Loading…
Optimizing Road Safety: Advancements in Lightweight YOLOv8 Models and GhostC2f Design for Real-Time Distracted Driving Detection
The rapid detection of distracted driving behaviors is crucial for enhancing road safety and preventing traffic accidents. Compared with the traditional methods of distracted-driving-behavior detection, the YOLOv8 model has been proven to possess powerful capabilities, enabling it to perceive global...
Saved in:
Published in: | Sensors (Basel, Switzerland) Switzerland), 2023-10, Vol.23 (21), p.8844 |
---|---|
Main Authors: | , , , |
Format: | Article |
Language: | English |
Subjects: | |
Citations: | Items that this one cites Items that cite this one |
Online Access: | Get full text |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
cited_by | cdi_FETCH-LOGICAL-c430t-7afb76c50a29bec849c017da5c92bcb063c486aeeaacddab32792b3cc09633393 |
---|---|
cites | cdi_FETCH-LOGICAL-c430t-7afb76c50a29bec849c017da5c92bcb063c486aeeaacddab32792b3cc09633393 |
container_end_page | |
container_issue | 21 |
container_start_page | 8844 |
container_title | Sensors (Basel, Switzerland) |
container_volume | 23 |
creator | Du, Yingjie Liu, Xiaofeng Yi, Yuwei Wei, Kun |
description | The rapid detection of distracted driving behaviors is crucial for enhancing road safety and preventing traffic accidents. Compared with the traditional methods of distracted-driving-behavior detection, the YOLOv8 model has been proven to possess powerful capabilities, enabling it to perceive global information more swiftly. Currently, the successful application of GhostConv in edge computing and embedded systems further validates the advantages of lightweight design in real-time detection using large models. Effectively integrating lightweight strategies into YOLOv8 models and reducing their impact on model performance has become a focal point in the field of real-time distracted driving detection based on deep learning. Inspired by GhostConv, this paper presents an innovative GhostC2f design, aiming to integrate the idea of linear transformation to generate more feature maps without additional computation into YOLOv8 for real-time distracted-driving-detection tasks. The goal is to reduce model parameters and computational load. Additionally, enhancements have been made to the path aggregation network (PAN) to amplify multi-level feature fusion and contextual information propagation. Furthermore, simple attention mechanisms (SimAMs) are introduced to perform self-normalization on each feature map, emphasizing feature maps with valuable information and suppressing redundant information interference in complex backgrounds. Lastly, the nine distinct distracted driving types in the publicly available SFDDD dataset were expanded to 14 categories, and nighttime scenarios were introduced. The results indicate a 5.1% improvement in model accuracy, with model weight size and computational load reduced by 36.7% and 34.6%, respectively. During 30 real vehicle tests, the distracted-driving-detection accuracy reached 91.9% during daylight and 90.3% at night, affirming the exceptional performance of the proposed model in assisting distracted driving detection when driving and contributing to accident-risk reduction. |
doi_str_mv | 10.3390/s23218844 |
format | article |
fullrecord | <record><control><sourceid>gale_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_d3c7988c8d674e849d300a7f968c6946</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A772536161</galeid><doaj_id>oai_doaj_org_article_d3c7988c8d674e849d300a7f968c6946</doaj_id><sourcerecordid>A772536161</sourcerecordid><originalsourceid>FETCH-LOGICAL-c430t-7afb76c50a29bec849c017da5c92bcb063c486aeeaacddab32792b3cc09633393</originalsourceid><addsrcrecordid>eNpdUsFu1DAQjRBIlMKBP7DEBQ5pHTsb29xWu6VUWrRSKQdO0cSepF4l9mJ7F5UTn47DVhVClsaj8Zv35llTFG8resG5opeRcVZJWdfPirOqZnUpGaPP_8lfFq9i3FHKOOfyrPi93Sc72V_WDeTWgyFfocf08JEszRGcxgldisQ6srHDffqJcyTft5vtUZIv3uAYCThDru99TCvWkzVGOzjS-0BuEcbyzk5I1jamADqhIetgj7PWGhPqZL17XbzoYYz45vE-L759urpbfS432-ub1XJT6prTVAroO9HoBQWmOtSyVppWwsBCK9bpjjZc17IBRABtDHScifzAtaaqyU4VPy9uTrzGw67dBztBeGg92PZvwYehhZCsHrE1XAslpZamETVmKcMpBdGrRupG1U3men_i2gf_44AxtZONGscRHPpDbJmUSqmaC5mh7_6D7vwhuOx0RkkuBKfzcBcn1ABZ37rez_-Vj8HJau-wt7m-FIIteFM1VW74cGrQwccYsH9yVNF2XoT2aRH4H6CVpDg</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2888377309</pqid></control><display><type>article</type><title>Optimizing Road Safety: Advancements in Lightweight YOLOv8 Models and GhostC2f Design for Real-Time Distracted Driving Detection</title><source>Publicly Available Content Database</source><source>PubMed Central</source><creator>Du, Yingjie ; Liu, Xiaofeng ; Yi, Yuwei ; Wei, Kun</creator><creatorcontrib>Du, Yingjie ; Liu, Xiaofeng ; Yi, Yuwei ; Wei, Kun</creatorcontrib><description>The rapid detection of distracted driving behaviors is crucial for enhancing road safety and preventing traffic accidents. Compared with the traditional methods of distracted-driving-behavior detection, the YOLOv8 model has been proven to possess powerful capabilities, enabling it to perceive global information more swiftly. Currently, the successful application of GhostConv in edge computing and embedded systems further validates the advantages of lightweight design in real-time detection using large models. Effectively integrating lightweight strategies into YOLOv8 models and reducing their impact on model performance has become a focal point in the field of real-time distracted driving detection based on deep learning. Inspired by GhostConv, this paper presents an innovative GhostC2f design, aiming to integrate the idea of linear transformation to generate more feature maps without additional computation into YOLOv8 for real-time distracted-driving-detection tasks. The goal is to reduce model parameters and computational load. Additionally, enhancements have been made to the path aggregation network (PAN) to amplify multi-level feature fusion and contextual information propagation. Furthermore, simple attention mechanisms (SimAMs) are introduced to perform self-normalization on each feature map, emphasizing feature maps with valuable information and suppressing redundant information interference in complex backgrounds. Lastly, the nine distinct distracted driving types in the publicly available SFDDD dataset were expanded to 14 categories, and nighttime scenarios were introduced. The results indicate a 5.1% improvement in model accuracy, with model weight size and computational load reduced by 36.7% and 34.6%, respectively. During 30 real vehicle tests, the distracted-driving-detection accuracy reached 91.9% during daylight and 90.3% at night, affirming the exceptional performance of the proposed model in assisting distracted driving detection when driving and contributing to accident-risk reduction.</description><identifier>ISSN: 1424-8220</identifier><identifier>EISSN: 1424-8220</identifier><identifier>DOI: 10.3390/s23218844</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accuracy ; Algorithms ; attention mechanism ; Behavior ; Comparative analysis ; Datasets ; Deep learning ; Distracted driving ; Embedded systems ; Fatalities ; feature fusion ; Fourier transforms ; GhostConv ; Neural networks ; Physiology ; Processing speed ; Traffic accidents & safety ; YOLOv8n</subject><ispartof>Sensors (Basel, Switzerland), 2023-10, Vol.23 (21), p.8844</ispartof><rights>COPYRIGHT 2023 MDPI AG</rights><rights>2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c430t-7afb76c50a29bec849c017da5c92bcb063c486aeeaacddab32792b3cc09633393</citedby><cites>FETCH-LOGICAL-c430t-7afb76c50a29bec849c017da5c92bcb063c486aeeaacddab32792b3cc09633393</cites><orcidid>0000-0002-3454-6939</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/2888377309/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/2888377309?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,25753,27924,27925,37012,37013,44590,75126</link.rule.ids></links><search><creatorcontrib>Du, Yingjie</creatorcontrib><creatorcontrib>Liu, Xiaofeng</creatorcontrib><creatorcontrib>Yi, Yuwei</creatorcontrib><creatorcontrib>Wei, Kun</creatorcontrib><title>Optimizing Road Safety: Advancements in Lightweight YOLOv8 Models and GhostC2f Design for Real-Time Distracted Driving Detection</title><title>Sensors (Basel, Switzerland)</title><description>The rapid detection of distracted driving behaviors is crucial for enhancing road safety and preventing traffic accidents. Compared with the traditional methods of distracted-driving-behavior detection, the YOLOv8 model has been proven to possess powerful capabilities, enabling it to perceive global information more swiftly. Currently, the successful application of GhostConv in edge computing and embedded systems further validates the advantages of lightweight design in real-time detection using large models. Effectively integrating lightweight strategies into YOLOv8 models and reducing their impact on model performance has become a focal point in the field of real-time distracted driving detection based on deep learning. Inspired by GhostConv, this paper presents an innovative GhostC2f design, aiming to integrate the idea of linear transformation to generate more feature maps without additional computation into YOLOv8 for real-time distracted-driving-detection tasks. The goal is to reduce model parameters and computational load. Additionally, enhancements have been made to the path aggregation network (PAN) to amplify multi-level feature fusion and contextual information propagation. Furthermore, simple attention mechanisms (SimAMs) are introduced to perform self-normalization on each feature map, emphasizing feature maps with valuable information and suppressing redundant information interference in complex backgrounds. Lastly, the nine distinct distracted driving types in the publicly available SFDDD dataset were expanded to 14 categories, and nighttime scenarios were introduced. The results indicate a 5.1% improvement in model accuracy, with model weight size and computational load reduced by 36.7% and 34.6%, respectively. During 30 real vehicle tests, the distracted-driving-detection accuracy reached 91.9% during daylight and 90.3% at night, affirming the exceptional performance of the proposed model in assisting distracted driving detection when driving and contributing to accident-risk reduction.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>attention mechanism</subject><subject>Behavior</subject><subject>Comparative analysis</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Distracted driving</subject><subject>Embedded systems</subject><subject>Fatalities</subject><subject>feature fusion</subject><subject>Fourier transforms</subject><subject>GhostConv</subject><subject>Neural networks</subject><subject>Physiology</subject><subject>Processing speed</subject><subject>Traffic accidents & safety</subject><subject>YOLOv8n</subject><issn>1424-8220</issn><issn>1424-8220</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><sourceid>DOA</sourceid><recordid>eNpdUsFu1DAQjRBIlMKBP7DEBQ5pHTsb29xWu6VUWrRSKQdO0cSepF4l9mJ7F5UTn47DVhVClsaj8Zv35llTFG8resG5opeRcVZJWdfPirOqZnUpGaPP_8lfFq9i3FHKOOfyrPi93Sc72V_WDeTWgyFfocf08JEszRGcxgldisQ6srHDffqJcyTft5vtUZIv3uAYCThDru99TCvWkzVGOzjS-0BuEcbyzk5I1jamADqhIetgj7PWGhPqZL17XbzoYYz45vE-L759urpbfS432-ub1XJT6prTVAroO9HoBQWmOtSyVppWwsBCK9bpjjZc17IBRABtDHScifzAtaaqyU4VPy9uTrzGw67dBztBeGg92PZvwYehhZCsHrE1XAslpZamETVmKcMpBdGrRupG1U3men_i2gf_44AxtZONGscRHPpDbJmUSqmaC5mh7_6D7vwhuOx0RkkuBKfzcBcn1ABZ37rez_-Vj8HJau-wt7m-FIIteFM1VW74cGrQwccYsH9yVNF2XoT2aRH4H6CVpDg</recordid><startdate>20231031</startdate><enddate>20231031</enddate><creator>Du, Yingjie</creator><creator>Liu, Xiaofeng</creator><creator>Yi, Yuwei</creator><creator>Wei, Kun</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>7X8</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-3454-6939</orcidid></search><sort><creationdate>20231031</creationdate><title>Optimizing Road Safety: Advancements in Lightweight YOLOv8 Models and GhostC2f Design for Real-Time Distracted Driving Detection</title><author>Du, Yingjie ; Liu, Xiaofeng ; Yi, Yuwei ; Wei, Kun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c430t-7afb76c50a29bec849c017da5c92bcb063c486aeeaacddab32792b3cc09633393</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>attention mechanism</topic><topic>Behavior</topic><topic>Comparative analysis</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Distracted driving</topic><topic>Embedded systems</topic><topic>Fatalities</topic><topic>feature fusion</topic><topic>Fourier transforms</topic><topic>GhostConv</topic><topic>Neural networks</topic><topic>Physiology</topic><topic>Processing speed</topic><topic>Traffic accidents & safety</topic><topic>YOLOv8n</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Du, Yingjie</creatorcontrib><creatorcontrib>Liu, Xiaofeng</creatorcontrib><creatorcontrib>Yi, Yuwei</creatorcontrib><creatorcontrib>Wei, Kun</creatorcontrib><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>PML(ProQuest Medical Library)</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>MEDLINE - Academic</collection><collection>Directory of Open Access Journals</collection><jtitle>Sensors (Basel, Switzerland)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Du, Yingjie</au><au>Liu, Xiaofeng</au><au>Yi, Yuwei</au><au>Wei, Kun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Optimizing Road Safety: Advancements in Lightweight YOLOv8 Models and GhostC2f Design for Real-Time Distracted Driving Detection</atitle><jtitle>Sensors (Basel, Switzerland)</jtitle><date>2023-10-31</date><risdate>2023</risdate><volume>23</volume><issue>21</issue><spage>8844</spage><pages>8844-</pages><issn>1424-8220</issn><eissn>1424-8220</eissn><abstract>The rapid detection of distracted driving behaviors is crucial for enhancing road safety and preventing traffic accidents. Compared with the traditional methods of distracted-driving-behavior detection, the YOLOv8 model has been proven to possess powerful capabilities, enabling it to perceive global information more swiftly. Currently, the successful application of GhostConv in edge computing and embedded systems further validates the advantages of lightweight design in real-time detection using large models. Effectively integrating lightweight strategies into YOLOv8 models and reducing their impact on model performance has become a focal point in the field of real-time distracted driving detection based on deep learning. Inspired by GhostConv, this paper presents an innovative GhostC2f design, aiming to integrate the idea of linear transformation to generate more feature maps without additional computation into YOLOv8 for real-time distracted-driving-detection tasks. The goal is to reduce model parameters and computational load. Additionally, enhancements have been made to the path aggregation network (PAN) to amplify multi-level feature fusion and contextual information propagation. Furthermore, simple attention mechanisms (SimAMs) are introduced to perform self-normalization on each feature map, emphasizing feature maps with valuable information and suppressing redundant information interference in complex backgrounds. Lastly, the nine distinct distracted driving types in the publicly available SFDDD dataset were expanded to 14 categories, and nighttime scenarios were introduced. The results indicate a 5.1% improvement in model accuracy, with model weight size and computational load reduced by 36.7% and 34.6%, respectively. During 30 real vehicle tests, the distracted-driving-detection accuracy reached 91.9% during daylight and 90.3% at night, affirming the exceptional performance of the proposed model in assisting distracted driving detection when driving and contributing to accident-risk reduction.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/s23218844</doi><orcidid>https://orcid.org/0000-0002-3454-6939</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1424-8220 |
ispartof | Sensors (Basel, Switzerland), 2023-10, Vol.23 (21), p.8844 |
issn | 1424-8220 1424-8220 |
language | eng |
recordid | cdi_doaj_primary_oai_doaj_org_article_d3c7988c8d674e849d300a7f968c6946 |
source | Publicly Available Content Database; PubMed Central |
subjects | Accuracy Algorithms attention mechanism Behavior Comparative analysis Datasets Deep learning Distracted driving Embedded systems Fatalities feature fusion Fourier transforms GhostConv Neural networks Physiology Processing speed Traffic accidents & safety YOLOv8n |
title | Optimizing Road Safety: Advancements in Lightweight YOLOv8 Models and GhostC2f Design for Real-Time Distracted Driving Detection |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T06%3A20%3A20IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Optimizing%20Road%20Safety:%20Advancements%20in%20Lightweight%20YOLOv8%20Models%20and%20GhostC2f%20Design%20for%20Real-Time%20Distracted%20Driving%20Detection&rft.jtitle=Sensors%20(Basel,%20Switzerland)&rft.au=Du,%20Yingjie&rft.date=2023-10-31&rft.volume=23&rft.issue=21&rft.spage=8844&rft.pages=8844-&rft.issn=1424-8220&rft.eissn=1424-8220&rft_id=info:doi/10.3390/s23218844&rft_dat=%3Cgale_doaj_%3EA772536161%3C/gale_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c430t-7afb76c50a29bec849c017da5c92bcb063c486aeeaacddab32792b3cc09633393%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2888377309&rft_id=info:pmid/&rft_galeid=A772536161&rfr_iscdi=true |