Automated Building Heritage Assessment Using Street-Level Imagery

TL;DR

This paper presents an AI-based approach using GPT and machine learning to efficiently identify and classify heritage values in building facades, aiding heritage preservation efforts.

Contribution

It introduces a novel method combining GPT-derived data with building registers to classify heritage buildings, improving efficiency over traditional methods.

Findings

Achieved a macro F1-score of 0.71 with combined data.

Achieved a macro F1-score of 0.60 using only GPT data.

Demonstrated potential for supporting heritage decision-making.

Abstract

Registration of heritage values in buildings is important to safeguard heritage values that can be lost in renovation and energy efficiency projects. However, registering heritage values is a cumbersome process. Novel artificial intelligence tools may improve efficiency in identifying heritage values in buildings compared to costly and time-consuming traditional inventories. In this study, OpenAI's large language model GPT was used to detect various aspects of cultural heritage value in facade images. Using GPT derived data and building register data, machine learning models were trained to classify multi-family and non-residential buildings in Stockholm, Sweden. Validation against a heritage expert-created inventory shows a macro F1-score of 0.71 using a combination of register data and features retrieved from GPT, and a score of 0.60 using only GPT-derived data. The methods presented can contribute to higher-quality datasets and support decision making.