Evaluation of Street Building Color Quality Based on Artificial Intelligence and Street View Images - Taking the Duobao Road Historical and Cultural Block in Guangzhou as an Example
International Journal of Communication Systems and Network Technologies · 31.08.2025 · 14 (2) · 108-117
DOI: 10.18486/ijcsnt/14.2.010 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Communication Systems and Network Technologies, online erschienen am 31.08.2025. Verfasst von Shi Yang. Die Arbeit nennt 15 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
In the context of rapid urban renewal, the color style of buildings in historical and cultural blocks is vulnerable to constructive destruction, and it is urgent to establish a set of objective, efficient and quantitative evaluation methods that meet the needs of protection planning. To this end, this study proposes a set of evaluation frameworks for street building color quality. Firstly, high-resolution street view images of the Duobao Road historical and cultural district in Guangzhou are collected as the basic data source. Then, DeepLabv3+ (Deep Labelling version 3+) is used to accurately identify and extract the building facade areas in the image. In addition, multi-dimensional color features of the building facades are extracted and calculated. Finally, a comprehensive evaluation system for the color quality of street buildings is constructed that integrates objective quantitative indicators. The experimental results show that the overall color coordination score of the block buildings is high, and most of the main colors of the buildings meet the requirements of Guangzhou's traditional color spectrum (the highest matching degree is 92% and the error range is small), and the AI evaluation results are highly consistent with the expert evaluation. This method provides efficient and reliable technical support for the scientific evaluation and effective control of the architectural colors of historical and cultural blocks.
Zitieren
APA
Yang, S. (2025). Evaluation of Street Building Color Quality Based on Artificial Intelligence and Street View Images - Taking the Duobao Road Historical and Cultural Block in Guangzhou as an Example. International Journal of Communication Systems and Network Technologies, 14(2), 108-117. https://doi.org/10.18486/ijcsnt/14.2.010
Vancouver
Yang S. Evaluation of Street Building Color Quality Based on Artificial Intelligence and Street View Images - Taking the Duobao Road Historical and Cultural Block in Guangzhou as an Example. International Journal of Communication Systems and Network Technologies. 2025;14(2):108-117. doi:10.18486/ijcsnt/14.2.010
BibTeX
@article{Yang2025,
author = {Yang, Shi},
title = {Evaluation of Street Building Color Quality Based on Artificial Intelligence and Street View Images - Taking the Duobao Road Historical and Cultural Block in Guangzhou as an Example},
journal = {International Journal of Communication Systems and Network Technologies},
year = {2025},
volume = {14},
number = {2},
pages = {108--117},
doi = {10.18486/ijcsnt/14.2.010}
}
EUVIMED