构建了全球最大车载碰撞数据集，含超3万次真实碰撞事件。
VZCrash: A Large-Scale IMU Dataset of Ego-Vehicle Crashes
- 采集7.3万辆车多年运行数据，每秒记录加速度与角速度
- 包含31,000次验证碰撞和158,000个负样本，覆盖复杂场景
- 实证表明：大规模数据对真实场景下碰撞检测模型至关重要
我们引入VZCrash，目前公开可用的最大规模真实车辆碰撞数据集，包含惯性测量单元（IMU）遥测数据。该数据集涵盖超过31,000次经验证的碰撞事件和158,000个负样本，包括困难案例和干扰项。每个样本包含100 Hz的加速度与角速度数据，以及1 Hz的GPS速度。这些事件由安装在73,010辆不同尺寸商用汽车上的设备，在美国多地数年间采集。我们还基于该数据集开展广泛实验研究：首先对比了从简单阈值法到最先进深度学习模型的多种方法；其次通过实验证明数据规模对训练高质量碰撞检测模型的重要性，并表明在真实环境部署时，数据规模尤为关键。
原文摘要 · Abstract (English)
We introduce VZCrash, the largest publicly available dataset of real-world vehicle collision data featuring Inertial Measurement Unit (IMU) telemetry. The dataset contains more than 31,000 validated crashes and 158,000 negative samples, including hard cases and distractors. Each sample includes acceleration and angular velocity at 100 Hz, and GPS speed at 1 Hz. Events in VZCrash were captured by devices installed on a fleet of 73,010 commercial vehicles of different sizes driving in the United States over the span of several years. We also present an extensive experimental study enabled by the volume of the dataset. We first benchmark several different approaches, from a simple threshold-based heuristic to state-of-the-art deep learning models. Then, we present an experiment demonstrating the importance of scaling data to train high-quality crash detection models, and we show that scale is especially important when these models need to be deployed into a real-world environment.
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。