Day-to-Night Street View Image Generation for 24-Hour Urban Scene Auditing Using Generative AI
Journal of Imaging · 07.05.2024 · 10 (5) · 112
DOI: 10.3390/jimaging10050112 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 07.05.2024. Verfasst von Zhiyi Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Architecture and Urban Planning, Beijing University of Civil Engineering and Architecture, Beijing 100044, China. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 91 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Hong Kong’s URC Seed Fund, Start-up Fund.
Abstract (Originalsprache)
A smarter city should be a safer city. Nighttime safety in metropolitan areas has long been a global concern, particularly for large cities with diverse demographics and intricate urban forms, whose citizens are often threatened by higher street-level crime rates. However, due to the lack of night-time urban appearance data, prior studies based on street view imagery (SVI) rarely addressed the perceived night-time safety issue, which can generate important implications for crime prevention. This study hypothesizes that night-time SVI can be effectively generated from widely existing daytime SVIs using generative AI (GenAI). To test the hypothesis, this study first collects pairwise day-and-night SVIs across four cities diverged in urban landscapes to construct a comprehensive day-and-night SVI dataset. It then trains and validates a day-to-night (D2N) model with fine-tuned brightness adjustment, effectively transforming daytime SVIs to nighttime ones for distinct urban forms tailored for urban scene perception studies. Our findings indicate that: (1) the performance of D2N transformation varies significantly by urban-scape variations related to urban density; (2) the proportion of building and sky views are important determinants of transformation accuracy; (3) within prevailed models, CycleGAN maintains the consistency of D2N scene conversion, but requires abundant data. Pix2Pix achieves considerable accuracy when pairwise day–and–night-night SVIs are available and are sensitive to data quality. StableDiffusion yields high-quality images with expensive training costs. Therefore, CycleGAN is most effective in balancing the accuracy, data requirement, and cost. This study contributes to urban scene studies by constructing a first-of-its-kind D2N dataset consisting of pairwise day-and-night SVIs across various urban forms. The D2N generator will provide a cornerstone for future urban studies that heavily utilize SVIs to audit urban environments.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Architecture and Urban Planning, Beijing University of Civil Engineering and Architecture, Beijing 100044, China.
- School of Architecture, South Minzu University, Chengdu 610225, China.
- Department of Product Research and Development, Smart Gwei Tech, Shanghai 200940, China.
- Department of Computer Science, University of Bath, Bath BA2 7AY, UK.
- Center for Spatial Information Science, The University of Tokyo, Kashiwa-shi 277-0882, Chiba-ken, Japan.
- Department of Urban Planning and Design, The University of Hong Kong, Pokfulam Road, Hong Kong SAR, China.
ORCID-Profile: Wenjing Li, Waishan Qiu
Förderung
- University of Hong Kong’s URC Seed Fund
- Start-up Fund
Zitieren
APA
Liu, Z., Li, T., Ren, T., Chen, D., Li, W., & Qiu, W. (2024). Day-to-Night Street View Image Generation for 24-Hour Urban Scene Auditing Using Generative AI. Journal of Imaging, 10(5), 112. https://doi.org/10.3390/jimaging10050112
Vancouver
Liu Z, Li T, Ren T, Chen D, Li W, Qiu W. Day-to-Night Street View Image Generation for 24-Hour Urban Scene Auditing Using Generative AI. Journal of Imaging. 2024;10(5):112. doi:10.3390/jimaging10050112
BibTeX
@article{Liu2024,
author = {Liu, Zhiyi and Li, Tingting and Ren, Tianyi and Chen, Da and Li, Wenjing and Qiu, Waishan},
title = {Day-to-Night Street View Image Generation for 24-Hour Urban Scene Auditing Using Generative AI},
journal = {Journal of Imaging},
year = {2024},
volume = {10},
number = {5},
pages = {112},
doi = {10.3390/jimaging10050112}
}
EUVIMED