Safety-Critical Learning for Long-Tail Events: The TUM Traffic Accident Dataset
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 20 Aug 2025.
Builds on
20 of 27 references.
References · 20
- 2023DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Drivingcited by 73
- 2024TUMTraf V2X Cooperative Perception Datasetcited by 67
- 2024A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlookcited by 66
- 2021LaneAF: Robust Multi-Lane Detection with Affinity Fieldscited by 41
- 2022A9-Dataset: Multi-Sensor Infrastructure-Based Dataset for Mobility Researchcited by 40
- 20193D BAT: A Semi-Automatic, Web-based 3D Annotation Toolbox for Full-Surround, Multi-Modal Data Streamscited by 36
- 2021IPS300+: a Challenging Multimodal Dataset for Intersection Perception Systemcited by 26
- 2023InfraDet3D: Multi-Modal 3D Object Detection based on Roadside Infrastructure Camera and LiDAR Sensorscited by 25
- 2024Towards Explainable, Safe Autonomous Driving with Language Embeddings for Novelty Identification and Active Learning: Framework and Experimental Analysis with Real-World Data Setscited by 25
- 2024The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Explorationcited by 17
- 2024ActiveAnno3D -- An Active Learning Framework for Multi-Modal 3D Object Detectioncited by 17
- 2024TUMTraf Event: Calibration and Fusion Resulting in a Dataset for Roadside Event-Based and RGB Camerascited by 13
8 more
- 2023Safe Control Transitions: Machine Vision Based Observable Readiness Index and Data-Driven Takeover Time Predictioncited by 12
- 2022A Survey of Robust 3D Object Detection Methods in Point Cloudscited by 10
- 2022Real-Time and Robust 3D Object Detection Within Road-Side LiDARs Using Domain Adaptationcited by 10
- 2018Drive Video Analysis for the Detection of Traffic Near-Miss Incidentscited by 9
- 2022Real-Time And Robust 3D Object Detection with Roadside LiDARscited by 9
- 2023Pedestrian Behavior Maps for Safety Advisories: CHAMP Framework and Real-World Data Analysiscited by 9
- 2022Planning with Occluded Traffic Agents using Bi-Level Variational Occlusion Modelscited by 5
- 2024GraphRelate3D: Context-Dependent 3D Object Detection with Inter-Object Relationship Graphscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.