Training Surface Crack Segmentation Networks With Groupwise Normalization Attention and Padding–Shifting–Cutting Convolution

Cracks can provide early warning for damage of roadway pavement and civil infrastructure. However, due to the diversity of texture and color of the materials, the complexity of the background, and the interference factors, such as noise, low illumination, and tiny cracks, crack detection using image sensor is extremely challenging. To address the above problems, we propose a surface crack detection method based on semantic segmentation network. First, to cope with the interference of various complex situations in wild scenes, we propose an attention mechanism based on groupwise normalization to suppress meaningless features and highlight meaningful features. We compress feature maps into components of a vector along the channel dimension and normalize these components by each group in the vector, then use the learnable parameters in groupwise normalization to weight feature maps by channel. Second, to enlarge the receptive field, we propose a “padding–shifting–cutting” convolution (PSCconv). Our proposed convolution cyclically shifts the feature maps by different counts of pixels horizontally and vertically. After shifted, each part of the feature map exchanges information, thus our model can obtain longer range crack information and detect tiny cracks better. Finally, experimental results show that our method has achieved better performance than other methods on four public datasets: crack forest dataset (CFD), CrackTree260, DeepCrack, and CrackLS315. Our model surpasses most excellent existing models in terms of precision, recall,
$F1$
-score, mean intersection-over-union (mIoU), and intersection-over-union (IoU) on the CrackTree260 dataset.