Automatic Inspection of Bridge Bolts Using Unmanned Aerial Vision and Adaptive Scale Unification-Based Deep Learning

• Published in: Remote sensing (Basel, Switzerland) Vol. 15; no. 2; p. 328
• Main Authors: Jiang, Shang, Zhang, Jian, Wang, Weiguo, Wang, Yingjun
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.01.2023
• Subjects: Accuracy; Artificial vision; Blurring; bolt inspection; Bolted joints; Bridge inspection; Cameras; Classification; convolutional neural network; Corrosion; Damage detection; Data acquisition; Deep learning; Defects; Image segmentation; Inspection; Laboratories; Machine learning; motion deblurring; Neural networks; Object recognition; Remote sensing; super-resolution; Teaching methods; unmanned aerial system
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs15020328

Bolted connections are essential components that require regular inspection to ensure bridge safety. Existing methods mainly rely on traditional artificial vision-based inspection, which is inefficient due to the many bolts of bridges. A vision-based method using deep learning and unmanned aerial vision is proposed to automatically analyze the bridge bolts’ condition. The contributions are as follows: (1) Addressing the problems that motion blur often exists in videos captured by unmanned ariel systems (UASs) with high moving speed, and that bolt damage is hard to accurately detect due to the few pixels a single bolt occupies, a bolt image preprocessing method, including image deblurring based on inverse filtering with camera motion model and adaptive scaling based on super-resolution, is proposed to eliminate the motion blur of bolt images and segment them into subimages with uniform bolt size. (2) Addressing the problem that directly applying an object detection network for both bolt detection and classification may lead to the wrong identification of bolt damage, a two-stage detection method is proposed to divide bolt inspection into bolt object segmentation and damage classification. The proposed method was verified on an in-service bridge to detect bolts and classify them into normal bolts, corrosion bolts, and loose bolts. The results show that the proposed method can effectively eliminate the inherent defects of data acquired by UAS and accurately classify the bolt defects, verifying the practicability and high precision of the proposed method.