Method and system for reducing misrecognition rate of power transmission channel forest fire smoke detection model
The invention discloses a method and system for reducing the false recognition rate of a power transmission channel forest fire smoke detection model, and the method comprises the steps: carrying out the recognition and filtering through a trained yolo-s model, and screening an image data set of non...
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 | YUAN SHAOGUANG PANG KAI ZHANG JIAXIANG WANG QI MAO WANDENG GUO ZHIMIN JIANG LIANG WANG QIAN TIAN YANGYANG LI PANYANG CUI JIABIN KOU XIAOSHI ZHANG WEIJIAN CHEN BIN LIU SHANFENG SONG WEI CHENG XIAWEI LI ZHE ZHANG LU TAN LEI ZHANG YU ZHENG WEI CHEN CEN |
| description | The invention discloses a method and system for reducing the false recognition rate of a power transmission channel forest fire smoke detection model, and the method comprises the steps: carrying out the recognition and filtering through a trained yolo-s model, and screening an image data set of non-forest fire smoke; secondly, carrying out fixed position alarm duplicate removal, and filtering out a duplicate information image data set; and finally, final filtering is carried out by combining environmental factor information in the image data set. According to the method, after the collected images are filtered and screened for three times, the accuracy of the identified forest fire smoke images can reach 97%, the false identification rate of forest fire smoke image identification is effectively reduced, and the precision of power transmission channel forest fire smoke model detection is remarkably improved.
一种降低输电通道山火烟雾检测模型误识别率的方法和系统，所述方法包括：首先通过训练好的yolo-s模型进行识别过滤，筛选出非山火烟雾的图像数据集；其次进行固定位置告警去重，过滤掉重复信息图像数据集；最后通过 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN117953372A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN117953372A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN117953372A3</originalsourceid><addsrcrecordid>eNqNi7EKwkAQBdNYiPoP6wdYxCDBUoJio5V9OO7eJYe53XB7Iv69RvwAqylmZl6kC3Ivjgw70pdmRPKSKME9bOCOYtAEKx2HHIQpmQwST6M8kSgnw_opdFK2N8wYph2ayYcE0ih3kEOG_e5RHIZlMfNmUKx-XBTr0_HWnDcYpYWOxoKR2-ZalvV-V1X19lD907wBUfNE2Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Method and system for reducing misrecognition rate of power transmission channel forest fire smoke detection model</title><source>esp@cenet</source><creator>YUAN SHAOGUANG ; PANG KAI ; ZHANG JIAXIANG ; WANG QI ; MAO WANDENG ; GUO ZHIMIN ; JIANG LIANG ; WANG QIAN ; TIAN YANGYANG ; LI PANYANG ; CUI JIABIN ; KOU XIAOSHI ; ZHANG WEIJIAN ; CHEN BIN ; LIU SHANFENG ; SONG WEI ; CHENG XIAWEI ; LI ZHE ; ZHANG LU ; TAN LEI ; ZHANG YU ; ZHENG WEI ; CHEN CEN</creator><creatorcontrib>YUAN SHAOGUANG ; PANG KAI ; ZHANG JIAXIANG ; WANG QI ; MAO WANDENG ; GUO ZHIMIN ; JIANG LIANG ; WANG QIAN ; TIAN YANGYANG ; LI PANYANG ; CUI JIABIN ; KOU XIAOSHI ; ZHANG WEIJIAN ; CHEN BIN ; LIU SHANFENG ; SONG WEI ; CHENG XIAWEI ; LI ZHE ; ZHANG LU ; TAN LEI ; ZHANG YU ; ZHENG WEI ; CHEN CEN</creatorcontrib><description>The invention discloses a method and system for reducing the false recognition rate of a power transmission channel forest fire smoke detection model, and the method comprises the steps: carrying out the recognition and filtering through a trained yolo-s model, and screening an image data set of non-forest fire smoke; secondly, carrying out fixed position alarm duplicate removal, and filtering out a duplicate information image data set; and finally, final filtering is carried out by combining environmental factor information in the image data set. According to the method, after the collected images are filtered and screened for three times, the accuracy of the identified forest fire smoke images can reach 97%, the false identification rate of forest fire smoke image identification is effectively reduced, and the precision of power transmission channel forest fire smoke model detection is remarkably improved.
一种降低输电通道山火烟雾检测模型误识别率的方法和系统，所述方法包括：首先通过训练好的yolo-s模型进行识别过滤，筛选出非山火烟雾的图像数据集；其次进行固定位置告警去重，过滤掉重复信息图像数据集；最后通过</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&date=20240430&DB=EPODOC&CC=CN&NR=117953372A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,778,883,25547,76298</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240430&DB=EPODOC&CC=CN&NR=117953372A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YUAN SHAOGUANG</creatorcontrib><creatorcontrib>PANG KAI</creatorcontrib><creatorcontrib>ZHANG JIAXIANG</creatorcontrib><creatorcontrib>WANG QI</creatorcontrib><creatorcontrib>MAO WANDENG</creatorcontrib><creatorcontrib>GUO ZHIMIN</creatorcontrib><creatorcontrib>JIANG LIANG</creatorcontrib><creatorcontrib>WANG QIAN</creatorcontrib><creatorcontrib>TIAN YANGYANG</creatorcontrib><creatorcontrib>LI PANYANG</creatorcontrib><creatorcontrib>CUI JIABIN</creatorcontrib><creatorcontrib>KOU XIAOSHI</creatorcontrib><creatorcontrib>ZHANG WEIJIAN</creatorcontrib><creatorcontrib>CHEN BIN</creatorcontrib><creatorcontrib>LIU SHANFENG</creatorcontrib><creatorcontrib>SONG WEI</creatorcontrib><creatorcontrib>CHENG XIAWEI</creatorcontrib><creatorcontrib>LI ZHE</creatorcontrib><creatorcontrib>ZHANG LU</creatorcontrib><creatorcontrib>TAN LEI</creatorcontrib><creatorcontrib>ZHANG YU</creatorcontrib><creatorcontrib>ZHENG WEI</creatorcontrib><creatorcontrib>CHEN CEN</creatorcontrib><title>Method and system for reducing misrecognition rate of power transmission channel forest fire smoke detection model</title><description>The invention discloses a method and system for reducing the false recognition rate of a power transmission channel forest fire smoke detection model, and the method comprises the steps: carrying out the recognition and filtering through a trained yolo-s model, and screening an image data set of non-forest fire smoke; secondly, carrying out fixed position alarm duplicate removal, and filtering out a duplicate information image data set; and finally, final filtering is carried out by combining environmental factor information in the image data set. According to the method, after the collected images are filtered and screened for three times, the accuracy of the identified forest fire smoke images can reach 97%, the false identification rate of forest fire smoke image identification is effectively reduced, and the precision of power transmission channel forest fire smoke model detection is remarkably improved.
一种降低输电通道山火烟雾检测模型误识别率的方法和系统，所述方法包括：首先通过训练好的yolo-s模型进行识别过滤，筛选出非山火烟雾的图像数据集；其次进行固定位置告警去重，过滤掉重复信息图像数据集；最后通过</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>eNqNi7EKwkAQBdNYiPoP6wdYxCDBUoJio5V9OO7eJYe53XB7Iv69RvwAqylmZl6kC3Ivjgw70pdmRPKSKME9bOCOYtAEKx2HHIQpmQwST6M8kSgnw_opdFK2N8wYph2ayYcE0ih3kEOG_e5RHIZlMfNmUKx-XBTr0_HWnDcYpYWOxoKR2-ZalvV-V1X19lD907wBUfNE2Q</recordid><startdate>20240430</startdate><enddate>20240430</enddate><creator>YUAN SHAOGUANG</creator><creator>PANG KAI</creator><creator>ZHANG JIAXIANG</creator><creator>WANG QI</creator><creator>MAO WANDENG</creator><creator>GUO ZHIMIN</creator><creator>JIANG LIANG</creator><creator>WANG QIAN</creator><creator>TIAN YANGYANG</creator><creator>LI PANYANG</creator><creator>CUI JIABIN</creator><creator>KOU XIAOSHI</creator><creator>ZHANG WEIJIAN</creator><creator>CHEN BIN</creator><creator>LIU SHANFENG</creator><creator>SONG WEI</creator><creator>CHENG XIAWEI</creator><creator>LI ZHE</creator><creator>ZHANG LU</creator><creator>TAN LEI</creator><creator>ZHANG YU</creator><creator>ZHENG WEI</creator><creator>CHEN CEN</creator><scope>EVB</scope></search><sort><creationdate>20240430</creationdate><title>Method and system for reducing misrecognition rate of power transmission channel forest fire smoke detection model</title><author>YUAN SHAOGUANG ; PANG KAI ; ZHANG JIAXIANG ; WANG QI ; MAO WANDENG ; GUO ZHIMIN ; JIANG LIANG ; WANG QIAN ; TIAN YANGYANG ; LI PANYANG ; CUI JIABIN ; KOU XIAOSHI ; ZHANG WEIJIAN ; CHEN BIN ; LIU SHANFENG ; SONG WEI ; CHENG XIAWEI ; LI ZHE ; ZHANG LU ; TAN LEI ; ZHANG YU ; ZHENG WEI ; CHEN CEN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN117953372A3</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>YUAN SHAOGUANG</creatorcontrib><creatorcontrib>PANG KAI</creatorcontrib><creatorcontrib>ZHANG JIAXIANG</creatorcontrib><creatorcontrib>WANG QI</creatorcontrib><creatorcontrib>MAO WANDENG</creatorcontrib><creatorcontrib>GUO ZHIMIN</creatorcontrib><creatorcontrib>JIANG LIANG</creatorcontrib><creatorcontrib>WANG QIAN</creatorcontrib><creatorcontrib>TIAN YANGYANG</creatorcontrib><creatorcontrib>LI PANYANG</creatorcontrib><creatorcontrib>CUI JIABIN</creatorcontrib><creatorcontrib>KOU XIAOSHI</creatorcontrib><creatorcontrib>ZHANG WEIJIAN</creatorcontrib><creatorcontrib>CHEN BIN</creatorcontrib><creatorcontrib>LIU SHANFENG</creatorcontrib><creatorcontrib>SONG WEI</creatorcontrib><creatorcontrib>CHENG XIAWEI</creatorcontrib><creatorcontrib>LI ZHE</creatorcontrib><creatorcontrib>ZHANG LU</creatorcontrib><creatorcontrib>TAN LEI</creatorcontrib><creatorcontrib>ZHANG YU</creatorcontrib><creatorcontrib>ZHENG WEI</creatorcontrib><creatorcontrib>CHEN CEN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YUAN SHAOGUANG</au><au>PANG KAI</au><au>ZHANG JIAXIANG</au><au>WANG QI</au><au>MAO WANDENG</au><au>GUO ZHIMIN</au><au>JIANG LIANG</au><au>WANG QIAN</au><au>TIAN YANGYANG</au><au>LI PANYANG</au><au>CUI JIABIN</au><au>KOU XIAOSHI</au><au>ZHANG WEIJIAN</au><au>CHEN BIN</au><au>LIU SHANFENG</au><au>SONG WEI</au><au>CHENG XIAWEI</au><au>LI ZHE</au><au>ZHANG LU</au><au>TAN LEI</au><au>ZHANG YU</au><au>ZHENG WEI</au><au>CHEN CEN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Method and system for reducing misrecognition rate of power transmission channel forest fire smoke detection model</title><date>2024-04-30</date><risdate>2024</risdate><abstract>The invention discloses a method and system for reducing the false recognition rate of a power transmission channel forest fire smoke detection model, and the method comprises the steps: carrying out the recognition and filtering through a trained yolo-s model, and screening an image data set of non-forest fire smoke; secondly, carrying out fixed position alarm duplicate removal, and filtering out a duplicate information image data set; and finally, final filtering is carried out by combining environmental factor information in the image data set. According to the method, after the collected images are filtered and screened for three times, the accuracy of the identified forest fire smoke images can reach 97%, the false identification rate of forest fire smoke image identification is effectively reduced, and the precision of power transmission channel forest fire smoke model detection is remarkably improved.
一种降低输电通道山火烟雾检测模型误识别率的方法和系统，所述方法包括：首先通过训练好的yolo-s模型进行识别过滤，筛选出非山火烟雾的图像数据集；其次进行固定位置告警去重，过滤掉重复信息图像数据集；最后通过</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN117953372A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING PHYSICS |
| title | Method and system for reducing misrecognition rate of power transmission channel forest fire smoke detection model |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-16T20%3A02%3A04IST&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=YUAN%20SHAOGUANG&rft.date=2024-04-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN117953372A%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 |