统一推理交通视频，解决异常检测与行人意图预测难题
UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations
- 采用观察-推理-行动-验证流程，统一处理多任务交通视频分析
- 在鱼眼视频和行人意图问答中分别取得第二、第四名成绩
- 适用于交通监控、自动驾驶等需要多模态理解的场景
交通视频理解在智能交通中至关重要，因其能提供事故、违规及车辆与弱势道路使用者互动的直接证据。理想系统应解释事件发展过程、原因及交互时机，但多模态大模型因交通视频事件稀疏、视角多样而难以胜任。本文提出UniTraffic-Agent，即第10届AI City Challenge Track 3的MR-CAS解决方案，包含交通异常推理（TAR）及两项域外评估：针对鱼眼视频的FETV和行人意图推理的PSI-VQA。该系统遵循观察—推理—行动—验证的工作流，对同一视频片段中的所有问题一次性推理，并通过任务特定的动作适配器转换输出。在官方公开排行榜上，MR-CAS在TAR任务中排名第16，得分为0.5780；在FETV中排名第二，得分为0.4884；在PSI-VQA中排名第四，得分为64.4161。代码已开源。
原文摘要 · Abstract (English)
Traffic video understanding has become an important problem in intelligent transportation, as road videos provide direct evidence for accidents, violations, and interactions between vehicles and vulnerable road users. A useful system should explain how a traffic event develops, why it happens, and when the relevant interaction occurs, yet this remains difficult for multimodal large language models (MLLMs) because traffic videos contain sparse events and varied viewpoints. We introduce UniTraffic-Agent, the MR-CAS solution for Track~3 of the 10th AI City Challenge, which includes Traffic Anomaly Reasoning (TAR) and two out-of-domain evaluations: FETV for fisheye traffic events and PSI-VQA for pedestrian intention reasoning. UniTraffic-Agent follows an observe--reason--act--verify workflow that samples timestamped visual evidence, reasons over all questions from the same clip in one request, and converts responses through task-specific action adapters. On the official Public leaderboards, MR-CAS ranks 16th on TAR with a score of 0.5780, 2nd on FETV with 0.4884, and 4th on PSI-VQA with 64.4161. The code is available at https://github.com/Roclp/UniTraffic-Agent.
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。