Sep 2026· Scientific Research Bulletin· 0 citations· 20 references
Abstract
Building facade inspection is essential for maintaining structural safety, yet conventional approaches remain limited by high-altitude risks, labour intensity, and inconsistent evaluation. This study develops Zhiyi Building Inspection, an integrated unmanned aerial vehicle-artificial intelligence-building information modeling (UAV-AI-BIM) framework for automated facade damage detection. The system combines UAV-based image acquisition with real-time kinematic (RTK) positioning, an improved You Only Look Once version 5 Large (YOLOv5l) detection model incorporating Complete Intersection over Union (CIoU) loss and Convolutional Block Attention Module (CBAM), Sobel-based defect quantification, severity assessment, and BIM-assisted visualisation. A dataset of 3,982 high-resolution images covering eight facade-defect categories was constructed for model training and evaluation. Experimental results demonstrate that the proposed framework improves detection accuracy while maintaining real-time processing capability and provides engineering-oriented outputs including defect location, severity, and inspection reports. The study demonstrates the feasibility of integrating UAV sensing, artificial intelligence, and digital building management for safer and more efficient facade maintenance.
An improved YOLOv5s(You Only Look Once version 5s) object detection method is proposed to address the issues of target occlusion, frequent missed small targets, and low recognition accuracy in unmanned aerial vehicle (UAV) detection images of power infrastructure sites. GrabCut(Interactive Foreground Extraction using I...
Lei Zhang, Xiao-Li Qu, Chao Sun· Journal of Physics, Conferen...· 0 citations
In UAV aerial photography-based pavement defect detection, several challenges remain, including large variations in defect scales, complex background interference, difficult extraction of effective features, and the inability of existing methods to balance detection accuracy and real-time performance. To address these...
Yan Wu, Yi-Ming Li· International Conference on...· 0 citations
Automated vision-based structural health monitoring (SHM) of catenary support components is critical for ensuring railway operational safety. However, achieving reliable structural damage identification in practical engineering scenarios is hindered by complex environmental and operational variations (EOVs) in aerial i...
The proposed Confidence-Guided Cascade Decision System (CG-CDS) effectively addresses the inherent trade-off between computational efficiency and detection accuracy by dynamically routing challenging samples to a specialized fine-grained detector, which achieves robust performance across diverse environmental condition...
Accurate pavement-distress detection in unmanned aerial vehicle (UAV) imagery remains challenging because defects exhibit weak texture, irregular geometry, scale variation, and visual similarity to markings, shadows, water, and repaired pavement. This study presents YOLO-MCG, an engineering adaptation of YOLOv10 that i...
Rong Li, Jian Liu, Cui-Zhen Sun et al.· Electronics· 0 citations
This study proposes a multimodal UAV-based slope inspection framework with Vision Foundation Models and decision-level fusion, and evaluated the proposed framework using 2007 patch triplets from five highway slopes in Shandong, China.
