Department of Ocean Engineering, Pukyong National University, Nam-gu, Busan 48513, Korea.
Sensors (Basel). 2020 Dec 2;20(23):6888. doi: 10.3390/s20236888.
In this study, a regional convolutional neural network (RCNN)-based deep learning and Hough line transform (HLT) algorithm are applied to monitor corroded and loosened bolts in steel structures. The monitoring goals are to detect rusted bolts distinguished from non-corroded ones and also to estimate bolt-loosening angles of the identified bolts. The following approaches are performed to achieve the goals. Firstly, a RCNN-based autonomous bolt detection scheme is designed to identify corroded and clean bolts in a captured image. Secondly, a HLT-based image processing algorithm is designed to estimate rotational angles (i.e., bolt-loosening) of cropped bolts. Finally, the accuracy of the proposed framework is experimentally evaluated under various capture distances, perspective distortions, and light intensities. The lab-scale monitoring results indicate that the suggested method accurately acquires rusted bolts for images captured under perspective distortion angles less than 15° and light intensities larger than 63 lux.
在这项研究中，应用了一种基于区域卷积神经网络（RCNN）的深度学习和 Hough 线变换（HLT）算法来监测钢结构中腐蚀和松动的螺栓。监测目标是检测生锈的螺栓与未生锈的螺栓，并估计已识别螺栓的螺栓松动角度。为了实现这些目标，我们采用了以下方法。首先，设计了一种基于 RCNN 的自主螺栓检测方案，用于识别捕获图像中的腐蚀和干净的螺栓。其次，设计了一种基于 HLT 的图像处理算法，用于估计裁剪螺栓的旋转角度（即螺栓松动）。最后，在不同的捕获距离、透视失真和光照强度下，对所提出的框架的准确性进行了实验评估。实验室规模的监测结果表明，对于透视失真角度小于 15°和光照强度大于 63 勒克斯的图像，所提出的方法可以准确地获取生锈的螺栓。
