Streetscape Analysis with Generative AI (SAGAI): Vision-language assessment and mapping of urban scenes

Streetscapes are an essential component of urban space. Their assessment is presently either limited to morphometric properties of their mass skeleton or requires labor-intensive qualitative evaluations of visually perceived qualities. This paper introduces SAGAI: Streetscape Analysis with Generative Artificial Intelligence, a modular workflow for scoring street-level urban scenes using open-access data and vision-language models. SAGAI integrates OpenStreetMap geometries, Google Street View imagery, and a lightweight version of the LLaVA model to generate structured spatial indicators from images via customizable natural language prompts. The pipeline includes an automated mapping module that aggregates visual scores at both the point and street levels, enabling direct cartographic interpretation. It operates without task-specific training or proprietary software dependencies, supporting scalable and interpretable analysis of urban environments. Two exploratory case studies in Nice and Vienna illustrate SAGAI’s capacity to produce geospatial outputs from vision-language inference. The initial results show strong performance for binary urban–rural scene classification, moderate precision in commercial feature detection, and lower estimates, but still informative, of sidewalk width. Fully deployable by any user, SAGAI can be easily adapted to a wide range of urban research themes, such as walkability, safety, or urban design, through prompt modification alone. • SAGAI is a lightweight, modular workflow for assessing streetscape features from street-level imagery using only a bounding box as input, with no need for annotated datasets. • The pipeline integrates OpenStreetMap, Google Street View, and the LLaVA 1.6 Mistral-7B vision-language model to classify, count, and measure features directly from urban scenes. • SAGAI supports zero-shot visual inference through a modular prompting system, allowing users to define tasks such as urban-rural classification, storefront counting, or sidewalk width estimation via natural language instructions. • The system is fully open-source and deployable on free-tier cloud environments. It was tested in two suburban districts of Nice (France) and Vienna (Austria), and can scale to any region with street-level imagery. • Final outputs consist of spatialized scores mapped at both point and street segment levels, enabling direct visual interpretation and integration into geospatial analyses or planning tools.