.png){kind=icon}
.png){kind=icon}
Return
BFA-YOLO: A balanced multiscale object detection network for building elements detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.aei.2025.103289.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The detection of fa & ccedil;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). However, this field faces significant challenges, including the uneven distribution of fa & ccedil;ade elements, the presence of small objects, and substantial background noise, which hamper detection accuracy. To address these issues, we developed 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 & ccedil;ade elements. 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 & ccedil;ade element categories. This dataset is developed to address the limitations present in existing fa & ccedil;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 mAP50 on the BFA-3D dataset and the public Fa & ccedil;ade-WHU dataset, respectively, when compared to the baseline YOLOv8 model. These results highlight the superior performance of BFA-YOLO in fa & ccedil;ade element detection and the advancement of intelligent BIM technologies. The dataset and code are available at https://github.com/CVEO/BFA-YOLO.
Keywords:
Building fa & ccedil
ade elements
Object detection
Deep learning
Journal
IF:
9.9
Papers:
4.0K
Citations:
1.7W