SAVeD: A First-Person Social Media Video Dataset for ADAS-equipped vehicle Near-Miss and Crash Event Analyses

TL;DR

SAVeD is a large-scale, first-person social media video dataset focused on ADAS vehicle near-miss and crash events, enabling advanced analysis of risk scenarios and model benchmarking.

Contribution

The paper introduces SAVeD, a novel dataset with detailed annotations for ADAS-related near-misses and crashes, and proposes new frameworks for risk quantification and model evaluation.

Findings

SAVeD enables improved model performance through domain adaptation.

The framework accurately computes real-time Time-to-Collision (TTC).

Extreme risk modeling using GEV distribution quantifies near-miss severity.

Abstract

The advancement of safety-critical research in driving behavior in ADAS-equipped vehicles require real-world datasets that not only include diverse traffic scenarios but also capture high-risk edge cases such as near-miss events and system failures. However, existing datasets are largely limited to either simulated environments or human-driven vehicle data, lacking authentic ADAS (Advanced Driver Assistance System) vehicle behavior under risk conditions. To address this gap, this paper introduces SAVeD, a large-scale video dataset curated from publicly available social media content, explicitly focused on ADAS vehicle-related crashes, near-miss incidents, and disengagements. SAVeD features 2,119 first-person videos, capturing ADAS vehicle operations in diverse locations, lighting conditions, and weather scenarios. The dataset includes video frame-level annotations for collisions, evasive maneuvers, and disengagements, enabling analysis of both perception and decision-making failures. We demonstrate SAVeD's utility through multiple analyses and contributions: (1) We propose a novel framework integrating semantic segmentation and monocular depth estimation to compute real-time Time-to-Collision (TTC) for dynamic objects. (2) We utilize the Generalized Extreme Value (GEV) distribution to model and quantify the extreme risk in crash and near-miss events across different roadway types. (3) We establish benchmarks for state-of-the-art VLLMs (VideoLLaMA2 and InternVL2.5 HiCo R16), showing that SAVeD's detailed annotations significantly enhance model performance through domain adaptation in complex near-miss scenarios.