BFA-YOLO: A balanced multiscale object detection network for building façade elements detection
Advanced Engineering Informatics · 2025-05 · 65 · 103289
DOI: 10.1016/j.aei.2025.103289 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Engineering Informatics, 2025-05. Verfasst von Yangguang Chen und 9 weiteren Autor:innen. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 66 Literaturangaben. Gefördert von: China Postdoctoral Science Foundation, National Natural Science Foundation of China, Science and Technology Commission of Shanghai Municipality.
Abstract (Originalsprache)
The detection of fa\c{c}ade elements on buildings, such as doors, windows, balconies, air conditioning units, billboards, and glass curtain walls, is a critical step in automating the creation of Building Information Modeling (BIM). Yet, this field faces significant challenges, including the uneven distribution of fa\c{c}ade elements, the presence of small objects, and substantial background noise, which hamper detection accuracy. To address these issues, we develop the BFA-YOLO model and the BFA-3D dataset in this study. The BFA-YOLO model is an advanced architecture designed specifically for analyzing multi-view images of fa\c{c}ade attachments. It integrates three novel components: the Feature Balanced Spindle Module (FBSM) that tackles the issue of uneven object distribution; the Target Dynamic Alignment Task Detection Head (TDATH) that enhances the detection of small objects; and the Position Memory Enhanced Self-Attention Mechanism (PMESA), aimed at reducing the impact of background noise. These elements collectively enable BFA-YOLO to effectively address each challenge, thereby improving model robustness and detection precision. The BFA-3D dataset, offers multi-view images with precise annotations across a wide range of fa\c{c}ade attachment categories. This dataset is developed to address the limitations present in existing fa\c{c}ade detection datasets, which often feature a single perspective and insufficient category coverage. Through comparative analysis, BFA-YOLO demonstrated improvements of 1.8\% and 2.9\% in mAP$_{50}$ on the BFA-3D dataset and the public Fa\c{c}ade-WHU dataset, respectively, when compared to the baseline YOLOv8 model. These results highlight the superior performance of BFA-YOLO in fa\c{c}ade element detection and the advancement of intelligent BIM technologies.
Förderung
- China Postdoctoral Science Foundation
- National Natural Science Foundation of China
- Science and Technology Commission of Shanghai Municipality
Zitieren
APA
Chen, Y., Wang, T., Chen, G., Zhu, K., Tan, X., Wang, J., Guo, W., Wang, Q., Luo, X., & Zhang, X. (2025). BFA-YOLO: A balanced multiscale object detection network for building façade elements detection. Advanced Engineering Informatics, 65, 103289. https://doi.org/10.1016/j.aei.2025.103289
Vancouver
Chen Y, Wang T, Chen G, Zhu K, Tan X, Wang J, et al. BFA-YOLO: A balanced multiscale object detection network for building façade elements detection. Advanced Engineering Informatics. 2025;65:103289. doi:10.1016/j.aei.2025.103289
BibTeX
@article{Chen2025,
author = {Chen, Yangguang and Wang, Tong and Chen, Guanzhou and Zhu, Kun and Tan, Xiaoliang and Wang, Jiaqi and Guo, Wenchao and Wang, Qing and Luo, Xiaolong and Zhang, Xiaodong},
title = {BFA-YOLO: A balanced multiscale object detection network for building façade elements detection},
journal = {Advanced Engineering Informatics},
year = {2025},
volume = {65},
pages = {103289},
doi = {10.1016/j.aei.2025.103289}
}
EUVIMED