用分角色LoRA实现快速筛查与精准诊断的轨迹异常分析框架
TrajMind: Chaining Role-Specialized LoRAs for Fast-and-Slow Collective Trajectory Anomaly Diagnosis
- 分离快速筛查与慢速诊断，通过三类专用LoRA适配器切换
- 慢速路径在跨城场景下异常分类准确率提升15.3%，定位精度提升13.8%
- 快速路径延迟降低41.1%，保持93.5%以上二分类平衡准确率
从城市轨迹中诊断集体异常对交通治理日益重要，可揭示事件发生的时间、地点、涉及人员及过程。现有检测器虽能高效生成评分或标签，视觉-语言模型则提供更丰富的语义信息，但二者均未能将可验证的诊断结果与低延迟监控相结合。核心挑战在于：如何从原始轨迹中识别集体模式并还原确切事件细节，而不对每个监测窗口运行完整诊断流程。为此，本文提出TrajMind，一种快慢结合的框架，通过在冻结的视觉-语言主干上切换三类角色专用的LoRA适配器。其慢速路径（TrajMind$_{\text{slow}}$）串联基于画布的类型识别、基于类型条件的序列化轨迹定位与可执行验证，输出结构化且有证据支持的诊断结果。快速路径（TrajMind$_{\text{fast}}$）仅通过一次文本处理完成每窗口筛查，生成高效结构化警报。大量实验表明，TrajMind$_{\mathrm{slow}}$ 在异常分类上优于最强基线至少15.3个百分点，在定位上提升13.8个百分点，跨城市迁移下仍具优势；而TrajMind$_{\mathrm{fast}}$ 将延迟降低41.1%，并维持至少93.5%的二分类平衡准确率。整体实现了跨城市高精度、有证据支撑的诊断与高效的前端监控。
原文摘要 · Abstract (English)
Diagnosing collective anomalies from urban trajectories is increasingly important for traffic governance, as it reveals what happened, who was involved, and where and when the event occurred. Existing detectors efficiently produce scores or labels, whereas vision--language pipelines provide richer semantics; neither couples verifiable diagnosis with low-latency monitoring. The central challenge is to recognize collective patterns and recover exact event details from the source trajectories without running the full diagnostic pipeline for every monitored window. We therefore separate always-on screening from on-demand diagnosis: screening raises alerts, while diagnosis releases only source-verified what--who--where--when records. We present TrajMind, a fast-and-slow framework that switches three role-specialized LoRA adapters over one frozen vision--language backbone. Its slow path, \textit{TrajMind$_{\text{slow}}$}, chains canvas-based typing, type-conditioned localization over serialized trajectories, and executable verification, yielding structured, evidence-backed diagnoses. Additionally, the fast path, \textit{TrajMind$_{\text{fast}}$}, screens each window in a single text-only pass, delivering efficient structured alerts. Extensive experiments show that, TrajMind$_{\mathrm{slow}}$ outperforms the strongest baselines by at least $15.3$ percentage points in anomaly typing and $13.8$ percentage points in localization. These gains persist under cross-city transfer, and TrajMind$_{\mathrm{fast}}$ reduces latency by $41.1\%$ and maintains binary balanced accuracy of at least $93.5\%$. Together, TrajMind delivers accurate, evidence-backed diagnoses across cities and efficient front-line monitoring.
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。