EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis

TL;DR

This paper introduces EQ-TAA, a novel approach that synthesizes accident videos using diffusion models to improve traffic accident anticipation without extra annotations, achieving competitive results.

Contribution

The paper proposes an Attentive Video Diffusion model for generating causal accident clips and an equivariant TAA framework, enhancing accident anticipation in traffic scenes.

Findings

Competitive performance against state-of-the-art methods

Effective synthesis of accident videos from normal clips

Improved accident anticipation accuracy

Abstract

Traffic Accident Anticipation (TAA) in traffic scenes is a challenging problem for achieving zero fatalities in the future. Current approaches typically treat TAA as a supervised learning task needing the laborious annotation of accident occurrence duration. However, the inherent long-tailed, uncertain, and fast-evolving nature of traffic scenes has the problem that real causal parts of accidents are difficult to identify and are easily dominated by data bias, resulting in a background confounding issue. Thus, we propose an Attentive Video Diffusion (AVD) model that synthesizes additional accident video clips by generating the causal part in dashcam videos, i.e., from normal clips to accident clips. AVD aims to generate causal video frames based on accident or accident-free text prompts while preserving the style and content of frames for TAA after video generation. This approach can be trained using datasets collected from various driving scenes without any extra annotations. Additionally, AVD facilitates an Equivariant TAA (EQ-TAA) with an equivariant triple loss for an anchor accident-free video clip, along with the generated pair of contrastive pseudo-normal and pseudo-accident clips. Extensive experiments have been conducted to evaluate the performance of AVD and EQ-TAA, and competitive performance compared to state-of-the-art methods has been obtained.