做交通安全分析或自动驾驶细粒度感知的团队，可以直接用这个开源流水线替代粗粒度检测，它用弃权机制解决了域迁移下的误分类问题，值得在真实道路视频上试试。
该研究提出一个开源的两阶段计算机视觉流水线，用于从自然道路视频中细粒度分类车辆类型（轿车、SUV、皮卡、小型货车、大型货车、商用卡车），以评估自行车事故中骑车人受伤严重程度。第一阶段使用预训练的RT-DETR检测器进行粗略车辆定位，第二阶段使用微调的Vision Transformer（ViT-Base/16）进行六类车身类型分类。引入基于置信度的弃权机制（softmax输出低于0.60时输出“未知”标签），避免静默误分类。在密歇根州安阿伯市自行车道走廊的3805个超车事件（分布内）上，流水线准确率达0.94，各类F1分数在0.91（小型货车）到0.97（SUV）之间。在独立的外部数据集（311个事件，无再训练）上，准确率为0.89，其中三个常见类别F1仍保持在0.90以上，小型货车因弃权率从2.4%升至25.0%导致F1降至0.72，但未出现主动误分类。完整流水线（含推理脚本、训练代码、评估工具和模型权重）已开源，支持道路视频档案和骑行安全研究的复现与复用。
An Open-Source Two-Stage Computer Vision Pipeline for Fine-Grained Vehicle Classification using Vision Transformers
Vehicle body type is a significant determinant of cyclist injury severity in overtaking crashes, yet automated tools for classifying vehicles into injury-risk-relevant categories from naturalistic roadway video do not exist in the open literature. Standard object detection benchmarks provide only coarse vehicle labels (car, truck, bus, motorcycle), while existing fine-grained recognition systems are trained on controlled imagery and lack evaluation for deployment robustness across recording sites. This paper presents an open-source two-stage computer vision pipeline combining a pre-trained RT-DETR detector for coarse vehicle localization with a fine-tuned Vision Transformer (ViT-Base/16) for six-category body-type classification: passenger car, SUV, pickup truck, minivan, large van, and commercial truck. A confidence-based abstention mechanism withholds Stage 2 predictions when softmax output falls below 0.60, producing unknown labels rather than silent misclassifications. Evaluated on 3,805 annotated overtaking events from a bicycle-lane corridor in Ann Arbor, Michigan (in-distribution), the pipeline achieved 0.94 accuracy with per-class F1 scores from 0.91 (minivan) to 0.97 (SUV). On an independent out-of-distribution evaluation of 311 events from an open cycling dataset without retraining, accuracy was 0.89. Three of four well-represented categories maintained F1 at or above 0.90 under domain shift. The largest degradation was observed for minivan (F1 = 0.72), driven by abstention rate rising from 2.4% to 25.0% rather than active misclassification, consistent with the mechanism propagating genuine model uncertainty. The full pipeline, including inference scripts, training code, evaluation utilities, and model weights, is released as open-source software to support reproducibility and reuse across roadside video archives and cycling safety research.