BFA-YOLO：一种用于建筑立面附属物检测的平衡多尺度目标检测网络
BFA-YOLO: A balanced multiscale object detection network for building façade attachments detection
AI总结：
针对建筑立面元素检测中分布不均、小目标和背景噪声问题，提出BFA-YOLO模型与BFA-3D数据集，通过集成FBSM、TDATH和PMESA模块提升检测精度，在两个数据集上mAP50较YOLOv8分别提升1.8%和2.9%。
摘要：
检测建筑立面元素（如门、窗、阳台、空调外机、广告牌和玻璃幕墙）是实现建筑信息模型（BIM）自动化创建的关键步骤。然而，该领域面临重大挑战，包括立面元素分布不均、小目标的存在以及大量背景噪声，这些都阻碍了检测精度的提升。为了解决这些问题，本研究开发了BFA-YOLO模型和BFA-3D数据集。BFA-YOLO模型是一种专门为分析立面附属物多视角图像而设计的先进架构。它集成了三个新颖组件：解决目标分布不均问题的特征平衡主轴模块（FBSM）；增强小目标检测的目标动态对齐任务检测头（TDATH）；以及旨在降低背景噪声影响的位置记忆增强自注意力机制（PMESA）。这些组件共同使BFA-YOLO能够有效应对各项挑战，从而提升模型鲁棒性和检测精度。BFA-3D数据集提供了涵盖广泛立面附属物类别的多视角图像及精确标注。该数据集的构建旨在克服现有立面检测数据集的局限性，这些现有数据集通常仅具有单一视角且类别覆盖不足。通过对比分析，与基线YOLOv8模型相比，BFA-YOLO在BFA-3D数据集和公开的Façade-WHU数据集上的mAP$_{50}$分别提升了1.8%和2.9%。这些结果突显了BFA-YOLO在立面元素检测中的卓越性能，推动了智能BIM技术的发展。
英文摘要：
The detection of façade 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 façade 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 façade 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 façade attachment categories. This dataset is developed to address the limitations present in existing façade 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 Façade-WHU dataset, respectively, when compared to the baseline YOLOv8 model. These results highlight the superior performance of BFA-YOLO in façade element detection and the advancement of intelligent BIM technologies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
