Automating Crash Diagram Generation Using Vision-Language Models: A Case Study on Multi-Lane Roundabouts
On the map: Multimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
Abstract (arXiv)
Crash diagrams are essential tools in transportation safety analysis, yet their manual preparation remains time-consuming and prone to human variability. This study investigates the use of Vision-Language Models (VLMs) to automate crash diagram generation from police crash reports, focusing on multilane roundabouts as a challenging test case. A three-part structured prompt framework was developed to guide model reasoning through interpretation, extraction, and visual synthesis, while a 10-metric evaluation system was designed to assess diagram quality in terms of semantic accuracy, spatial fidelity, and visual clarity. Three popular models, including GPT-4o, Gemini-1.5-Flash, and Janus-4o, were tested on 79 crash reports. GPT-4o achieved the highest average performance (6.29 out of 10), followed by Gemini-1.5-Flash (5.28) and Janus-4o (3.64). The analysis revealed GPT-4o's superior spatial reasoning and alignment between extracted and visualized crash data. These results highlight both the promise and current limitations of VLMs in engineering visualization tasks. The study lays the groundwork for integrating generative AI into crash analysis workflows to improve efficiency, consistency, and interpretability.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Driving VLMs and open-vocabulary detection, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 4 of its 14 references that are in the map. First posted on arXiv 9 Mar 2026.
Builds on
4 of 14 references.
References · 4
- 2025ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generationcited by 97
- 2024Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inferencecited by 14
- 2025CrashSage: A Large Language Model-Centered Framework for Contextual and Interpretable Traffic Crash Analysiscited by 6
- 2025Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challengescited by 3
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Vision and Language: Novel Representations and Artificial intelligence for Driving Scene Safety Assessment and Autonomous Vehicle Planning
- 2024GPT-4V as Traffic Assistant: An In-depth Look at Vision Language Model on Complex Traffic Events
- 2025Mind the Gap: Evaluating LLM Understanding of Human-Taught Road Safety Principles
- 2025Are VLMs Ready for Lane Topology Awareness in Autonomous Driving?
- 2025Visual Reasoning at Urban Intersections: FineTuning GPT-4o for Traffic Conflict Detection
- 2026CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning
- 2025Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trends
- 2025Hierarchical Reasoning with Vision-Language Models for Incident Reports from Dashcam Videos