Scholarlink

<p>A significant number of traffic crashes are secondary crashes that occur because of an earlier incident on the road. Thus, early detection of traffic incidents is crucial for road users from a safety perspective with a potential to reduce the risk of secondary crashes. The wide availability of GPS devices now-a-days gives an opportunity of tracking and recording vehicle trajectories. The objective of this study is to use vehicle trajectory data for advance real-time detection of traffic incidents on highways using machine learning-based algorithms. The study uses 3 days of unevenly sequenced vehicle trajectory data and traffic incident data on I-10, one of the most crash-prone highways in Louisiana, USA. Vehicle trajectories are converted to trajectories based on virtual detector locations to maintain spatial uniformity as well as to generate historical traffic data for machine learning algorithms. Trips matched with traffic incidents on the way are separated and along with other trips with similar spatial attributes are used to build a database for modeling. Multiple machine learning algorithms such as Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boost (XGB), and Artificial Neural Network (ANN) models are used to detect a trajectory that is likely to face an incident in the downstream road section. Results suggest that the Extreme Gradient Boosting model achieves the best performance for detecting an incident with higher AUC-ROC (0.68) and recall (0.69). The analysis also demonstrates that moderately oversampling the minority class (incident-affected trajectories) using a SMOTE ratio 0.25 to 0.50 can achieve better detection result. This study will significantly enhance driving safety by alerting drivers to avoid secondary crashes and assist in implementing efficient response plans to mitigate congestion impacts due to traffic incidents.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Advance Real-Time Detection of Traffic Incidents in Highways Using Vehicle Trajectory Data

  • 期刊论文

  • 发表日期：

    2026年2月3日

查看全文
  • Sudipta Roy,
  • Samiul Hasan

摘要

A significant number of traffic crashes are secondary crashes that occur because of an earlier incident on the road. Thus, early detection of traffic incidents is crucial for road users from a safety perspective with a potential to reduce the risk of secondary crashes. The wide availability of GPS devices now-a-days gives an opportunity of tracking and recording vehicle trajectories. The objective of this study is to use vehicle trajectory data for advance real-time detection of traffic incidents on highways using machine learning-based algorithms. The study uses 3 days of unevenly sequenced vehicle trajectory data and traffic incident data on I-10, one of the most crash-prone highways in Louisiana, USA. Vehicle trajectories are converted to trajectories based on virtual detector locations to maintain spatial uniformity as well as to generate historical traffic data for machine learning algorithms. Trips matched with traffic incidents on the way are separated and along with other trips with similar spatial attributes are used to build a database for modeling. Multiple machine learning algorithms such as Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boost (XGB), and Artificial Neural Network (ANN) models are used to detect a trajectory that is likely to face an incident in the downstream road section. Results suggest that the Extreme Gradient Boosting model achieves the best performance for detecting an incident with higher AUC-ROC (0.68) and recall (0.69). The analysis also demonstrates that moderately oversampling the minority class (incident-affected trajectories) using a SMOTE ratio 0.25 to 0.50 can achieve better detection result. This study will significantly enhance driving safety by alerting drivers to avoid secondary crashes and assist in implementing efficient response plans to mitigate congestion impacts due to traffic incidents.