BuildingView: Constructing Urban Building Exteriors Databases with Street View Imagery and Multimodal Large Language Mode
🤖 AI Summary
Urban building façades lack systematic quantification and structured databases for multidimensional performance metrics—namely energy efficiency, environmental sustainability, and human-centered design.
Method: We propose an automated annotation framework integrating street-level imagery (Google Street View) with spatial data (OpenStreetMap) and leveraging the ChatGPT-4o multimodal API for fine-grained façade attribute recognition. A reusable, literature-informed classification system was developed and validated through field sampling.
Contribution/Results: This work establishes the first cross-city transferable façade annotation paradigm, yielding a high-accuracy, expert-validated database covering New York, Amsterdam, and Singapore. Key attribute annotation accuracy is significantly improved over prior approaches. The resulting structured dataset serves as a scalable data foundation and decision-support tool for urban planning, green building design, and environmental policy formulation.
Application Category
📝 Abstract
Urban Building Exteriors are increasingly important in urban analytics, driven by advancements in Street View Imagery and its integration with urban research. Multimodal Large Language Models (LLMs) offer powerful tools for urban annotation, enabling deeper insights into urban environments. However, challenges remain in creating accurate and detailed urban building exterior databases, identifying critical indicators for energy efficiency, environmental sustainability, and human-centric design, and systematically organizing these indicators. To address these challenges, we propose BuildingView, a novel approach that integrates high-resolution visual data from Google Street View with spatial information from OpenStreetMap via the Overpass API. This research improves the accuracy of urban building exterior data, identifies key sustainability and design indicators, and develops a framework for their extraction and categorization. Our methodology includes a systematic literature review, building and Street View sampling, and annotation using the ChatGPT-4O API. The resulting database, validated with data from New York City, Amsterdam, and Singapore, provides a comprehensive tool for urban studies, supporting informed decision-making in urban planning, architectural design, and environmental policy. The code for BuildingView is available at https://github.com/Jasper0122/BuildingView.
Problem
Research questions and friction points this paper is trying to address.
Creating accurate urban building exterior databases
Identifying sustainability and design indicators
Developing a framework for data extraction and categorization
Innovation
Methods, ideas, or system contributions that make the work stand out.
Integrates Google Street View with OpenStreetMap
Uses ChatGPT-4O for urban annotation
Develops framework for sustainability indicators
🔎 Similar Papers
No similar papers found.
