Won Kwanghee, Sim Chungwook
Electrical Engineering and Computer Science, South Dakota State University, Brookings, SD 57007, USA.
Department of Civil and Environmental Engineering, University of Nebraska-Lincoln, Omaha, NE 68182, USA.
Sensors (Basel). 2020 Mar 26;20(7):1838. doi: 10.3390/s20071838.
Transverse cracks on bridge decks provide the path for chloride penetration and are the major reason for deck deterioration. For such reasons, collecting information related to the crack widths and spacing of transverse cracks are important. In this study, we focused on developing a data pipeline for automated crack detection using non-contact optical sensors. We developed a data acquisition system that is able to acquire data in a fast and simple way without obstructing traffic. Understanding that GPS is not always available and odometer sensor data can only provide relative positions along the direction of traffic, we focused on providing an alternative localization strategy only using optical sensors. In addition, to improve existing crack detection methods which mostly rely on the low-intensity and localized line-segment characteristics of cracks, we considered the direction and shape of the cracks to make our machine learning approach smarter. The proposed system may serve as a useful inspection tool for big data analytics because the system is easy to deploy and provides multiple properties of cracks. Progression of crack deterioration, if any, both in spatial and temporal scale, can be checked and compared if the system is deployed multiple times.
桥面板上的横向裂缝为氯化物渗透提供了通道，是桥面板劣化的主要原因。因此，收集与横向裂缝宽度和间距相关的信息非常重要。在本研究中，我们专注于开发一种使用非接触式光学传感器进行自动裂缝检测的数据管道。我们开发了一种数据采集系统，该系统能够以快速简单的方式采集数据，而不会妨碍交通。由于了解到GPS并非始终可用，里程计传感器数据只能提供沿交通方向的相对位置，我们专注于仅使用光学传感器提供一种替代定位策略。此外，为了改进现有的裂缝检测方法，这些方法大多依赖于裂缝的低强度和局部线段特征，我们考虑了裂缝的方向和形状，以使我们的机器学习方法更智能。所提出的系统可以作为大数据分析的有用检测工具，因为该系统易于部署，并能提供裂缝的多种属性。如果多次部署该系统，可以检查和比较裂缝劣化在空间和时间尺度上的进展情况（如果有进展的话）。
