Understanding the potential of emerging digital technologies for improving road safety

被引:35
作者
Torbaghan, Mehran Eskandari [1 ]
Sasidharan, Manu [1 ,2 ]
Reardon, Louise [3 ]
Muchanga-Hvelplund, Leila C. W. [1 ]
机构
[1] Univ Birmingham, Sch Engn, Edgbaston B15 2TT, England
[2] Univ Cambridge, Dept Engn, Cambridge CB3 0FS, England
[3] Univ Birmingham, Inst Local Govt Studies, Edgbaston B15 2TT, England
关键词
Safety; Road; Transport; Digital technology; Information; TRAFFIC CONGESTION; SENSOR DATA; SYSTEM; RISK; ALGORITHMS; FRAMEWORK; BEHAVIOR; CRASHES; SPEED;
D O I
10.1016/j.aap.2021.106543
中图分类号
TB18 [人体工程学];
学科分类号
1201 ;
摘要
Each year, 1.35 million people are killed on the world's roads and another 20-50 million are seriously injured. Morbidity or serious injury from road traffic collisions is estimated to increase to 265 million people between 2015 and 2030. Current road safety management systems rely heavily on manual data collection, visual in-spection and subjective expert judgment for their effectiveness, which is costly, time-consuming, and sometimes ineffective due to under-reporting and the poor quality of the data. A range of innovations offers the potential to provide more comprehensive and effective data collection and analysis to improve road safety. However, there has been no systematic analysis of this evidence base. To this end, this paper provides a systematic review of the state of the art. It identifies that digital technologies -Artificial Intelligence (AI), Machine-Learning, Image-Processing, Internet-of-Things (IoT), Smartphone applications, Geographic Information System (GIS), Global Positioning System (GPS), Drones, Social Media, Virtual-reality, Simulator, Radar, Sensor, Big Data - provide useful means for identifying and providing information on road safety factors including road user behaviour, road characteristics and operational environment. Moreover, the results show that digital technologies such as AI, Image processing and IoT have been widely applied to enhance road safety, due to their ability to auto-matically capture and analyse data while preventing the possibility of human error. However, a key gap in the literature remains their effectiveness in real-world environments. This limits their potential to be utilised by policymakers and practitioners.
引用
收藏
页数:23
相关论文
共 133 条
[1]   Driving speed and the risk of road crashes: A review [J].
Aarts, L ;
van Schagen, I .
ACCIDENT ANALYSIS AND PREVENTION, 2006, 38 (02) :215-224
[2]  
Acilo J.P.N., 2018, 2018 IEEE 14 INT C S
[3]   Using low-cost smartphone sensor data for locating crash risk spots in a road network [J].
Aichinger, Claus ;
Nitsche, Philippe ;
Stuetz, Rainer ;
Harnisch, Marko .
TRANSPORT RESEARCH ARENA TRA2016, 2016, 14 :2015-2024
[4]  
Al Najada H, 2016, INT WIREL COMMUN, P256, DOI 10.1109/IWCMC.2016.7577067
[5]  
Al-Marafi M., 2018, Indian Journal of Science and Technology, V11, P1
[6]  
Allal I, 2015, GLOB INFORM INFRAS
[7]   Modeling pedestrian-cyclist interactions in shared space using inverse reinforcement learning [J].
Alsaleh, Rushdi ;
Sayed, Tarek .
TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 2020, 70 :37-57
[8]  
Ameddah M.A., 2018, 2018 IEEE GLOB COMMU, P1, DOI DOI 10.1109/GLOCOM.2018.8647334
[9]  
Anass R., 2016, Int. J. Comput. Appl, V145, P975
[10]  
Anderson T., 2003, CASA WORKING PAPERS, V67