Dangerous Driving Behavior Detection Based on Multi-source Information Fusion

Dangerous driving does great harm to traffic safety. A dangerous driving detection model was proposed based on multi-source information fusion in this paper. The information fusion model includes face fatigue features and distracted driving features, which are related to dangerous driving. Firstly,...

Full description

Saved in:
Bibliographic Details
Main Authors: Cai, Jianfeng, Bai, Junjie, Zhou, Taoqi, Gao, Shuai, Li, Jiajie, Bai, Junbo
Format: Conference Proceeding
Language:English
Subjects:
Behavioral sciences
D-SET
Distracted driving
Fatigue
Fatigue driving
Information fusion
Libraries
Mobile handsets
Mouth
Robustness
Technological innovation
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 370
container_issue
container_start_page 366
container_title
container_volume
creator Cai, Jianfeng
Bai, Junjie
Zhou, Taoqi
Gao, Shuai
Li, Jiajie
Bai, Junbo
description Dangerous driving does great harm to traffic safety. A dangerous driving detection model was proposed based on multi-source information fusion in this paper. The information fusion model includes face fatigue features and distracted driving features, which are related to dangerous driving. Firstly, according to the characteristics of face fatigue, OpenCV and Dlib library are used to detect the blink rate, yawning behavior and head posture offset. The characteristics of face fatigue are comprehensively determined by calculating EAR (Eye Aspect Ratio), MAR (Mouth Aspect Ratio) and head posture offset. Then, distracted driving behavior includes making phone call, drinking water and looking at mobile phone, which are detected by the algorithm of improved YOLO-V5. Finally, the features of fatigue and distraction are fused, which is based on D-SET algorithm. The innovation of the paper is to fuse the features of different detection objects to improve the model detection effect. Compared with detecting two single indicators respectively, the accuracy of the algorithms fusion model for dangerous driving detection is improved by 4.8%, and the system response time is also faster by 0.53 seconds. Ultimately, the experimental results show that the model fusion algorithm effectively alleviates the problem of inaccurate detection caused by single information, and improves the accuracy of detection and the robustness of the system.
doi_str_mv 10.1109/BigDIA56350.2022.9874197
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9874197</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9874197</ieee_id><sourcerecordid>9874197</sourcerecordid><originalsourceid>FETCH-LOGICAL-i482-36a785148c25b3d91ee6feb48fba3acd319088119dcbde7456b2a5fed656af3a3</originalsourceid><addsrcrecordid>eNotj8tKw0AYRkdBsNQ8gZt5gcS5X5ZNYzXQ4qb7Msn8E0faRGaagm9v0a7Otzh8cBDClFSUEvtSx6FpV1JxSSpGGKus0YJafYcKqw1VSgqjrWL3aMG0pqWyhD2iIucvQghnRBDJFmjXuHGANM0ZNyle4jjgGj7dJU4JN3CG_hynEdcug8fXsZuP51jmaU494HYMUzq5P2Mz5yue0ENwxwzFjUu037zu1-_l9uOtXa-2ZRSGlVw5bSQVpmey495SABWgEyZ0jrvec2qJMZRa33cetJCqY04G8EoqF7jjS_T8fxsB4PCd4smln8Otn_8C0upRFQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Dangerous Driving Behavior Detection Based on Multi-source Information Fusion</title><source>IEEE Xplore All Conference Series</source><creator>Cai, Jianfeng ; Bai, Junjie ; Zhou, Taoqi ; Gao, Shuai ; Li, Jiajie ; Bai, Junbo</creator><creatorcontrib>Cai, Jianfeng ; Bai, Junjie ; Zhou, Taoqi ; Gao, Shuai ; Li, Jiajie ; Bai, Junbo</creatorcontrib><description>Dangerous driving does great harm to traffic safety. A dangerous driving detection model was proposed based on multi-source information fusion in this paper. The information fusion model includes face fatigue features and distracted driving features, which are related to dangerous driving. Firstly, according to the characteristics of face fatigue, OpenCV and Dlib library are used to detect the blink rate, yawning behavior and head posture offset. The characteristics of face fatigue are comprehensively determined by calculating EAR (Eye Aspect Ratio), MAR (Mouth Aspect Ratio) and head posture offset. Then, distracted driving behavior includes making phone call, drinking water and looking at mobile phone, which are detected by the algorithm of improved YOLO-V5. Finally, the features of fatigue and distraction are fused, which is based on D-SET algorithm. The innovation of the paper is to fuse the features of different detection objects to improve the model detection effect. Compared with detecting two single indicators respectively, the accuracy of the algorithms fusion model for dangerous driving detection is improved by 4.8%, and the system response time is also faster by 0.53 seconds. Ultimately, the experimental results show that the model fusion algorithm effectively alleviates the problem of inaccurate detection caused by single information, and improves the accuracy of detection and the robustness of the system.</description><identifier>EISSN: 2771-6902</identifier><identifier>EISBN: 9781665487962</identifier><identifier>EISBN: 1665487968</identifier><identifier>DOI: 10.1109/BigDIA56350.2022.9874197</identifier><language>eng</language><publisher>IEEE</publisher><subject>Behavioral sciences ; D-SET ; Distracted driving ; Fatigue ; Fatigue driving ; Information fusion ; Libraries ; Mobile handsets ; Mouth ; Robustness ; Technological innovation</subject><ispartof>2022 8th International Conference on Big Data and Information Analytics (BigDIA), 2022, p.366-370</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/9874197$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>310,311,786,790,795,796,27958,54906,55283</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9874197$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Cai, Jianfeng</creatorcontrib><creatorcontrib>Bai, Junjie</creatorcontrib><creatorcontrib>Zhou, Taoqi</creatorcontrib><creatorcontrib>Gao, Shuai</creatorcontrib><creatorcontrib>Li, Jiajie</creatorcontrib><creatorcontrib>Bai, Junbo</creatorcontrib><title>Dangerous Driving Behavior Detection Based on Multi-source Information Fusion</title><title>2022 8th International Conference on Big Data and Information Analytics (BigDIA)</title><addtitle>BIGDIA</addtitle><description>Dangerous driving does great harm to traffic safety. A dangerous driving detection model was proposed based on multi-source information fusion in this paper. The information fusion model includes face fatigue features and distracted driving features, which are related to dangerous driving. Firstly, according to the characteristics of face fatigue, OpenCV and Dlib library are used to detect the blink rate, yawning behavior and head posture offset. The characteristics of face fatigue are comprehensively determined by calculating EAR (Eye Aspect Ratio), MAR (Mouth Aspect Ratio) and head posture offset. Then, distracted driving behavior includes making phone call, drinking water and looking at mobile phone, which are detected by the algorithm of improved YOLO-V5. Finally, the features of fatigue and distraction are fused, which is based on D-SET algorithm. The innovation of the paper is to fuse the features of different detection objects to improve the model detection effect. Compared with detecting two single indicators respectively, the accuracy of the algorithms fusion model for dangerous driving detection is improved by 4.8%, and the system response time is also faster by 0.53 seconds. Ultimately, the experimental results show that the model fusion algorithm effectively alleviates the problem of inaccurate detection caused by single information, and improves the accuracy of detection and the robustness of the system.</description><subject>Behavioral sciences</subject><subject>D-SET</subject><subject>Distracted driving</subject><subject>Fatigue</subject><subject>Fatigue driving</subject><subject>Information fusion</subject><subject>Libraries</subject><subject>Mobile handsets</subject><subject>Mouth</subject><subject>Robustness</subject><subject>Technological innovation</subject><issn>2771-6902</issn><isbn>9781665487962</isbn><isbn>1665487968</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2022</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj8tKw0AYRkdBsNQ8gZt5gcS5X5ZNYzXQ4qb7Msn8E0faRGaagm9v0a7Otzh8cBDClFSUEvtSx6FpV1JxSSpGGKus0YJafYcKqw1VSgqjrWL3aMG0pqWyhD2iIucvQghnRBDJFmjXuHGANM0ZNyle4jjgGj7dJU4JN3CG_hynEdcug8fXsZuP51jmaU494HYMUzq5P2Mz5yue0ENwxwzFjUu037zu1-_l9uOtXa-2ZRSGlVw5bSQVpmey495SABWgEyZ0jrvec2qJMZRa33cetJCqY04G8EoqF7jjS_T8fxsB4PCd4smln8Otn_8C0upRFQ</recordid><startdate>20220824</startdate><enddate>20220824</enddate><creator>Cai, Jianfeng</creator><creator>Bai, Junjie</creator><creator>Zhou, Taoqi</creator><creator>Gao, Shuai</creator><creator>Li, Jiajie</creator><creator>Bai, Junbo</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20220824</creationdate><title>Dangerous Driving Behavior Detection Based on Multi-source Information Fusion</title><author>Cai, Jianfeng ; Bai, Junjie ; Zhou, Taoqi ; Gao, Shuai ; Li, Jiajie ; Bai, Junbo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i482-36a785148c25b3d91ee6feb48fba3acd319088119dcbde7456b2a5fed656af3a3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Behavioral sciences</topic><topic>D-SET</topic><topic>Distracted driving</topic><topic>Fatigue</topic><topic>Fatigue driving</topic><topic>Information fusion</topic><topic>Libraries</topic><topic>Mobile handsets</topic><topic>Mouth</topic><topic>Robustness</topic><topic>Technological innovation</topic><toplevel>online_resources</toplevel><creatorcontrib>Cai, Jianfeng</creatorcontrib><creatorcontrib>Bai, Junjie</creatorcontrib><creatorcontrib>Zhou, Taoqi</creatorcontrib><creatorcontrib>Gao, Shuai</creatorcontrib><creatorcontrib>Li, Jiajie</creatorcontrib><creatorcontrib>Bai, Junbo</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 Xplore</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>Cai, Jianfeng</au><au>Bai, Junjie</au><au>Zhou, Taoqi</au><au>Gao, Shuai</au><au>Li, Jiajie</au><au>Bai, Junbo</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Dangerous Driving Behavior Detection Based on Multi-source Information Fusion</atitle><btitle>2022 8th International Conference on Big Data and Information Analytics (BigDIA)</btitle><stitle>BIGDIA</stitle><date>2022-08-24</date><risdate>2022</risdate><spage>366</spage><epage>370</epage><pages>366-370</pages><eissn>2771-6902</eissn><eisbn>9781665487962</eisbn><eisbn>1665487968</eisbn><abstract>Dangerous driving does great harm to traffic safety. A dangerous driving detection model was proposed based on multi-source information fusion in this paper. The information fusion model includes face fatigue features and distracted driving features, which are related to dangerous driving. Firstly, according to the characteristics of face fatigue, OpenCV and Dlib library are used to detect the blink rate, yawning behavior and head posture offset. The characteristics of face fatigue are comprehensively determined by calculating EAR (Eye Aspect Ratio), MAR (Mouth Aspect Ratio) and head posture offset. Then, distracted driving behavior includes making phone call, drinking water and looking at mobile phone, which are detected by the algorithm of improved YOLO-V5. Finally, the features of fatigue and distraction are fused, which is based on D-SET algorithm. The innovation of the paper is to fuse the features of different detection objects to improve the model detection effect. Compared with detecting two single indicators respectively, the accuracy of the algorithms fusion model for dangerous driving detection is improved by 4.8%, and the system response time is also faster by 0.53 seconds. Ultimately, the experimental results show that the model fusion algorithm effectively alleviates the problem of inaccurate detection caused by single information, and improves the accuracy of detection and the robustness of the system.</abstract><pub>IEEE</pub><doi>10.1109/BigDIA56350.2022.9874197</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2771-6902
ispartof 2022 8th International Conference on Big Data and Information Analytics (BigDIA), 2022, p.366-370
issn 2771-6902
language eng
recordid cdi_ieee_primary_9874197
source IEEE Xplore All Conference Series
subjects Behavioral sciences
D-SET
Distracted driving
Fatigue
Fatigue driving
Information fusion
Libraries
Mobile handsets
Mouth
Robustness
Technological innovation
title Dangerous Driving Behavior Detection Based on Multi-source Information Fusion
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-10-01T13%3A43%3A38IST&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=Dangerous%20Driving%20Behavior%20Detection%20Based%20on%20Multi-source%20Information%20Fusion&rft.btitle=2022%208th%20International%20Conference%20on%20Big%20Data%20and%20Information%20Analytics%20(BigDIA)&rft.au=Cai,%20Jianfeng&rft.date=2022-08-24&rft.spage=366&rft.epage=370&rft.pages=366-370&rft.eissn=2771-6902&rft_id=info:doi/10.1109/BigDIA56350.2022.9874197&rft.eisbn=9781665487962&rft.eisbn_list=1665487968&rft_dat=%3Cieee_CHZPO%3E9874197%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i482-36a785148c25b3d91ee6feb48fba3acd319088119dcbde7456b2a5fed656af3a3%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=9874197&rfr_iscdi=true