VZCrash: A Large-Scale IMU Dataset of Ego-Vehicle Crashes
Researchers have introduced VZCrash, a new dataset containing over 31,000 real-world vehicle crashes recorded using Inertial Measurement Unit (IMU) telemetry. This dataset, collected from a fleet of over 73,000 vehicles in the United States, includes detailed acceleration, angular velocity, and GPS data. The researchers used this dataset to benchmark various crash detection models, highlighting the critical role of data scale in training effective models for real-world deployment. AI
IMPACT Provides a large-scale dataset for training and evaluating AI models in vehicle crash detection.