基于视觉注意映射和深度卷积神经网络的图像碰撞风险预测模型

IF 2.4 3区 工程技术 Q3 TRANSPORTATION Journal of Transportation Safety & Security Pub Date : 2021-12-28 DOI:10.1080/19439962.2021.2015731
Chengyu Hu, Wenchen Yang, Chenglong Liu, Rui Fang, Zhongyin Guo, Bijiang Tian
{"title":"基于视觉注意映射和深度卷积神经网络的图像碰撞风险预测模型","authors":"Chengyu Hu, Wenchen Yang, Chenglong Liu, Rui Fang, Zhongyin Guo, Bijiang Tian","doi":"10.1080/19439962.2021.2015731","DOIUrl":null,"url":null,"abstract":"Abstract Crash risk prediction plays a pivotal role in traffic management and infrastructure optimization. Previous research has studied the relationship between crashes and multiple factors using statistical methods. As both drivers’ attention and environmental complexity substantially affect traffic safety, this article presents a novel method to predict crash risk proactively by combining these two interactive factors. More than 200 high-risk zones and 300 noncrash zones were screened out through social media data. Corresponding environmental information was collected using the street view map. Spectral saliency mapping was applied to depict the driver’s attention distribution toward images. A DeepLabV3 pretrained network was implemented to label the semantic features in the environment. A featured vector was then constructed by fuzing the visual attention model and image semantics. The gradient boosting decision tree algorithm was applied to analyze the relationship between the multitype crash data and featured vectors. The results showed that the accuracy of the proposed method for detecting different types of crashes was over 0.81. Dynamic objects are the most substantial factors that affect crash possibility and categories. Traffic signals are vulnerable to drivers’ attention, which may be easily overlooked. The proposed method provides new insights into understanding traffic crash risk, which can help us predict different types of crashes more effectively.","PeriodicalId":46672,"journal":{"name":"Journal of Transportation Safety & Security","volume":null,"pages":null},"PeriodicalIF":2.4000,"publicationDate":"2021-12-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"An image-based crash risk prediction model using visual attention mapping and a deep convolutional neural network\",\"authors\":\"Chengyu Hu, Wenchen Yang, Chenglong Liu, Rui Fang, Zhongyin Guo, Bijiang Tian\",\"doi\":\"10.1080/19439962.2021.2015731\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Crash risk prediction plays a pivotal role in traffic management and infrastructure optimization. Previous research has studied the relationship between crashes and multiple factors using statistical methods. As both drivers’ attention and environmental complexity substantially affect traffic safety, this article presents a novel method to predict crash risk proactively by combining these two interactive factors. More than 200 high-risk zones and 300 noncrash zones were screened out through social media data. Corresponding environmental information was collected using the street view map. Spectral saliency mapping was applied to depict the driver’s attention distribution toward images. A DeepLabV3 pretrained network was implemented to label the semantic features in the environment. A featured vector was then constructed by fuzing the visual attention model and image semantics. The gradient boosting decision tree algorithm was applied to analyze the relationship between the multitype crash data and featured vectors. The results showed that the accuracy of the proposed method for detecting different types of crashes was over 0.81. Dynamic objects are the most substantial factors that affect crash possibility and categories. Traffic signals are vulnerable to drivers’ attention, which may be easily overlooked. The proposed method provides new insights into understanding traffic crash risk, which can help us predict different types of crashes more effectively.\",\"PeriodicalId\":46672,\"journal\":{\"name\":\"Journal of Transportation Safety & Security\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2021-12-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Transportation Safety & Security\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1080/19439962.2021.2015731\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"TRANSPORTATION\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Transportation Safety & Security","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1080/19439962.2021.2015731","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"TRANSPORTATION","Score":null,"Total":0}
引用次数: 1

摘要

碰撞风险预测在交通管理和基础设施优化中起着至关重要的作用。以往的研究使用统计方法研究了车祸与多因素之间的关系。由于驾驶员的注意力和环境复杂性对交通安全都有重要影响,本文提出了一种将驾驶员注意力和环境复杂性相结合的前瞻性碰撞风险预测方法。通过社交媒体数据筛选出200多个高风险区域和300多个非事故区域。利用街景地图收集相应的环境信息。采用光谱显著性映射来描述驾驶员对图像的注意分布。采用DeepLabV3预训练网络对环境中的语义特征进行标注。然后将视觉注意模型与图像语义相融合,构造特征向量。采用梯度增强决策树算法分析多类型碰撞数据与特征向量之间的关系。结果表明,该方法检测不同类型碰撞的准确率均在0.81以上。动态对象是影响碰撞可能性和类别的最重要因素。交通信号很容易引起司机的注意,这一点很容易被忽视。该方法为理解交通事故风险提供了新的视角,可以帮助我们更有效地预测不同类型的交通事故。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
An image-based crash risk prediction model using visual attention mapping and a deep convolutional neural network
Abstract Crash risk prediction plays a pivotal role in traffic management and infrastructure optimization. Previous research has studied the relationship between crashes and multiple factors using statistical methods. As both drivers’ attention and environmental complexity substantially affect traffic safety, this article presents a novel method to predict crash risk proactively by combining these two interactive factors. More than 200 high-risk zones and 300 noncrash zones were screened out through social media data. Corresponding environmental information was collected using the street view map. Spectral saliency mapping was applied to depict the driver’s attention distribution toward images. A DeepLabV3 pretrained network was implemented to label the semantic features in the environment. A featured vector was then constructed by fuzing the visual attention model and image semantics. The gradient boosting decision tree algorithm was applied to analyze the relationship between the multitype crash data and featured vectors. The results showed that the accuracy of the proposed method for detecting different types of crashes was over 0.81. Dynamic objects are the most substantial factors that affect crash possibility and categories. Traffic signals are vulnerable to drivers’ attention, which may be easily overlooked. The proposed method provides new insights into understanding traffic crash risk, which can help us predict different types of crashes more effectively.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
6.00
自引率
15.40%
发文量
38
期刊最新文献
Examining the crash risk factors associated with cycling by considering spatial and temporal disaggregation of exposure: Findings from four Dutch cities Traffic safety performance evaluation in a connected vehicle environment with queue warning and speed harmonization applications Enhancing bicyclist survival time in fatal crashes: Investigating the impact of faster crash notification time through explainable machine learning Factors affecting pedestrian injury severity in pedestrian-vehicle crashes: Insights from a data mining and mixed logit model approach Prediction of high-risk bus drivers characterized by aggressive driving behavior
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1