EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911001418399744 |
|---|---|
| author | Fang, Jianwu Li, Lei-Lei Zheng, Zhedong Yu, Hongkai Xue, Jianru Li, Zhengguo Chua, Tat-Seng |
| author_facet | Fang, Jianwu Li, Lei-Lei Zheng, Zhedong Yu, Hongkai Xue, Jianru Li, Zhengguo Chua, Tat-Seng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_10002 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis Fang, Jianwu Li, Lei-Lei Zheng, Zhedong Yu, Hongkai Xue, Jianru Li, Zhengguo Chua, Tat-Seng Multimedia Artificial Intelligence Computer Vision and Pattern Recognition Robotics 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. |
| title | EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis |
| topic | Multimedia Artificial Intelligence Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2506.10002 |