Debashis Ray Sarkar, K. Ramachandra Rao, Niladri Chatterjee
{"title":"Automatic Traffic Safety Analysis using Unmanned Aerial Vehicle Technology at Unsignalized Intersections in Heterogeneous Traffic","authors":"Debashis Ray Sarkar, K. Ramachandra Rao, Niladri Chatterjee","doi":"10.1177/03611981241266838","DOIUrl":null,"url":null,"abstract":"A generalized, reliable unmanned aerial vehicle (UAV) system for visual tracking and detection of road vehicles from aerial videography would outperform traditional traffic monitoring systems, providing extensive coverage and optimal study area perspectives. The combination of UAV technology for data collection and advanced video processing tools for visual tracking would assist traffic engineers in a detailed spatial and temporal utilization analysis with accurate traffic characteristics. Initially, traffic conflicts were determined by post encroachment time from visual data at unsignalized intersection. But a new concept (known as “required post encroachment time”) has been proposed to differentiate between critical and non-critical conflicts among road users. Finally, by extracting the information of vehicle trajectories, we have also developed a “collision probability evaluation model” to determine the severity level of critical conflicts in heterogeneous traffic conditions. Our numerical results show the high precision of our suggested model with regard to risk recognition when evaluating the collision probability at the study intersection. This research utilizes vehicle trajectories to evaluate driving risk at intersections through automatic traffic safety analysis.","PeriodicalId":309251,"journal":{"name":"Transportation Research Record: Journal of the Transportation Research Board","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transportation Research Record: Journal of the Transportation Research Board","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1177/03611981241266838","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
A generalized, reliable unmanned aerial vehicle (UAV) system for visual tracking and detection of road vehicles from aerial videography would outperform traditional traffic monitoring systems, providing extensive coverage and optimal study area perspectives. The combination of UAV technology for data collection and advanced video processing tools for visual tracking would assist traffic engineers in a detailed spatial and temporal utilization analysis with accurate traffic characteristics. Initially, traffic conflicts were determined by post encroachment time from visual data at unsignalized intersection. But a new concept (known as “required post encroachment time”) has been proposed to differentiate between critical and non-critical conflicts among road users. Finally, by extracting the information of vehicle trajectories, we have also developed a “collision probability evaluation model” to determine the severity level of critical conflicts in heterogeneous traffic conditions. Our numerical results show the high precision of our suggested model with regard to risk recognition when evaluating the collision probability at the study intersection. This research utilizes vehicle trajectories to evaluate driving risk at intersections through automatic traffic safety analysis.