Night pedestrian detection method

Night pedestrian detection method

According to the night pedestrian detection method provided by the invention, partial details are improved based on an existing YOLOv5 algorithm network structure, so that the network has better detection performance, and the precision and speed of a fusion algorithm are further ensured. According t...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: SONG YUNQING, WANG TINGTING, ZHAO WEI
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
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 SONG YUNQING
WANG TINGTING
ZHAO WEI
description According to the night pedestrian detection method provided by the invention, partial details are improved based on an existing YOLOv5 algorithm network structure, so that the network has better detection performance, and the precision and speed of a fusion algorithm are further ensured. According to the method, the radar initial data are preprocessed, interference of invalid targets on the radar data is reduced, the algorithm operation speed is improved, the radar data are detected and tracked by adopting the unscented Kalman filtering algorithm, the radar detection false alarm rate is reduced, and the reliability and stability of the radar data are improved. In order to solve the problem that a single sensor cannot accurately obtain comprehensive state information of a night pedestrian target, the performance advantages of the infrared camera and the millimeter wave radar are fully utilized, and the situations of missing detection, false detection and the like of the single sensor on the target detection pe
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116469077A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116469077A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116469077A3</originalsourceid><addsrcrecordid>eNrjZFD0y0zPKFEoSE1JLS4pykzMU0hJLUlNLsnMz1PITS3JyE_hYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxzn6GhmYmZpYG5uaOxsSoAQCVvCXj</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Night pedestrian detection method</title><source>esp@cenet</source><creator>SONG YUNQING ; WANG TINGTING ; ZHAO WEI</creator><creatorcontrib>SONG YUNQING ; WANG TINGTING ; ZHAO WEI</creatorcontrib><description>According to the night pedestrian detection method provided by the invention, partial details are improved based on an existing YOLOv5 algorithm network structure, so that the network has better detection performance, and the precision and speed of a fusion algorithm are further ensured. According to the method, the radar initial data are preprocessed, interference of invalid targets on the radar data is reduced, the algorithm operation speed is improved, the radar data are detected and tracked by adopting the unscented Kalman filtering algorithm, the radar detection false alarm rate is reduced, and the reliability and stability of the radar data are improved. In order to solve the problem that a single sensor cannot accurately obtain comprehensive state information of a night pedestrian target, the performance advantages of the infrared camera and the millimeter wave radar are fully utilized, and the situations of missing detection, false detection and the like of the single sensor on the target detection pe</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&amp;date=20230721&amp;DB=EPODOC&amp;CC=CN&amp;NR=116469077A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230721&amp;DB=EPODOC&amp;CC=CN&amp;NR=116469077A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>SONG YUNQING</creatorcontrib><creatorcontrib>WANG TINGTING</creatorcontrib><creatorcontrib>ZHAO WEI</creatorcontrib><title>Night pedestrian detection method</title><description>According to the night pedestrian detection method provided by the invention, partial details are improved based on an existing YOLOv5 algorithm network structure, so that the network has better detection performance, and the precision and speed of a fusion algorithm are further ensured. According to the method, the radar initial data are preprocessed, interference of invalid targets on the radar data is reduced, the algorithm operation speed is improved, the radar data are detected and tracked by adopting the unscented Kalman filtering algorithm, the radar detection false alarm rate is reduced, and the reliability and stability of the radar data are improved. In order to solve the problem that a single sensor cannot accurately obtain comprehensive state information of a night pedestrian target, the performance advantages of the infrared camera and the millimeter wave radar are fully utilized, and the situations of missing detection, false detection and the like of the single sensor on the target detection pe</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>eNrjZFD0y0zPKFEoSE1JLS4pykzMU0hJLUlNLsnMz1PITS3JyE_hYWBNS8wpTuWF0twMim6uIc4euqkF-fGpxQWJyal5qSXxzn6GhmYmZpYG5uaOxsSoAQCVvCXj</recordid><startdate>20230721</startdate><enddate>20230721</enddate><creator>SONG YUNQING</creator><creator>WANG TINGTING</creator><creator>ZHAO WEI</creator><scope>EVB</scope></search><sort><creationdate>20230721</creationdate><title>Night pedestrian detection method</title><author>SONG YUNQING ; WANG TINGTING ; ZHAO WEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116469077A3</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>SONG YUNQING</creatorcontrib><creatorcontrib>WANG TINGTING</creatorcontrib><creatorcontrib>ZHAO WEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>SONG YUNQING</au><au>WANG TINGTING</au><au>ZHAO WEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Night pedestrian detection method</title><date>2023-07-21</date><risdate>2023</risdate><abstract>According to the night pedestrian detection method provided by the invention, partial details are improved based on an existing YOLOv5 algorithm network structure, so that the network has better detection performance, and the precision and speed of a fusion algorithm are further ensured. According to the method, the radar initial data are preprocessed, interference of invalid targets on the radar data is reduced, the algorithm operation speed is improved, the radar data are detected and tracked by adopting the unscented Kalman filtering algorithm, the radar detection false alarm rate is reduced, and the reliability and stability of the radar data are improved. In order to solve the problem that a single sensor cannot accurately obtain comprehensive state information of a night pedestrian target, the performance advantages of the infrared camera and the millimeter wave radar are fully utilized, and the situations of missing detection, false detection and the like of the single sensor on the target detection pe</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116469077A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Night pedestrian detection method
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T19%3A53%3A56IST&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=SONG%20YUNQING&rft.date=2023-07-21&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116469077A%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