Real-Time Lane-Level Crash Detection on Freeways Using Sparse Telematics Data

TL;DR

This paper introduces a real-time, lane-level crash detection system for freeways that uses only sparse telematics data, achieving high accuracy and early detection with low cost.

Contribution

It presents a novel approach leveraging sparse telematics data for real-time, lane-level crash detection, with an offline training and online scoring framework.

Findings

75% crash identification rate with lane-level accuracy

96% overall detection accuracy and 0.84 F1-score

Detects 13% of crashes more than 3 minutes early

Abstract

Real-time traffic crash detection is critical in intelligent transportation systems because traditional crash notifications often suffer delays and lack specific, lane-level location information, which can lead to safety risks and economic losses. This paper proposes a real-time, lane-level crash detection approach for freeways that only leverages sparse telematics trajectory data. In the offline stage, the historical trajectories are discretized into spatial cells using vector cross-product techniques, and then used to estimate a vehicle intention distribution and select an alert threshold by maximizing the F1-score based on official crash reports. In the online stage, incoming telematics records are mapped to these cells and scored for three modules: transition anomalies, speed deviations, and lateral maneuver risks, with scores accumulated into a cell-specific risk map. When any cell's risk exceeds the alert threshold, the system issues a prompt warning. Relying solely on telematics data, this real-time and low-cost solution is evaluated on a Wisconsin dataset and validated against official crash reports, achieving a 75% crash identification rate with accurate lane-level localization, an overall accuracy of 96%, an F1-score of 0.84, and a non-crash-to-crash misclassification rate of only 0.6%, while also detecting 13% of crashes more than 3 minutes before the recorded crash time.