Segmentation method of U-net sheet metal engineering drawing based on CBAM attention mechanism

Abstract In this paper, an improved U-net welding engineering drawing segmentation model is proposed for the automatic segmentation and extraction of sheet metal engineering drawings in the process of mechanical manufacturing, to improve the cutting efficiency of sheet metal parts. To construct a high-precision segmentation model for sheet metal engineering drawings, this paper proposes a U-net jump structure with an attention mechanism based on the Convolutional Attention Module (CBAM) attention mechanism. At the same time, this paper also designs an encoder jump structure with vertical double pooling convolution, which fuses the features after maximum pooling+convolution of the high-dimensional encoder with the features after average pooling+convolution of the low-dimensional encoder. The method in this paper not only improves the global semantic feature extraction ability of the model but also reduces the dimensionality difference between the low-dimensional encoder and the high-dimensional decoder. Using Vgg16 as the backbone network, experiments verify that the IoU, mAP, and Accu indices of this paper’s method in the welding engineering drawing dataset segmentation task are 84.72%, 86.84%, and 99.42%, respectively, which are 22.10, 19.09 and 0.05 percentage points higher compared to the traditional U-net model, and it has a relatively excellent value in engineering applications.