Interpretable Traffic Responsibility from Dashcam Video via Legal Multi Agent Reasoning
2026-03-18 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a new dataset called C-TRAIL that links dashcam videos of traffic accidents to Chinese traffic laws and descriptions of who is responsible. They developed a two-step system where the first part turns video into text descriptions, and the second part uses this text to decide legal responsibility and cite relevant laws. Their approach was tested and found to work better than other existing legal and video understanding AI systems, while also explaining the reasoning behind its decisions.
dashcam videotraffic accidentlegal responsibilitymultimodal datasetChinese traffic regulationtextual video descriptionlegal reasoninglarge language modelsmulti-agent framework
Authors
Jingchun Yang, Jinchang Zhang
Abstract
The widespread adoption of dashcams has made video evidence in traffic accidents increasingly abundant, yet transforming "what happened in the video" into "who is responsible under which legal provisions" still relies heavily on human experts. Existing ego-view traffic accident studies mainly focus on perception and semantic understanding, while LLM-based legal methods are mostly built on textual case descriptions and rarely incorporate video evidence, leaving a clear gap between the two. We first propose C-TRAIL, a multimodal legal dataset that, under the Chinese traffic regulation system, explicitly aligns dashcam videos and textual descriptions with a closed set of responsibility modes and their corresponding Chinese traffic statutes. On this basis, we introduce a two-stage framework: (1) a traffic accident understanding module that generates textual video descriptions; and (2) a legal multi-agent framework that outputs responsibility modes, statute sets, and complete judgment reports. Experimental results on C-TRAIL and MM-AU show that our method outperforms general and legal LLMs, as well as existing agent-based approaches, while providing a transparent and interpretable legal reasoning process.