJIANG ; YAN YUXIN ; WANG QUAN ; LI ZHAOYU ; LI ZHONGHUI</creator><creatorcontrib>ZHAO JINGJIAN ; WANG XUEZHU ; JIA MINGYONG ; WU CHUNSHENG ; ZHAO JIANFENG ; XIA ZHIYUAN ; ZHAO JIANJUN ; SONG XINJIANG ; YAN YUXIN ; WANG QUAN ; LI ZHAOYU ; LI ZHONGHUI</creatorcontrib><description>The invention provides a contact network detection method, which belongs to the technical field of electrified railway equipment state performance detection, and comprises the following steps: obtaining contact network detection data; performing color correction on the contact network detection image; performing contrast enhancement on the color correction image; performing weighting processing on pixel features and channel features by using a convolutional neural network for constructing space attention and channel attention calculation branches; extracting an effective edge of the image by using a Canny operator; carrying out image annotation, and making a sample data set; and carrying out detection model training by using the positive sample data set and the negative sample data set, and carrying out detection to obtain a detection result. According to the method, the detection image data obtained in a severe environment can be enhanced in a targeted manner, the use efficiency of the detection data is impr</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; 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=20240524&DB=EPODOC&CC=CN&NR=118071752A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240524&DB=EPODOC&CC=CN&NR=118071752A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHAO JINGJIAN</creatorcontrib><creatorcontrib>WANG XUEZHU</creatorcontrib><creatorcontrib>JIA MINGYONG</creatorcontrib><creatorcontrib>WU CHUNSHENG</creatorcontrib><creatorcontrib>ZHAO JIANFENG</creatorcontrib><creatorcontrib>XIA ZHIYUAN</creatorcontrib><creatorcontrib>ZHAO JIANJUN</creatorcontrib><creatorcontrib>SONG XINJIANG</creatorcontrib><creatorcontrib>YAN YUXIN</creatorcontrib><creatorcontrib>WANG QUAN</creatorcontrib><creatorcontrib>LI ZHAOYU</creatorcontrib><creatorcontrib>LI ZHONGHUI</creatorcontrib><title>Contact network detection method</title><description>The invention provides a contact network detection method, which belongs to the technical field of electrified railway equipment state performance detection, and comprises the following steps: obtaining contact network detection data; performing color correction on the contact network detection image; performing contrast enhancement on the color correction image; performing weighting processing on pixel features and channel features by using a convolutional neural network for constructing space attention and channel attention calculation branches; extracting an effective edge of the image by using a Canny operator; carrying out image annotation, and making a sample data set; and carrying out detection model training by using the positive sample data set and the negative sample data set, and carrying out detection to obtain a detection result. According to the method, the detection image data obtained in a severe environment can be enhanced in a targeted manner, the use efficiency of the detection data is impr</description><subject>CALCULATING</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>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZFBwzs8rSUwuUchLLSnPL8pWSEktSU0uyczPU8hNLcnIT-FhYE1LzClO5YXS3AyKbq4hzh66qQX58anFBYnJqUCt8c5-hoYWBuaG5qZGjsbEqAEAa_clfQ</recordid><startdate>20240524</startdate><enddate>20240524</enddate><creator>ZHAO JINGJIAN</creator><creator>WANG XUEZHU</creator><creator>JIA MINGYONG</creator><creator>WU CHUNSHENG</creator><creator>ZHAO JIANFENG</creator><creator>XIA ZHIYUAN</creator><creator>ZHAO JIANJUN</creator><creator>SONG XINJIANG</creator><creator>YAN YUXIN</creator><creator>WANG QUAN</creator><creator>LI ZHAOYU</creator><creator>LI ZHONGHUI</creator><scope>EVB</scope></search><sort><creationdate>20240524</creationdate><title>Contact network detection method</title><author>ZHAO JINGJIAN ; WANG XUEZHU ; JIA MINGYONG ; WU CHUNSHENG ; ZHAO JIANFENG ; XIA ZHIYUAN ; ZHAO JIANJUN ; SONG XINJIANG ; YAN YUXIN ; WANG QUAN ; LI ZHAOYU ; LI ZHONGHUI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118071752A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHAO JINGJIAN</creatorcontrib><creatorcontrib>WANG XUEZHU</creatorcontrib><creatorcontrib>JIA MINGYONG</creatorcontrib><creatorcontrib>WU CHUNSHENG</creatorcontrib><creatorcontrib>ZHAO JIANFENG</creatorcontrib><creatorcontrib>XIA ZHIYUAN</creatorcontrib><creatorcontrib>ZHAO JIANJUN</creatorcontrib><creatorcontrib>SONG XINJIANG</creatorcontrib><creatorcontrib>YAN YUXIN</creatorcontrib><creatorcontrib>WANG QUAN</creatorcontrib><creatorcontrib>LI ZHAOYU</creatorcontrib><creatorcontrib>LI ZHONGHUI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHAO JINGJIAN</au><au>WANG XUEZHU</au><au>JIA MINGYONG</au><au>WU CHUNSHENG</au><au>ZHAO JIANFENG</au><au>XIA ZHIYUAN</au><au>ZHAO JIANJUN</au><au>SONG XINJIANG</au><au>YAN YUXIN</au><au>WANG QUAN</au><au>LI ZHAOYU</au><au>LI ZHONGHUI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Contact network detection method</title><date>2024-05-24</date><risdate>2024</risdate><abstract>The invention provides a contact network detection method, which belongs to the technical field of electrified railway equipment state performance detection, and comprises the following steps: obtaining contact network detection data; performing color correction on the contact network detection image; performing contrast enhancement on the color correction image; performing weighting processing on pixel features and channel features by using a convolutional neural network for constructing space attention and channel attention calculation branches; extracting an effective edge of the image by using a Canny operator; carrying out image annotation, and making a sample data set; and carrying out detection model training by using the positive sample data set and the negative sample data set, and carrying out detection to obtain a detection result. According to the method, the detection image data obtained in a severe environment can be enhanced in a targeted manner, the use efficiency of the detection data is impr</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN118071752A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING IMAGE DATA PROCESSING OR GENERATION, IN GENERAL PHYSICS |
| title | Contact network detection method |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T10%3A50%3A42IST&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=ZHAO%20JINGJIAN&rft.date=2024-05-24&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118071752A%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 |