Deep Learning Architecture for Computer Vision-based Structural Defect Detection

Structural health monitoring (SHM) refers to the implementation of a damage detection strategy for structures. Fault occurrence in these structural systems during the operation is inevitable. Efficient, fast, and precise health monitoring methods are required to proactively perform the necessary repairs and maintenance on time before it is too late. The current structural health monitoring methods involve physically attached sensors or non-contact vision-based vibration measurements. However, these methods have significant drawbacks due to the low spatial resolution, weight influence on the lightweight structure, and time/labor consumption. Recently, computer-vison-based deep learning methods like convolutional neural network (CNN) and fully convolutional neural network (FCN) have been applied for defect detection and localization, which address the aforementioned problems and obtain high accuracy. This paper proposes a novel hybrid deep learning architecture comprising CNN and temporal convolutional networks (CNN-TCN) for the computer vision-based defect detection task. Various beam samples, consisting of five different materials and various structural defects, were used to evaluate the proposed deep learning algorithms' performance. The proposed deep learning methods treat each pixel of the video frame like a sensor to extract valuable features for defect detection. Through empirical results, we demonstrate that this 'pixel-sensor' approach is more efficient and accurate and can achieve a better defect detection performance on different beam samples compared with the current state-of-the-art approaches, including CNN-long short-term memory (LSTM), CNN-bidirectional long short-term memory (BiLSTM), multi-scale CNN-LSTM, and CNN-gated recurrent unit(GRU) methods.