• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

利用多种深度学习和街景图像识别和改进非机动化交通中的危险场景。

Identification and Improvement of Hazard Scenarios in Non-Motorized Transportation Using Multiple Deep Learning and Street View Images.

机构信息

School of Architecture and Urban Planning, Nanjing University, Nanjing 210093, China.

School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen 518107, China.

出版信息

Int J Environ Res Public Health. 2022 Oct 28;19(21):14054. doi: 10.3390/ijerph192114054.

DOI:10.3390/ijerph192114054
PMID:36360941
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9658839/
Abstract

In the prioritized vehicle traffic environment, motorized transportation has been obtaining more spatial and economic resources, posing potential threats to the travel quality and life safety of non-motorized transportation participants. It is becoming urgent to improve the safety situation of non-motorized transportation participants. Most previous studies have focused on the psychological aspects of pedestrians and cyclists exposed to the actual road environment rather than quantifying the objective safety hazards, which has led to a non-rigorous evaluation of their basic safety situation. An integrated processing approach is proposed to comprehensively and objectively evaluate the overall safety level of non-motorized transportation participants on each road segment. Our main contributions include (1) the universal approach is established to automatically identify hazard scenarios related to non-motorized transportation and their direct causing factors from street view images based on multiple deep learning models; (2) a seed points spreading algorithm is designed to convert semantic images into target detection results with detail contour, which breaks the functional limitation of these two types of methods to a certain extent; (3) The safety situation of non-motorized transportation on various road sections in Gulou District, Nanjing, China has been evaluated and based on this, a series of suggestions have been put forward to guide the better adaptation among multiple transportation participants.

摘要

在优先考虑机动车交通的环境中，机动化交通获得了更多的空间和经济资源，这对非机动化交通参与者的出行质量和生命安全构成了潜在威胁。提高非机动化交通参与者的安全状况变得尤为紧迫。以往的大多数研究都集中在实际道路环境中暴露的行人和骑车人心理方面，而不是量化客观的安全危害，这导致对其基本安全状况的评估不够严谨。提出了一种综合处理方法，以全面、客观地评估每个路段上非机动化交通参与者的整体安全水平。我们的主要贡献包括：（1）建立了一种通用方法，基于多个深度学习模型，从街景图像中自动识别与非机动化交通相关的危险场景及其直接原因；（2）设计了一种种子点扩展算法，将语义图像转换为具有细节轮廓的目标检测结果，在一定程度上突破了这两种方法的功能限制；（3）评估了中国南京市鼓楼区各路段的非机动化交通安全状况，并在此基础上提出了一系列建议，以指导多种交通参与者的更好适应。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/be15c2949ebd/ijerph-19-14054-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/d66ba24d6bf6/ijerph-19-14054-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/567bc4dfc713/ijerph-19-14054-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/3926a7b442da/ijerph-19-14054-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/1409fcd91911/ijerph-19-14054-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/f07ac7c85b82/ijerph-19-14054-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/eb0e65a76c64/ijerph-19-14054-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/b2ce7b163a25/ijerph-19-14054-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/80bbdb5b6fa6/ijerph-19-14054-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/f78b5a2b99c6/ijerph-19-14054-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/014d5741aff3/ijerph-19-14054-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/287dfcfd279f/ijerph-19-14054-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/ca3dd2ed7672/ijerph-19-14054-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/2fc43e0a2cc9/ijerph-19-14054-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/8c6c4968a260/ijerph-19-14054-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/50fd8e5b6217/ijerph-19-14054-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/3b7fc5ec2b8c/ijerph-19-14054-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/e97be65663a9/ijerph-19-14054-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/6312963eda68/ijerph-19-14054-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/c92b1e6005da/ijerph-19-14054-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/be15c2949ebd/ijerph-19-14054-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/d66ba24d6bf6/ijerph-19-14054-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/567bc4dfc713/ijerph-19-14054-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/3926a7b442da/ijerph-19-14054-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/1409fcd91911/ijerph-19-14054-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/f07ac7c85b82/ijerph-19-14054-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/eb0e65a76c64/ijerph-19-14054-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/b2ce7b163a25/ijerph-19-14054-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/80bbdb5b6fa6/ijerph-19-14054-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/f78b5a2b99c6/ijerph-19-14054-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/014d5741aff3/ijerph-19-14054-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/287dfcfd279f/ijerph-19-14054-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/ca3dd2ed7672/ijerph-19-14054-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/2fc43e0a2cc9/ijerph-19-14054-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/8c6c4968a260/ijerph-19-14054-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/50fd8e5b6217/ijerph-19-14054-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/3b7fc5ec2b8c/ijerph-19-14054-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/e97be65663a9/ijerph-19-14054-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/6312963eda68/ijerph-19-14054-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/c92b1e6005da/ijerph-19-14054-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/b1c5/9658839/be15c2949ebd/ijerph-19-14054-g020.jpg

相似文献

1
Identification and Improvement of Hazard Scenarios in Non-Motorized Transportation Using Multiple Deep Learning and Street View Images.利用多种深度学习和街景图像识别和改进非机动化交通中的危险场景。
Int J Environ Res Public Health. 2022 Oct 28;19(21):14054. doi: 10.3390/ijerph192114054.
2
Pedestrians' Perceptions of Motorized Traffic Variables in Relation to Appraisals of Urban Route Environments.行人和骑车人对与城市道路环境评估有关的机动车交通变量的感知。
Int J Environ Res Public Health. 2023 Feb 20;20(4):3743. doi: 10.3390/ijerph20043743.
3
Enhancing non-motorist safety by simulating trip exposure using a transportation planning approach.运用交通规划方法模拟出行暴露，以提高非机动化出行者安全。
Accid Anal Prev. 2021 Jun;156:106128. doi: 10.1016/j.aap.2021.106128. Epub 2021 Apr 26.
4
Left-turning vehicle-pedestrian conflicts at signalized intersections with traffic lights: Benefit or harm? A two-stage study.设有交通信号灯的交叉路口处左转车辆与行人的冲突：是利还是弊？一项分两阶段的研究。
Chin J Traumatol. 2019 Apr;22(2):63-68. doi: 10.1016/j.cjtee.2018.07.007. Epub 2019 Mar 11.
5
Traveling by Bus Instead of Car on Urban Major Roads: Safety Benefits for Vehicle Occupants, Pedestrians, and Cyclists.在城市主要道路上乘坐公共汽车而非汽车出行：对车辆乘客、行人和骑自行车者的安全益处。
J Urban Health. 2018 Apr;95(2):196-207. doi: 10.1007/s11524-017-0222-6.
6
Virtual testing of speed reduction schemes on urban collector roads.城市集束道路减速方案的虚拟测试。
Accid Anal Prev. 2018 Jan;110:38-51. doi: 10.1016/j.aap.2017.09.020. Epub 2017 Nov 6.
7
[The significance of the results of crash-tests with the use of the models of the pedestrians' lower extremities for the prevention of the traffic road accidents].[使用行人下肢模型进行碰撞测试结果对预防交通事故的意义]
Sud Med Ekspert. 2017;60(3):13-18. doi: 10.17116/sudmed201760313-18.
8
Investigating factors affecting riders' behaviors of occupying motorized vehicle lanes on urban streets.研究影响城市街道摩托车骑行者占用机动车道行为的因素。
Accid Anal Prev. 2019 Jan;122:127-133. doi: 10.1016/j.aap.2018.09.025. Epub 2018 Oct 18.
9
Can we trust our eyes? Interpreting the misperception of road safety from street view images and deep learning.我们能相信自己的眼睛吗？从街景图像和深度学习解读道路安全的误判
Accid Anal Prev. 2024 Mar;197:107455. doi: 10.1016/j.aap.2023.107455. Epub 2024 Jan 12.
10
Motorized and non-motorized mixed traffic characteristics and lateral opening spacing calculation for the section of arterial highway through small towns.穿过小镇的干线公路路段的机动化与非机动化混合交通特性及侧向开口间距计算
Sci Rep. 2024 Feb 28;14(1):4834. doi: 10.1038/s41598-024-55529-0.

引用本文的文献

1
StreetAware: A High-Resolution Synchronized Multimodal Urban Scene Dataset.街道感知：高分辨率同步多模态城市场景数据集。
Sensors (Basel). 2023 Apr 3;23(7):3710. doi: 10.3390/s23073710.

本文引用的文献

1
Assessing the Impact of Street-View Greenery on Fear of Neighborhood Crime in Guangzhou, China.评估广州市街景绿化对居民社区犯罪恐惧的影响。
Int J Environ Res Public Health. 2021 Jan 4;18(1):311. doi: 10.3390/ijerph18010311.
2
Fifty Years of Accident Analysis & Prevention: A Bibliometric and Scientometric Overview.《事故分析与预防五十年：文献计量与科学计量概述》。
Accid Anal Prev. 2020 Sep;144:105568. doi: 10.1016/j.aap.2020.105568. Epub 2020 Jun 18.
3
Walkability Safety and Walkability Participation: A Health Concern.可步行性安全与可步行性参与：一个健康关注点。
Health Educ Behav. 2020 Jun;47(3):430-438. doi: 10.1177/1090198120903256. Epub 2020 Feb 26.
4
Road traffic injuries in China from 2007 to 2016: the epidemiological characteristics, trends and influencing factors.2007年至2016年中国道路交通伤害：流行病学特征、趋势及影响因素
PeerJ. 2019 Aug 6;7:e7423. doi: 10.7717/peerj.7423. eCollection 2019.
5
Large scale detailed mapping of dengue vector breeding sites using street view images.利用街景图像进行大规模详细的登革热媒介孳生地测绘。
PLoS Negl Trop Dis. 2019 Jul 29;13(7):e0007555. doi: 10.1371/journal.pntd.0007555. eCollection 2019 Jul.
6
An examination of the increases in pedestrian motor-vehicle crash fatalities during 2009-2016.分析 2009-2016 年行人与机动车碰撞致死事故的增加情况。
J Safety Res. 2018 Dec;67:37-44. doi: 10.1016/j.jsr.2018.09.009. Epub 2018 Sep 27.
7
Using Deep Learning to Identify Utility Poles with Crossarms and Estimate Their Locations from Google Street View Images.利用深度学习从谷歌街景图像中识别带有横臂的电线杆并估算其位置。
Sensors (Basel). 2018 Aug 1;18(8):2484. doi: 10.3390/s18082484.
8
Knowledge and Beliefs About Pedestrian Safety in an Urban Community: Implications for Promoting Safe Walking.城市社区行人安全知识和信念：促进安全行走的意义。
J Community Health. 2019 Feb;44(1):103-111. doi: 10.1007/s10900-018-0559-0.
9
The influence of conformity and group identity on drink walking intentions: comparing intentions to drink walk across risky pedestrian crossing scenarios.从众和群体认同对酒后步行意图的影响：比较在不同危险行人穿越场景下酒后步行的意图。
Accid Anal Prev. 2012 Mar;45:639-45. doi: 10.1016/j.aap.2011.09.035. Epub 2011 Oct 10.
10
Flood area and damage estimation in Zhejiang, China.中国浙江的洪水区域及损失估计。
J Environ Manage. 2002 Sep;66(1):1-8. doi: 10.1006/jema.2002.0544.