Vigilance Monitoring for Safer Driving and Passenger Protection using ML

Anshu Gupta, Harsh Vardhan, Shivani, Rimjhim, Sanya Singh, Sakshi Khandelwal
{"title":"Vigilance Monitoring for Safer Driving and Passenger Protection using ML","authors":"Anshu Gupta, Harsh Vardhan, Shivani, Rimjhim, Sanya Singh, Sakshi Khandelwal","doi":"10.1109/ICCES57224.2023.10192874","DOIUrl":null,"url":null,"abstract":"The main element to be considered before driving is vigilance because failing to do so could endanger safety. According to the Royal Society for the Prevention of Accidents (ROSPA), close to 20% of all traffic accidents are the result of drowsy driving, which is in line with a WHO report that estimates that 1.3 million people die annually because of road accidents. The passengers’ safety is equally vital to the drivers; however, in today's online taxi and cab systems, passengers have no idea whether or not the cab they are in is safe, in terms of the driver's alert and vigilant state, or it may put them in danger. If the passenger is unaware of the driver's condition while driving, they put themselves at risk. Yet, many drivers operate their vehicles continuously without stopping, leaving the passenger in the dark about his level of attention while driving. Nonetheless, for a long time, many people have been researching drowsiness detecting systems. In many earlier research works, algorithms, particular factors, and various machine learning models are created to provide the best and most accurate results. This research will be comparing various algorithms and models developed and inherited from earlier works to determine which algorithm can perform better in each situation. These factors include face detection, face landmark predictor, which includes eye aspect ratio calculation, and the investigation of whether the driver is lethargic, making use of an alarm system that will sound to inform both the driver and the passenger to the driver's level of alertness or drowsiness that could help the passenger decide whether it is safe to continue the ride or to halt it and find another.","PeriodicalId":442189,"journal":{"name":"2023 8th International Conference on Communication and Electronics Systems (ICCES)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 8th International Conference on Communication and Electronics Systems (ICCES)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCES57224.2023.10192874","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

The main element to be considered before driving is vigilance because failing to do so could endanger safety. According to the Royal Society for the Prevention of Accidents (ROSPA), close to 20% of all traffic accidents are the result of drowsy driving, which is in line with a WHO report that estimates that 1.3 million people die annually because of road accidents. The passengers’ safety is equally vital to the drivers; however, in today's online taxi and cab systems, passengers have no idea whether or not the cab they are in is safe, in terms of the driver's alert and vigilant state, or it may put them in danger. If the passenger is unaware of the driver's condition while driving, they put themselves at risk. Yet, many drivers operate their vehicles continuously without stopping, leaving the passenger in the dark about his level of attention while driving. Nonetheless, for a long time, many people have been researching drowsiness detecting systems. In many earlier research works, algorithms, particular factors, and various machine learning models are created to provide the best and most accurate results. This research will be comparing various algorithms and models developed and inherited from earlier works to determine which algorithm can perform better in each situation. These factors include face detection, face landmark predictor, which includes eye aspect ratio calculation, and the investigation of whether the driver is lethargic, making use of an alarm system that will sound to inform both the driver and the passenger to the driver's level of alertness or drowsiness that could help the passenger decide whether it is safe to continue the ride or to halt it and find another.
基于机器学习的安全驾驶和乘客保护警惕性监测
开车前要考虑的主要因素是警惕,因为不这样做可能会危及安全。据英国皇家预防事故学会(ROSPA)称,所有交通事故中有近20%是由于疲劳驾驶造成的,这与世卫组织的一份报告相符,该报告估计每年有130万人死于交通事故。乘客的安全对司机来说同样重要;然而,在今天的在线出租车和出租车系统中,乘客不知道他们所乘坐的出租车是否安全,从司机的警觉和警惕状态来看,或者可能会使他们处于危险之中。如果乘客在开车时不知道司机的状况,他们就会把自己置于危险之中。然而,许多司机不停地开车,让乘客不知道他在开车时的注意力水平。尽管如此,长期以来,许多人一直在研究睡意检测系统。在许多早期的研究工作中,算法、特定因素和各种机器学习模型都是为了提供最好和最准确的结果而创建的。本研究将比较从早期工作中发展和继承的各种算法和模型,以确定哪种算法在每种情况下表现更好。这些因素包括面部检测,面部地标预测器,其中包括眼睛宽高比计算,以及调查司机是否昏昏欲睡,利用警报系统,将声音告知司机和乘客司机的警觉或困倦水平,可以帮助乘客决定是否安全继续骑行或停止它并找到另一个。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信