ACCIDENT: A Benchmark Dataset for Vehicle Accident Detection from Traffic Surveillance Videos
This dataset provides a standardized benchmark for evaluating accident detection models in traffic surveillance, addressing a gap in available datasets for this domain.
The paper introduces ACCIDENT, a benchmark dataset for vehicle accident detection in CCTV footage, comprising 2,027 real and 2,211 synthetic clips with annotations for temporal and spatial localization and collision type classification. The benchmark is designed for supervised and zero-shot settings, and baseline evaluations show it is challenging.
We introduce ACCIDENT, a benchmark dataset for traffic accident detection in CCTV footage, designed to evaluate models in supervised (IID and OOD) and zero-shot settings, reflecting both data-rich and data-scarce scenarios. The benchmark consists of a curated set of 2,027 real and 2,211 synthetic clips annotated with the accident time, spatial location, and high-level collision type. We define three core tasks: (i) temporal localization of the accident, (ii) its spatial localization, and (iii) collision type classification. Each task is evaluated using custom metrics that account for the uncertainty and ambiguity inherent in CCTV footage. In addition to the benchmark, we provide a diverse set of baselines, including heuristic, motion-aware, and vision-language approaches, and show that ACCIDENT is challenging. You can access the ACCIDENT at: https://accidentbench.github.io