发表机构
University of West Bohemia（西波希米亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究利用真实世界多视角碰撞后照片，通过监督学习预测碰撞变形分类和速度变化，联合训练显著降低角度和速度误差，为多模态融合提供基准。
AI 中文摘要
从真实世界碰撞中估计事故力学对于车辆安全分析、损伤建模、碰撞严重性预测以及保险理赔分诊等操作工作流至关重要。在标准事故记录中，关键元数据如碰撞构型、力的主方向以及速度变化（$\Delta V$）可能缺失、延迟或损坏，而碰撞后照片广泛可用且包含丰富的变形视觉证据。我们研究了在结构化信号缺失时，能直接从车辆照片中恢复多少碰撞力学信息。我们将碰撞理解表述为基于逐案例多视角照片集的监督预测。目标包括六个碰撞变形分类（CDC）描述符以及重建的$\Delta V$的纵向和横向分量。每张照片由共享视觉骨干编码，得到的视图级特征融合成案例级表示，从中目标特定的头部预测碰撞描述符。使用来自碰撞调查采样系统的15.2k训练案例（从过滤前约150万张照片中选取），以及1.15k验证和1.15k测试案例，我们定义了一个基于视觉的碰撞描述符估计评估协议，用于不完整多视角证据。仅碰撞后图像即可为几个非平凡的碰撞力学描述符提供可用信号，而弱可观察和长尾目标仍具挑战性。在比较的训练方案中，选定的联合训练配方将力的主方向的平均绝对角度误差从20.1度降至14.05度，纵向$\Delta V$ MAE从8.04 km/h降至7.45 km/h。我们的工作为未来与结构化碰撞元数据的多模态融合提供了参考点。
英文摘要
Estimating accident mechanics from real-world crashes is important for vehicle-safety analysis, injury modeling, crash-severity prediction, and operational workflows such as insurance claim triage. In standard crash records, key metadata such as impact configuration, principal direction of force, and change in velocity ($ΔV$) may be missing, delayed, or corrupted, while post-crash photographs are widely available and contain rich visual evidence of deformation. We study how much crash-mechanics information can be recovered directly from vehicle photos when structured signals are absent. We formulate crash understanding as supervised prediction from per-case multi-view photo sets. Targets include six Collision Deformation Classification (CDC) descriptors and the longitudinal and lateral components of reconstructed $ΔV$. Each photo is encoded by a shared visual backbone, and the resulting view-level features are fused into a case-level representation from which target-specific heads predict crash descriptors. Using 15.2k training cases from the Crash Investigation Sampling System, drawn from about 1.5M photos before filtering, together with 1.15k validation and 1.15k test cases, we define an evaluation protocol for vision-based crash descriptor estimation from incomplete multi-view evidence. Post-crash imagery alone provides usable signal for several non-trivial crash-mechanics descriptors, while weakly observable and long-tailed targets remain challenging. Within the compared training regimes, the selected joint-training recipe reduces mean absolute angular error for principal direction of force from 20.1 to 14.05 degrees and longitudinal $ΔV$ MAE from 8.04 to 7.45 km/h. Our work provides a reference point for future multimodal fusion with structured crash metadata.
