Zeng, Z;
Goo, JM;
Wang, X;
Chi, B;
Wang, M;
Boehm, J;
(2024)
Zero-Shot Building Age Classification from Facade Image Using GPT-4.
In:
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences.
(pp. pp. 457-464).
Copernicus GmbH
Preview |
Text
isprs-archives-XLVIII-2-2024-457-2024.pdf - Published Version Download (6MB) | Preview |
Abstract
A building’s age of construction is crucial for supporting many geospatial applications. Much current research focuses on estimating building age from facade images using deep learning. However, building an accurate deep learning model requires a considerable amount of labelled training data, and the trained models often have geographical constraints. Recently, large pre-trained vision language models (VLMs) such as GPT-4 Vision, which demonstrate significant generalisation capabilities, have emerged as potential training-free tools for dealing with specific vision tasks, but their applicability and reliability for building information remain unexplored. In this study, a zero-shot building age classifier for facade images is developed using prompts that include logical instructions. Taking London as a test case, we introduce a new dataset, FI-London, comprising facade images and building age epochs. Although the training-free classifier achieved a modest accuracy of 39.69%, the mean absolute error of 0.85 decades indicates that the model can predict building age epochs successfully albeit with a small bias. The ensuing discussion reveals that the classifier struggles to predict the age of very old buildings and is challenged by fine-grained predictions within 2 decades. Overall, the classifier utilising GPT-4 Vision is capable of predicting the rough age epoch of a building from a single facade image without any training. The code and dataset are available at https://zichaozeng.github.io/ba_classifier.
| Type: | Proceedings paper |
|---|---|
| Title: | Zero-Shot Building Age Classification from Facade Image Using GPT-4 |
| Event: | ISPRS TC II Mid-term Symposium |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.5194/isprs-archives-XLVIII-2-2024-457-2024 |
| Publisher version: | https://doi.org/10.5194/isprs-archives-XLVIII-2-20... |
| Language: | English |
| Additional information: | © Author(s) 2024. This work is distributed under the Creative Commons Attribution 4.0 License. |
| Keywords: | Building, Facade, Image Understanding, Deep Learning, Multi-modal, Large Vision Language Model |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Bartlett School Env, Energy and Resources UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of the Built Environment > Centre for Advanced Spatial Analysis |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10194492 |
Archive Staff Only
 |
View Item |
