Enhancing Highway Safety: Accident Detection on the A9 Test Stretch Using Roadside Sensors

TL;DR

This paper presents a new accident detection framework using roadside sensors and a comprehensive real-world highway accident dataset to improve safety and response times on highways.

Contribution

It introduces a hybrid rule-based and learning-based accident detection system along with a large, detailed highway accident dataset in OpenLABEL format.

Findings

The proposed method reliably detects accidents in real-world highway scenarios.

The dataset includes extensive labeled data with 294,924 2D boxes and 93,012 3D boxes.

Experiments confirm the effectiveness of the combined detection approach.

Abstract

Road traffic injuries are the leading cause of death for people aged 5-29, resulting in about 1.19 million deaths each year. To reduce these fatalities, it is essential to address human errors like speeding, drunk driving, and distractions. Additionally, faster accident detection and quicker medical response can help save lives. We propose an accident detection framework that combines a rule-based approach with a learning-based one. We introduce a dataset of real-world highway accidents featuring high-speed crash sequences. It includes 294,924 labeled 2D boxes, 93,012 labeled 3D boxes, and track IDs across 48,144 frames captured at 10 Hz using four roadside cameras and LiDAR sensors. The dataset covers ten object classes and is released in the OpenLABEL format. Our experiments and analysis demonstrate the reliability of our method.