The Combination of Transformer and You Only Look Once for Automatic Concrete Pavement Crack Detection

Abstract

The real-time detection of cracks is an important part of road maintenance and an important initiative to reduce traffic accidents caused by road cracks. In response to the lack of efficiency of current research results for the real-time detection of road cracks and the low storage and computational capacity of edge devices, a new automatic crack detection algorithm is proposed: BT–YOLO. We combined Bottleneck Transformer with You Only Look Once (YOLO), which is more conducive to extracting the features of small cracks than YOLOv5s. The introduction of DWConv to the feature extraction network reduced the number of parameters and improved the inference speed of the network. We embedded the SimAM (Simple, Parameter-Free Attention Module) non-parametric attention mechanism to make the crack features more prominent. The experimental results showed that the accuracy of BT–YOLO in crack detection was increased by 4.5%, the mapped value was increased by 8%, and the parameter amount was decreased by 24.9%. Eventually, we deployed edge devices for testing. The frame rate reached 89, which satisfied the requirements of real-time crack detection.