Target detection model, method and device applied to hazardous chemical vehicle detection
According to the target detection model, method and device applied to hazardous chemical vehicle detection, a window pooling multi-head self-attention mechanism is embedded in a window pooling multi-head self-attention module in the scheme, so that the calculation amount is reduced; an offset window...
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 XIANGWEI DONG MOJIANG PENG DAMENG CAO ZHE MAO RUOKAI |
description | According to the target detection model, method and device applied to hazardous chemical vehicle detection, a window pooling multi-head self-attention mechanism is embedded in a window pooling multi-head self-attention module in the scheme, so that the calculation amount is reduced; an offset window pooling multi-head self-attention mechanism solves the defect that information transmission cannot be carried out between windows, and the square calculation complexity of self-attention is reduced; in addition, a high-order space interaction module is introduced to be completely based on high-order space interaction modeling of a convolution structure, a very flexible effect is achieved, various convolution forms can be compatible, and self-attention second-order space interaction modeling can be expanded to any order under the condition that the calculated amount is not remarkably increased.
本申请提出了一种应用于危化品车检测的目标检测模型、方法及装置,该方案的窗口池化多头部自注意力模块嵌入了窗口池化多头部自注意力机制用于减少计算量,且偏移窗口池化多头部自注意力机制解决窗口与窗口之间是无法进行信息传递的弊端,降低了自注意力的平方计算 |
format | Patent |
fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115375999A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115375999A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115375999A3</originalsourceid><addsrcrecordid>eNqNjL0KwjAURrM4iPoO112HUopklKI4OXVxKpfcTxPIH03s4NPrILg6neEczlLdBp4eqCSoMNWlSCEJ_I4Cqk1CHOXjZmdAnLN3EKqJLL94kvQsZCyCM-xphnXG4zdaq8WdfcHmy5Xank9Df9kjpxEls0FEHftr03TtodNaH9t_mjfLHzqx</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Target detection model, method and device applied to hazardous chemical vehicle detection</title><source>esp@cenet</source><creator>ZHANG XIANGWEI ; DONG MOJIANG ; PENG DAMENG ; CAO ZHE ; MAO RUOKAI</creator><creatorcontrib>ZHANG XIANGWEI ; DONG MOJIANG ; PENG DAMENG ; CAO ZHE ; MAO RUOKAI</creatorcontrib><description>According to the target detection model, method and device applied to hazardous chemical vehicle detection, a window pooling multi-head self-attention mechanism is embedded in a window pooling multi-head self-attention module in the scheme, so that the calculation amount is reduced; an offset window pooling multi-head self-attention mechanism solves the defect that information transmission cannot be carried out between windows, and the square calculation complexity of self-attention is reduced; in addition, a high-order space interaction module is introduced to be completely based on high-order space interaction modeling of a convolution structure, a very flexible effect is achieved, various convolution forms can be compatible, and self-attention second-order space interaction modeling can be expanded to any order under the condition that the calculated amount is not remarkably increased.
本申请提出了一种应用于危化品车检测的目标检测模型、方法及装置,该方案的窗口池化多头部自注意力模块嵌入了窗口池化多头部自注意力机制用于减少计算量,且偏移窗口池化多头部自注意力机制解决窗口与窗口之间是无法进行信息传递的弊端,降低了自注意力的平方计算</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</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=20221122&DB=EPODOC&CC=CN&NR=115375999A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25562,76317</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20221122&DB=EPODOC&CC=CN&NR=115375999A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG XIANGWEI</creatorcontrib><creatorcontrib>DONG MOJIANG</creatorcontrib><creatorcontrib>PENG DAMENG</creatorcontrib><creatorcontrib>CAO ZHE</creatorcontrib><creatorcontrib>MAO RUOKAI</creatorcontrib><title>Target detection model, method and device applied to hazardous chemical vehicle detection</title><description>According to the target detection model, method and device applied to hazardous chemical vehicle detection, a window pooling multi-head self-attention mechanism is embedded in a window pooling multi-head self-attention module in the scheme, so that the calculation amount is reduced; an offset window pooling multi-head self-attention mechanism solves the defect that information transmission cannot be carried out between windows, and the square calculation complexity of self-attention is reduced; in addition, a high-order space interaction module is introduced to be completely based on high-order space interaction modeling of a convolution structure, a very flexible effect is achieved, various convolution forms can be compatible, and self-attention second-order space interaction modeling can be expanded to any order under the condition that the calculated amount is not remarkably increased.
本申请提出了一种应用于危化品车检测的目标检测模型、方法及装置,该方案的窗口池化多头部自注意力模块嵌入了窗口池化多头部自注意力机制用于减少计算量,且偏移窗口池化多头部自注意力机制解决窗口与窗口之间是无法进行信息传递的弊端,降低了自注意力的平方计算</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNjL0KwjAURrM4iPoO112HUopklKI4OXVxKpfcTxPIH03s4NPrILg6neEczlLdBp4eqCSoMNWlSCEJ_I4Cqk1CHOXjZmdAnLN3EKqJLL94kvQsZCyCM-xphnXG4zdaq8WdfcHmy5Xank9Df9kjpxEls0FEHftr03TtodNaH9t_mjfLHzqx</recordid><startdate>20221122</startdate><enddate>20221122</enddate><creator>ZHANG XIANGWEI</creator><creator>DONG MOJIANG</creator><creator>PENG DAMENG</creator><creator>CAO ZHE</creator><creator>MAO RUOKAI</creator><scope>EVB</scope></search><sort><creationdate>20221122</creationdate><title>Target detection model, method and device applied to hazardous chemical vehicle detection</title><author>ZHANG XIANGWEI ; DONG MOJIANG ; PENG DAMENG ; CAO ZHE ; MAO RUOKAI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115375999A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</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 XIANGWEI</creatorcontrib><creatorcontrib>DONG MOJIANG</creatorcontrib><creatorcontrib>PENG DAMENG</creatorcontrib><creatorcontrib>CAO ZHE</creatorcontrib><creatorcontrib>MAO RUOKAI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG XIANGWEI</au><au>DONG MOJIANG</au><au>PENG DAMENG</au><au>CAO ZHE</au><au>MAO RUOKAI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Target detection model, method and device applied to hazardous chemical vehicle detection</title><date>2022-11-22</date><risdate>2022</risdate><abstract>According to the target detection model, method and device applied to hazardous chemical vehicle detection, a window pooling multi-head self-attention mechanism is embedded in a window pooling multi-head self-attention module in the scheme, so that the calculation amount is reduced; an offset window pooling multi-head self-attention mechanism solves the defect that information transmission cannot be carried out between windows, and the square calculation complexity of self-attention is reduced; in addition, a high-order space interaction module is introduced to be completely based on high-order space interaction modeling of a convolution structure, a very flexible effect is achieved, various convolution forms can be compatible, and self-attention second-order space interaction modeling can be expanded to any order under the condition that the calculated amount is not remarkably increased.
本申请提出了一种应用于危化品车检测的目标检测模型、方法及装置,该方案的窗口池化多头部自注意力模块嵌入了窗口池化多头部自注意力机制用于减少计算量,且偏移窗口池化多头部自注意力机制解决窗口与窗口之间是无法进行信息传递的弊端,降低了自注意力的平方计算</abstract><oa>free_for_read</oa></addata></record> |
fulltext | fulltext_linktorsrc |
identifier | |
ispartof | |
issn | |
language | chi ; eng |
recordid | cdi_epo_espacenet_CN115375999A |
source | esp@cenet |
subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS |
title | Target detection model, method and device applied to hazardous chemical vehicle detection |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-10T06%3A54%3A49IST&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%20XIANGWEI&rft.date=2022-11-22&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115375999A%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 |