Cascade target recognition method and system based on deep learning
The invention provides a cascade target recognition method and system based on deep learning, and the method comprises the steps: obtaining a to-be-detected sample of an inspection image, marking a target detection sample, and expanding the number of samples; fusing multiple features of the image en...
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 | ZHOU DAZHOU LIU GUANGXIU LI JIANXIANG WANG ZHENLI LI YONG XU RONGHAO MU SHIYOU LIU PIYU ZHANG XU WANG WANGUO ZHAO JINLONG LIU YUE LI ZHENYU JIA YAJUN XU WEI GUO RUI |
| description | The invention provides a cascade target recognition method and system based on deep learning, and the method comprises the steps: obtaining a to-be-detected sample of an inspection image, marking a target detection sample, and expanding the number of samples; fusing multiple features of the image enhancement data to carry out a multi-stage deep learning detection algorithm, realizing significant equipment detection for a target with a large proportion, and eliminating noise interference of a complex background on the detection algorithm. Multi-stage deep learning algorithm detection is carriedout by fusing multiple features of image enhancement data, so that the detection accuracy of deep learning in small target detection is improved, and the influence of image quality on the detection algorithm is reduced.
本公开提供了基于深度学习的级联目标识别方法及系统，获取巡检图像的待检测样本，对目标检测样本标记，并对样本数量进行扩充；融合图像增强数据的多特征进行多级深度学习检测算法，实现针对占比较大目标的显著设备检测，剔除复杂背景对检测算法的噪声干扰；融合图像增强数据的多特征进行多级深度学习算法检测，提高深度学习在小目标检测中的检测准确率，降低了图像质量对检测算法的影响。 |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN110688925A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN110688925A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN110688925A3</originalsourceid><addsrcrecordid>eNqNyjEOwjAMRuEuDAi4gzkAEgWByogiEBMTe2WSnzRS60SxF24PAwdgesP35o1zrJ4DyLhGGFX4HCVZykITbMiBWALpWw0TPVkR6EsBKDSCqySJy2b24lGx-nXRrK-Xh7ttUHIPLewhsN7d23Z77LrT7nDe__N8AGZ1Mkk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Cascade target recognition method and system based on deep learning</title><source>esp@cenet</source><creator>ZHOU DAZHOU ; LIU GUANGXIU ; LI JIANXIANG ; WANG ZHENLI ; LI YONG ; XU RONGHAO ; MU SHIYOU ; LIU PIYU ; ZHANG XU ; WANG WANGUO ; ZHAO JINLONG ; LIU YUE ; LI ZHENYU ; JIA YAJUN ; XU WEI ; GUO RUI</creator><creatorcontrib>ZHOU DAZHOU ; LIU GUANGXIU ; LI JIANXIANG ; WANG ZHENLI ; LI YONG ; XU RONGHAO ; MU SHIYOU ; LIU PIYU ; ZHANG XU ; WANG WANGUO ; ZHAO JINLONG ; LIU YUE ; LI ZHENYU ; JIA YAJUN ; XU WEI ; GUO RUI</creatorcontrib><description>The invention provides a cascade target recognition method and system based on deep learning, and the method comprises the steps: obtaining a to-be-detected sample of an inspection image, marking a target detection sample, and expanding the number of samples; fusing multiple features of the image enhancement data to carry out a multi-stage deep learning detection algorithm, realizing significant equipment detection for a target with a large proportion, and eliminating noise interference of a complex background on the detection algorithm. Multi-stage deep learning algorithm detection is carriedout by fusing multiple features of image enhancement data, so that the detection accuracy of deep learning in small target detection is improved, and the influence of image quality on the detection algorithm is reduced.
本公开提供了基于深度学习的级联目标识别方法及系统，获取巡检图像的待检测样本，对目标检测样本标记，并对样本数量进行扩充；融合图像增强数据的多特征进行多级深度学习检测算法，实现针对占比较大目标的显著设备检测，剔除复杂背景对检测算法的噪声干扰；融合图像增强数据的多特征进行多级深度学习算法检测，提高深度学习在小目标检测中的检测准确率，降低了图像质量对检测算法的影响。</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; HANDLING RECORD CARRIERS ; PHYSICS ; PRESENTATION OF DATA ; RECOGNITION OF DATA ; RECORD CARRIERS</subject><creationdate>2020</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=20200114&DB=EPODOC&CC=CN&NR=110688925A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76290</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20200114&DB=EPODOC&CC=CN&NR=110688925A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHOU DAZHOU</creatorcontrib><creatorcontrib>LIU GUANGXIU</creatorcontrib><creatorcontrib>LI JIANXIANG</creatorcontrib><creatorcontrib>WANG ZHENLI</creatorcontrib><creatorcontrib>LI YONG</creatorcontrib><creatorcontrib>XU RONGHAO</creatorcontrib><creatorcontrib>MU SHIYOU</creatorcontrib><creatorcontrib>LIU PIYU</creatorcontrib><creatorcontrib>ZHANG XU</creatorcontrib><creatorcontrib>WANG WANGUO</creatorcontrib><creatorcontrib>ZHAO JINLONG</creatorcontrib><creatorcontrib>LIU YUE</creatorcontrib><creatorcontrib>LI ZHENYU</creatorcontrib><creatorcontrib>JIA YAJUN</creatorcontrib><creatorcontrib>XU WEI</creatorcontrib><creatorcontrib>GUO RUI</creatorcontrib><title>Cascade target recognition method and system based on deep learning</title><description>The invention provides a cascade target recognition method and system based on deep learning, and the method comprises the steps: obtaining a to-be-detected sample of an inspection image, marking a target detection sample, and expanding the number of samples; fusing multiple features of the image enhancement data to carry out a multi-stage deep learning detection algorithm, realizing significant equipment detection for a target with a large proportion, and eliminating noise interference of a complex background on the detection algorithm. Multi-stage deep learning algorithm detection is carriedout by fusing multiple features of image enhancement data, so that the detection accuracy of deep learning in small target detection is improved, and the influence of image quality on the detection algorithm is reduced.
本公开提供了基于深度学习的级联目标识别方法及系统，获取巡检图像的待检测样本，对目标检测样本标记，并对样本数量进行扩充；融合图像增强数据的多特征进行多级深度学习检测算法，实现针对占比较大目标的显著设备检测，剔除复杂背景对检测算法的噪声干扰；融合图像增强数据的多特征进行多级深度学习算法检测，提高深度学习在小目标检测中的检测准确率，降低了图像质量对检测算法的影响。</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>HANDLING RECORD CARRIERS</subject><subject>PHYSICS</subject><subject>PRESENTATION OF DATA</subject><subject>RECOGNITION OF DATA</subject><subject>RECORD CARRIERS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2020</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyjEOwjAMRuEuDAi4gzkAEgWByogiEBMTe2WSnzRS60SxF24PAwdgesP35o1zrJ4DyLhGGFX4HCVZykITbMiBWALpWw0TPVkR6EsBKDSCqySJy2b24lGx-nXRrK-Xh7ttUHIPLewhsN7d23Z77LrT7nDe__N8AGZ1Mkk</recordid><startdate>20200114</startdate><enddate>20200114</enddate><creator>ZHOU DAZHOU</creator><creator>LIU GUANGXIU</creator><creator>LI JIANXIANG</creator><creator>WANG ZHENLI</creator><creator>LI YONG</creator><creator>XU RONGHAO</creator><creator>MU SHIYOU</creator><creator>LIU PIYU</creator><creator>ZHANG XU</creator><creator>WANG WANGUO</creator><creator>ZHAO JINLONG</creator><creator>LIU YUE</creator><creator>LI ZHENYU</creator><creator>JIA YAJUN</creator><creator>XU WEI</creator><creator>GUO RUI</creator><scope>EVB</scope></search><sort><creationdate>20200114</creationdate><title>Cascade target recognition method and system based on deep learning</title><author>ZHOU DAZHOU ; LIU GUANGXIU ; LI JIANXIANG ; WANG ZHENLI ; LI YONG ; XU RONGHAO ; MU SHIYOU ; LIU PIYU ; ZHANG XU ; WANG WANGUO ; ZHAO JINLONG ; LIU YUE ; LI ZHENYU ; JIA YAJUN ; XU WEI ; GUO RUI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN110688925A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2020</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>HANDLING RECORD CARRIERS</topic><topic>PHYSICS</topic><topic>PRESENTATION OF DATA</topic><topic>RECOGNITION OF DATA</topic><topic>RECORD CARRIERS</topic><toplevel>online_resources</toplevel><creatorcontrib>ZHOU DAZHOU</creatorcontrib><creatorcontrib>LIU GUANGXIU</creatorcontrib><creatorcontrib>LI JIANXIANG</creatorcontrib><creatorcontrib>WANG ZHENLI</creatorcontrib><creatorcontrib>LI YONG</creatorcontrib><creatorcontrib>XU RONGHAO</creatorcontrib><creatorcontrib>MU SHIYOU</creatorcontrib><creatorcontrib>LIU PIYU</creatorcontrib><creatorcontrib>ZHANG XU</creatorcontrib><creatorcontrib>WANG WANGUO</creatorcontrib><creatorcontrib>ZHAO JINLONG</creatorcontrib><creatorcontrib>LIU YUE</creatorcontrib><creatorcontrib>LI ZHENYU</creatorcontrib><creatorcontrib>JIA YAJUN</creatorcontrib><creatorcontrib>XU WEI</creatorcontrib><creatorcontrib>GUO RUI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHOU DAZHOU</au><au>LIU GUANGXIU</au><au>LI JIANXIANG</au><au>WANG ZHENLI</au><au>LI YONG</au><au>XU RONGHAO</au><au>MU SHIYOU</au><au>LIU PIYU</au><au>ZHANG XU</au><au>WANG WANGUO</au><au>ZHAO JINLONG</au><au>LIU YUE</au><au>LI ZHENYU</au><au>JIA YAJUN</au><au>XU WEI</au><au>GUO RUI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Cascade target recognition method and system based on deep learning</title><date>2020-01-14</date><risdate>2020</risdate><abstract>The invention provides a cascade target recognition method and system based on deep learning, and the method comprises the steps: obtaining a to-be-detected sample of an inspection image, marking a target detection sample, and expanding the number of samples; fusing multiple features of the image enhancement data to carry out a multi-stage deep learning detection algorithm, realizing significant equipment detection for a target with a large proportion, and eliminating noise interference of a complex background on the detection algorithm. Multi-stage deep learning algorithm detection is carriedout by fusing multiple features of image enhancement data, so that the detection accuracy of deep learning in small target detection is improved, and the influence of image quality on the detection algorithm is reduced.
本公开提供了基于深度学习的级联目标识别方法及系统，获取巡检图像的待检测样本，对目标检测样本标记，并对样本数量进行扩充；融合图像增强数据的多特征进行多级深度学习检测算法，实现针对占比较大目标的显著设备检测，剔除复杂背景对检测算法的噪声干扰；融合图像增强数据的多特征进行多级深度学习算法检测，提高深度学习在小目标检测中的检测准确率，降低了图像质量对检测算法的影响。</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | chi ; eng |
| recordid | cdi_epo_espacenet_CN110688925A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING HANDLING RECORD CARRIERS PHYSICS PRESENTATION OF DATA RECOGNITION OF DATA RECORD CARRIERS |
| title | Cascade target recognition method and system based on deep learning |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-30T04%3A58%3A40IST&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=ZHOU%20DAZHOU&rft.date=2020-01-14&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN110688925A%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 |