Search

Many damage detection methods that use data obtained from contact sensors physically attached to structures have been developed. However, damage-sensitive features such as the modal properties of steel and reinforced concrete are sensitive to environmental conditions such as temperature and humidity. These uncertainties are difficult to address with a regression model or any other temperature compensation method, and these uncertainties are the primary causes of false alarms. A vision-based remote sensing system can be an option for addressing some of the challenges inherent in traditional sensing systems because it provides information about structural conditions. Using bolted connections is a common engineering practice, but very few vision-based techniques have been developed for loosened bolt detection. Thus, this article proposes a fully automated vision-based method for detecting loosened civil structural bolts using the Viola–Jones algorithm and support vector machines. Images of bolt connections for training were taken with a smartphone camera. The Viola–Jones algorithm was trained on two datasets of images with and without bolts to localize all the bolts in the images. The localized bolts were automatically cropped and binarized to calculate the bolt head dimensions and the exposed shank length. The calculated features were fed into a support vector machine to generate a decision boundary separating loosened and tight bolts. We tested our method on images taken with a digital single-lens reflex camera. [ABSTRACT FROM AUTHOR]

Many contact-sensor-based methods for structural damage detection have been developed. However, these methods have difficulty compensating for environmental effects, such as variation or changes in temperature and humidity, which may lead to false alarms. In order to partially overcome these disadvantages, vision-based approaches have been developed to detect corrosions, cracks, delamination, and voids. However, there are few such approaches for loosened bolts. Therefore, we propose a novel vision-based detection method. Target images of loosened bolts were taken by a smartphone camera. From the images, simple damage-sensitive features, such as the horizontal and vertical lengths of the bolt head, were calculated automatically using the Hough transform and other image processing techniques. A linear support vector machine was trained with the aforementioned features, thereby building a robust classifier capable of automatically differentiating tight bolts from loose bolts. Leave-one-out cross-validation was adapted to analyze the performance of the proposed algorithm. The results highlight the excellent performance of the proposed approach to detecting loosened bolts, and that it can operate in quasi-real-time. [ABSTRACT FROM AUTHOR]