AI Matches Human Experts in Building Typology from Street View

Zahratu Shabrina, Muhammad Asa, Jin Rui, Lu Yin, Stephen Law· July 17, 2026 View original

Summary

This research compares Vision-Language Models (VLMs) with human experts in inferring building typologies (construction, use, storeys) from Google Street View images. VLMs achieved approximately 70% accuracy, demonstrating their potential for urban analysis automation, though they focus more on visual cues while humans use broader contextual knowledge.

The study explores the capability of Vision-Language Models (VLMs) to infer building typologies, such as construction type, current use, and number of storeys, directly from Google Street View (GSV) images. The VLM predictions were benchmarked against classifications made by human experts, specifically civil engineers and architects, who provided manually labeled ground-truth data. Researchers evaluated several state-of-the-art VLMs, including GPT-4o, Claude 3.5 Sonnet, and Gemini 2.0 Flash, employing various scaling strategies and prompting techniques. They found that Chain-of-Thought prompts generally led to more stable model performance. The analysis of VLM reasoning, by examining keyword probabilities in AI explanations, revealed that AI models tend to prioritize visual indicators. In contrast, human experts integrate broader contextual cues and domain knowledge alongside visual information. Overall, VLMs achieved an average accuracy of about 70% in approximating expert classifications, highlighting their potential as complementary tools for large-scale urban analysis and pattern recognition.

Why it matters

For urban planners, real estate professionals, and civil engineers, this research demonstrates AI's potential to automate and scale building typology classification from visual data, offering efficiencies in urban analysis, property assessment, and infrastructure planning.

How to implement this in your domain

  1. 1Pilot VLM for urban analysis: Experiment with state-of-the-art VLMs to automate building typology classification in your urban planning or real estate projects.
  2. 2Integrate Chain-of-Thought prompting: Apply advanced prompting techniques to improve the stability and accuracy of VLM predictions for complex visual tasks.
  3. 3Combine AI with expert knowledge: Design workflows where AI provides initial classifications, which human experts then refine with their broader contextual understanding.
  4. 4Leverage street view data: Explore using publicly available street view imagery as a scalable data source for AI-driven urban insights.

Who benefits

Urban PlanningReal EstateCivil EngineeringArchitectureGovernment (municipal planning)

Key takeaways

  • VLMs can classify building typologies from street view images with approximately 70% accuracy compared to human experts.
  • Chain-of-Thought prompting improves VLM performance in this task.
  • AI focuses on visual cues, while human experts integrate broader contextual and domain knowledge.
  • VLMs offer potential for scalable automation in urban analysis and pattern recognition.

Original post by Zahratu Shabrina, Muhammad Asa, Jin Rui, Lu Yin, Stephen Law

"arXiv:2607.14756v1 Announce Type: new Abstract: This research investigates the potential of Vision-Language Models (VLMs) to infer building typologies: Construction, Current Use, and Storeys from Google Street View (GSV) images. Predictions generated by VLMs are compared with inf…"

View on X

Originally posted by Zahratu Shabrina, Muhammad Asa, Jin Rui, Lu Yin, Stephen Law on X · view source

Want to go deeper?

Turn these trends into skills with Learnijoy's hands-on AI & tech courses.

Explore courses

More in AI Research