DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving (2304.01168v5)
Abstract: Safety is the primary priority of autonomous driving. Nevertheless, no published dataset currently supports the direct and explainable safety evaluation for autonomous driving. In this work, we propose DeepAccident, a large-scale dataset generated via a realistic simulator containing diverse accident scenarios that frequently occur in real-world driving. The proposed DeepAccident dataset includes 57K annotated frames and 285K annotated samples, approximately 7 times more than the large-scale nuScenes dataset with 40k annotated samples. In addition, we propose a new task, end-to-end motion and accident prediction, which can be used to directly evaluate the accident prediction ability for different autonomous driving algorithms. Furthermore, for each scenario, we set four vehicles along with one infrastructure to record data, thus providing diverse viewpoints for accident scenarios and enabling V2X (vehicle-to-everything) research on perception and prediction tasks. Finally, we present a baseline V2X model named V2XFormer that demonstrates superior performance for motion and accident prediction and 3D object detection compared to the single-vehicle model.
- nuscenes: A multimodal dataset for autonomous driving. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 11621–11631.
- CARLA: An open urban driving simulator. arXiv 2017. arXiv preprint arXiv:1711.03938.
- Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 32(11): 1231–1237.
- Crash to Not Crash: Learn to Identify Dangerous Vehicles Using a Simulator. In Proceedings of the AAAI Conference on Artificial Intelligence, 978–985.
- FIERY: future instance prediction in bird’s-eye view from surround monocular cameras. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 15273–15282.
- Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv preprint arXiv:2112.11790.
- PointPillars: Fast Encoders for Object Detection from Point Clouds. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 12697–12705.
- Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline. arXiv preprint arXiv:2301.12511.
- V2X-Sim: Multi-agent collaborative perception dataset and benchmark for autonomous driving. IEEE Robotics and Automation Letters, 7(4): 10914–10921.
- Learning Distilled Collaboration Graph for Multi-Agent Perception. In Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021).
- Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, 10012–10022.
- Pre-crash scenario typology for crash avoidance research. Technical report, United States. National Highway Traffic Safety Administration.
- Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior. In Conference on Computer Vision and Pattern Recognition (CVPR).
- VIENA2: A Driving Anticipation Dataset. arXiv e-prints, arXiv–1810.
- PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10529–10538.
- Scalability in perception for autonomous driving: Waymo open dataset. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2446–2454.
- AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles. Conference on Computer Vision and Pattern Recognition (CVPR).
- CoBEVT: Cooperative Bird’s Eye View Semantic Segmentation with Sparse Transformers. In Conference on Robot Learning (CoRL).
- V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer. In Proceedings of the European Conference on Computer Vision (ECCV).
- Opv2v: An open benchmark dataset and fusion pipeline for perception with vehicle-to-vehicle communication. In 2022 International Conference on Robotics and Automation (ICRA), 2583–2589. IEEE.
- TAD: A Large-Scale Benchmark for Traffic Accidents Detection from Video Surveillance. arXiv preprint arXiv:2209.12386.
- Dair-v2x: A large-scale dataset for vehicle-infrastructure cooperative 3d object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 21361–21370.
- V2X-Seq: A large-scale sequential dataset for vehicle-infrastructure cooperative perception and forecasting. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.
- Beverse: Unified perception and prediction in birds-eye-view for vision-centric autonomous driving. arXiv preprint arXiv:2205.09743.