零样本检测交通碰撞，用视觉语言模型+追踪实现精准定位
Zero-Shot Traffic Accident Detection via a Coarse-to-Fine VLM-Tracking Pipeline
- 分两步走：先粗筛事故时间点，再精查局部帧
- 在真实监控数据上达0.504的三类平均分数，领先基线22%
- 无需训练，适合无标注数据场景的事故监测系统
交通监控摄像头持续拍摄事故，但将原始视频转化为精确记录事故何时、何地、何种碰撞的结构化事件仍面临挑战。ACCIDENT @ CVPR基准要求在无真实世界标注训练数据条件下完成联合预测。本文提出一种无需训练的两阶段粗到细流水线，结合冻结的Qwen3-VL-32B-Instruct多模态模型、YOLO11x目标检测与BoT-SORT跟踪。第一阶段稀疏采样整段视频，锚定事故发生时刻；第二阶段在该时刻附近紧邻窗口内重新分析，利用带有稳定车辆标识和归一化框坐标的帧，使模型同时获得视觉画面与数值描述。在官方2,027段真实监控测试集上，系统取得三类任务调和平均分0.504，超越所有发布基线（包括最佳多模型集成0.412），相对提升22%。
原文摘要 · Abstract (English)
Traffic surveillance cameras capture accidents continuously, yet converting raw CCTV footage into structured event records that pinpoint when, where, and what type of collision occurred remains unsolved at scale. The ACCIDENT @ CVPR benchmark evaluates exactly this joint prediction under a strict constraint: no labeled real-world training data is available. We introduce a training-free, two-pass coarse-to-fine pipeline that pairs a frozen Qwen3-VL-32B-Instruct vision-language model with YOLO11x object detection and BoT-SORT tracking. A first pass sparsely samples the full clip to anchor the collision moment in time; a second pass re-examines a tight window around that estimate using frames annotated with stable vehicle identities and normalized bounding-box coordinates, which gives the model both a visual overlay and an explicit numeric description of the same scene. On the official 2,027-clip real-CCTV test set, our system achieves a three-way harmonic mean score of 0.504, surpassing all organizer-published baselines including the best multi-model ensemble (0.412) by a 22% relative margin.
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。