构建首个高速事故数据集，用于长尾罕见事故的智能检测。
Safety-Critical Learning for Long-Tail Events: The TUM Traffic Accident Dataset
- 融合规则与学习方法，实现事故检测
- 涵盖10类目标，29万+2D/9万+3D标注框
- 适合自动驾驶安全研究者使用
尽管交通安全性研究已取得大量成果，交通事故仍频繁发生，被视为交通网络不可避免且偶发的后果。本文提出TUM Traffic Accident (TUMTraf-A)数据集，包含真实高速公路事故的十段视频序列。数据由四台路边摄像头与激光雷达以10 Hz采样，共48,144帧，包含294,924个2D标注框、93,012个3D标注框及轨迹ID，覆盖10类物体，采用OpenLABEL格式。我们还提出了Accid3nD模型，结合规则与学习方法进行事故检测。在该数据集上的实验与消融分析验证了方法的鲁棒性。数据集、模型与代码已在项目网站公开：https://tum-traffic-dataset.github.io/tumtraf-a。
原文摘要 · Abstract (English)
Even though a significant amount of work has been done to increase the safety of transportation networks, accidents still occur regularly. They must be understood as an unavoidable and sporadic outcome of traffic networks. We present the TUM Traffic Accident (TUMTraf-A) dataset, a collection of real-world highway accidents. It contains ten sequences of vehicle crashes at high-speed driving with 294,924 labeled 2D and 93,012 labeled 3D boxes and track IDs within 48,144 labeled frames recorded from four roadside cameras and LiDARs at 10 Hz. The dataset contains ten object classes and is provided in the OpenLABEL format. We propose Accid3nD, an accident detection model that combines a rule-based approach with a learning-based one. Experiments and ablation studies on our dataset show the robustness of our proposed method. The dataset, model, and code are available on our project website: https://tum-traffic-dataset.github.io/tumtraf-a.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。