STMA-Net: A Spatial Transformation-Based Multiscale Attention Network for Complex Defect Detection With X-Ray Images

In the welding process of long-distance pipelines, cracks pose significant risks and can cause severe damage. The intelligent detection of hazardous defects in pipeline welds, with a focus on complex crack features with different shapes and scales, is a necessary but challenging task. Current deep learning-based visual detection models exhibit weak generalization and transfer capabilities when it comes to complex defect features. To address these challenges, this article proposes a spatial transformation-based multiscale attention network (STMA-Net) for weld defect detection with multiscale and shape-variant features in X-ray images. First, a novel spatial transformation attention network (STAN) is designed to capture the complex deformation features, which enhances the generalization ability of the feature extraction network. Then, in order to better utilize the discriminative features, a multilevel attention feature fusion network (MAFFN) is designed to improve the prediction accuracy of multiscale defects. Furthermore, a multilevel deep supervision is proposed to better update network parameters and enhance the inference ability of multilevel detection heads. Finally, three types of X-ray weld crack datasets in the real world are collected to guide a series of experiments and analyses. The results show that the generalization and transfer capabilities of the proposed method outperforms other detectors in the detection task of cracks and other defects (AP increased by 6.5%).