UrbanSense:AFramework for Quantitative Analysis of Urban Streetscapes leveraging Vision Large Language Models

2025-06-12

AI Summary

Urban cultural and architectural characteristics vary across geography, history, and sociopolitical contexts, yet traditional analyses rely on expert interpretation, lacking standardization and scalability. Method: We propose UrbanSense—the first quantitative street-scene analysis framework based on vision-language models (VLMs)—and introduce UrbanDiffBench, the first benchmark dataset enabling automated, cross-city and cross-temporal stylistic modeling and evolutionary comparison. Our approach integrates multimodal representation learning, style embedding generation, statistical significance testing (two-sample t-test), and human-centered evaluation via Phi coefficient. Contribution/Results: Experiments show that over 80% of generated stylistic descriptions achieve statistical significance (p < 0.05); Phi coefficients reach 0.912 (inter-city) and 0.833 (inter-temporal), confirming robust stylistic discrimination and interpretability. This work establishes a reproducible, scalable, and quantitative paradigm for urban cultural research.

Technology Category

• Computer Vision: Scene Analysis & Understanding
• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Humans and AI: Brain-Sensing and Analysis

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Urban cultures and architectural styles vary significantly across cities due to geographical, chronological, historical, and socio-political factors. Understanding these differences is essential for anticipating how cities may evolve in the future. As representative cases of historical continuity and modern innovation in China, Beijing and Shenzhen offer valuable perspectives for exploring the transformation of urban streetscapes. However, conventional approaches to urban cultural studies often rely on expert interpretation and historical documentation, which are difficult to standardize across different contexts. To address this, we propose a multimodal research framework based on vision-language models, enabling automated and scalable analysis of urban streetscape style differences. This approach enhances the objectivity and data-driven nature of urban form research. The contributions of this study are as follows: First, we construct UrbanDiffBench, a curated dataset of urban streetscapes containing architectural images from different periods and regions. Second, we develop UrbanSense, the first vision-language-model-based framework for urban streetscape analysis, enabling the quantitative generation and comparison of urban style representations. Third, experimental results show that Over 80% of generated descriptions pass the t-test (p less than 0.05). High Phi scores (0.912 for cities, 0.833 for periods) from subjective evaluations confirm the method's ability to capture subtle stylistic differences. These results highlight the method's potential to quantify and interpret urban style evolution, offering a scientifically grounded lens for future design.

Problem

• Analyzing urban streetscape differences across cities objectively
• Standardizing urban cultural studies with automated scalable methods
• Quantifying urban style evolution using vision-language models

Innovation

• Vision-language models for urban streetscape analysis
• Automated quantitative urban style representation
• High accuracy in capturing stylistic differences