Video Traffic Volume Extraction Based on Onelevel Feature

In this paper, a single-level feature detector network based on YOLOF is built to detect objects and extract traffic volume information for videos. YOLOF does not have a multi-scale feature fusion structure (such as FPN, PAN). It uses the dilated encoder and uniform matching method to replace the fu...

Full description

Saved in:
Bibliographic Details
Main Authors: Teng, Da, Xie, Xingsheng, Sun, Jiejie
Format: Conference Proceeding
Language:English
Subjects:
Backbone
Deep learning
Detectors
Feature extraction
Mechatronics
Sensitivity
Target tracking
traffic volume
Training
Video object detection
Video sequences
Yolof
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1764
container_issue
container_start_page 1760
container_title
container_volume 6
creator Teng, Da
Xie, Xingsheng
Sun, Jiejie
description In this paper, a single-level feature detector network based on YOLOF is built to detect objects and extract traffic volume information for videos. YOLOF does not have a multi-scale feature fusion structure (such as FPN, PAN). It uses the dilated encoder and uniform matching method to replace the fusion feature module, which simplifies the network structure and improves the response time while maintaining good accuracy. Finally, the target tracking algorithm is used to obtain the traffic flow statistics in the video sequence. Generally speaking, YOLOF has higher detection performance and faster speed than RetinaNet, DETR and other networks of similar structure.
doi_str_mv 10.1109/ITOEC53115.2022.9734413
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9734413</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9734413</ieee_id><sourcerecordid>9734413</sourcerecordid><originalsourceid>FETCH-LOGICAL-i482-9e37e0d9cbdc908d9e943405f2a0650e61df66e58fe1431a4c2590ad3977306f3</originalsourceid><addsrcrecordid>eNotj8FKw0AURUdBsNZ-gQvnBxLfzJuZ5C01pFooZBOKuzJm3sBI2kiSiv69Bbu6Z3U4V4hHBblSQE-btqkri0rZXIPWORVojMIrcaecswZVaYtrsdCOMNMlvd-K1TR9AgBqQCppIWiXAg-yHX2MqZO7oT8dWNY_8-i7OQ1H-eInDvIMzZF7_uZertnPp5HvxU30_cSryy5Fu67b6i3bNq-b6nmbJVPqjBgLhkDdR-gIykBMBg3YqD04C-xUiM6xLSOrc683nbYEPiAVBYKLuBQP_9rEzPuvMR38-Lu_HMU_TrBHEg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Video Traffic Volume Extraction Based on Onelevel Feature</title><source>IEEE Xplore All Conference Series</source><creator>Teng, Da ; Xie, Xingsheng ; Sun, Jiejie</creator><creatorcontrib>Teng, Da ; Xie, Xingsheng ; Sun, Jiejie</creatorcontrib><description>In this paper, a single-level feature detector network based on YOLOF is built to detect objects and extract traffic volume information for videos. YOLOF does not have a multi-scale feature fusion structure (such as FPN, PAN). It uses the dilated encoder and uniform matching method to replace the fusion feature module, which simplifies the network structure and improves the response time while maintaining good accuracy. Finally, the target tracking algorithm is used to obtain the traffic flow statistics in the video sequence. Generally speaking, YOLOF has higher detection performance and faster speed than RetinaNet, DETR and other networks of similar structure.</description><identifier>EISSN: 2693-289X</identifier><identifier>EISBN: 1665431857</identifier><identifier>EISBN: 9781665431859</identifier><identifier>DOI: 10.1109/ITOEC53115.2022.9734413</identifier><language>eng</language><publisher>IEEE</publisher><subject>Backbone ; Deep learning ; Detectors ; Feature extraction ; Mechatronics ; Sensitivity ; Target tracking ; traffic volume ; Training ; Video object detection ; Video sequences ; Yolof</subject><ispartof>2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC), 2022, Vol.6, p.1760-1764</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9734413$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,23930,23931,25140,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9734413$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Teng, Da</creatorcontrib><creatorcontrib>Xie, Xingsheng</creatorcontrib><creatorcontrib>Sun, Jiejie</creatorcontrib><title>Video Traffic Volume Extraction Based on Onelevel Feature</title><title>2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)</title><addtitle>ITOEC</addtitle><description>In this paper, a single-level feature detector network based on YOLOF is built to detect objects and extract traffic volume information for videos. YOLOF does not have a multi-scale feature fusion structure (such as FPN, PAN). It uses the dilated encoder and uniform matching method to replace the fusion feature module, which simplifies the network structure and improves the response time while maintaining good accuracy. Finally, the target tracking algorithm is used to obtain the traffic flow statistics in the video sequence. Generally speaking, YOLOF has higher detection performance and faster speed than RetinaNet, DETR and other networks of similar structure.</description><subject>Backbone</subject><subject>Deep learning</subject><subject>Detectors</subject><subject>Feature extraction</subject><subject>Mechatronics</subject><subject>Sensitivity</subject><subject>Target tracking</subject><subject>traffic volume</subject><subject>Training</subject><subject>Video object detection</subject><subject>Video sequences</subject><subject>Yolof</subject><issn>2693-289X</issn><isbn>1665431857</isbn><isbn>9781665431859</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2022</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8FKw0AURUdBsNZ-gQvnBxLfzJuZ5C01pFooZBOKuzJm3sBI2kiSiv69Bbu6Z3U4V4hHBblSQE-btqkri0rZXIPWORVojMIrcaecswZVaYtrsdCOMNMlvd-K1TR9AgBqQCppIWiXAg-yHX2MqZO7oT8dWNY_8-i7OQ1H-eInDvIMzZF7_uZertnPp5HvxU30_cSryy5Fu67b6i3bNq-b6nmbJVPqjBgLhkDdR-gIykBMBg3YqD04C-xUiM6xLSOrc683nbYEPiAVBYKLuBQP_9rEzPuvMR38-Lu_HMU_TrBHEg</recordid><startdate>20220304</startdate><enddate>20220304</enddate><creator>Teng, Da</creator><creator>Xie, Xingsheng</creator><creator>Sun, Jiejie</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20220304</creationdate><title>Video Traffic Volume Extraction Based on Onelevel Feature</title><author>Teng, Da ; Xie, Xingsheng ; Sun, Jiejie</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i482-9e37e0d9cbdc908d9e943405f2a0650e61df66e58fe1431a4c2590ad3977306f3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Backbone</topic><topic>Deep learning</topic><topic>Detectors</topic><topic>Feature extraction</topic><topic>Mechatronics</topic><topic>Sensitivity</topic><topic>Target tracking</topic><topic>traffic volume</topic><topic>Training</topic><topic>Video object detection</topic><topic>Video sequences</topic><topic>Yolof</topic><toplevel>online_resources</toplevel><creatorcontrib>Teng, Da</creatorcontrib><creatorcontrib>Xie, Xingsheng</creatorcontrib><creatorcontrib>Sun, Jiejie</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Teng, Da</au><au>Xie, Xingsheng</au><au>Sun, Jiejie</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Video Traffic Volume Extraction Based on Onelevel Feature</atitle><btitle>2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)</btitle><stitle>ITOEC</stitle><date>2022-03-04</date><risdate>2022</risdate><volume>6</volume><spage>1760</spage><epage>1764</epage><pages>1760-1764</pages><eissn>2693-289X</eissn><eisbn>1665431857</eisbn><eisbn>9781665431859</eisbn><abstract>In this paper, a single-level feature detector network based on YOLOF is built to detect objects and extract traffic volume information for videos. YOLOF does not have a multi-scale feature fusion structure (such as FPN, PAN). It uses the dilated encoder and uniform matching method to replace the fusion feature module, which simplifies the network structure and improves the response time while maintaining good accuracy. Finally, the target tracking algorithm is used to obtain the traffic flow statistics in the video sequence. Generally speaking, YOLOF has higher detection performance and faster speed than RetinaNet, DETR and other networks of similar structure.</abstract><pub>IEEE</pub><doi>10.1109/ITOEC53115.2022.9734413</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2693-289X
ispartof 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC), 2022, Vol.6, p.1760-1764
issn 2693-289X
language eng
recordid cdi_ieee_primary_9734413
source IEEE Xplore All Conference Series
subjects Backbone
Deep learning
Detectors
Feature extraction
Mechatronics
Sensitivity
Target tracking
traffic volume
Training
Video object detection
Video sequences
Yolof
title Video Traffic Volume Extraction Based on Onelevel Feature
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-04T23%3A58%3A22IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Video%20Traffic%20Volume%20Extraction%20Based%20on%20Onelevel%20Feature&rft.btitle=2022%20IEEE%206th%20Information%20Technology%20and%20Mechatronics%20Engineering%20Conference%20(ITOEC)&rft.au=Teng,%20Da&rft.date=2022-03-04&rft.volume=6&rft.spage=1760&rft.epage=1764&rft.pages=1760-1764&rft.eissn=2693-289X&rft_id=info:doi/10.1109/ITOEC53115.2022.9734413&rft.eisbn=1665431857&rft.eisbn_list=9781665431859&rft_dat=%3Cieee_CHZPO%3E9734413%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i482-9e37e0d9cbdc908d9e943405f2a0650e61df66e58fe1431a4c2590ad3977306f3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=9734413&rfr_iscdi=true