Distribution equalization learning mechanism for road crack detection

Visual-based road crack detection becomes a hot research topic over the last decade because of its huge application demands. Road crack detection is actually a special form of salient object detection task, whose objects are small and distribute randomly in the image compared to the traditional ones, which increase the difficulty of detecting. Most conventional methods utilize bottom information, such as color, texture, and contrast, to extract the crack regions in the image. Even though these methods can achieve satisfactory performances for images with simple scenarios, they are easily interfered by some factors such as light and shadow, which may decrease the detection result directly. Inspired by the competitive performances of deep convolutional neural networks on many visual tasks, we propose a distribution equalization learning mechanism for road crack detection in this paper. Firstly, we consider the crack detection task as a pixel-level classification and use a U-Net based architecture to finalize it. Secondly, the occurrence probability of crack and non-crack are so different, which results in the ill-conditioned classifier and undesirable detection performance, especially the high false detection rate. In this case, we propose a weighted cross entropy loss term and a data augmentation strategy to avoid influence from imbalanced samples through emphasizing the crack regions. Additionally, we propose an auxiliary interaction loss, and combine it with the popular self-attention strategy to alleviate the fracture situations through considering relationships among different local regions in the image. Finally, we tested the proposed method on three public and challenging datasets, and the experimental results demonstrate its effectiveness.