用扩散模型生成事故视频，解决真实数据少导致的预测偏差问题。
EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis
- 通过扩散模型从正常视频生成事故片段，聚焦因果部分。
- 在多个数据集上达到领先性能，显著提升事故预测准确率。
- 无需额外标注，适合自动驾驶和交通系统安全研究者。
交通事故预见（TAA）是实现零伤亡目标的关键挑战。现有方法多依赖人工标注事故持续时间，但交通场景具有长尾分布、不确定性高和快速演变的特点，导致真实事故因果部分难以识别，易受数据偏差影响，产生背景混淆问题。为此，我们提出注意力视频扩散（AVD）模型，通过生成行车记录仪视频中从正常到事故的因果片段来合成额外事故视频。AVD 能根据事故或无事故文本提示生成符合风格与内容的视频帧，且可在不需额外标注的情况下，基于多样驾驶场景数据训练。此外，结合等变三重损失，构建等变事故预见（EQ-TAA），以锚定无事故视频片段，并配对生成的对比伪正常与伪事故片段。大量实验表明，该方法性能优于当前最先进方法。
原文摘要 · Abstract (English)
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.
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。