A Corrosion Segmentation Method for Substation Equipment Based on Improved TransU-Net and Multimodal Feature Fusion

Substation equipment operating in harsh environments is highly susceptible to corrosion, yet conventional image segmentation methods often fail to achieve precise delineation of corroded regions. Here, we propose an enhanced TransU-Net-based approach for corrosion segmentation. Deformable convolution is incorporated into the encoder to strengthen the model’s capacity to represent irregular corrosion morphologies. A composite color–texture fusion module is developed to jointly exploit color information from HSV and Lab spaces together with multi-scale texture features. In addition, a Shape-IoU loss function is introduced to refine boundary fitting and improve contour accuracy. Experimental evaluations demonstrate that the proposed method consistently outperforms state-of-the-art models across multiple metrics, achieving an Intersection over Union (IoU) of 75.42% and a Recall (PA) of 83.14%. These results confirm that the model substantially enhances corrosion recognition accuracy and edge integrity under complex background conditions, offering a promising strategy for intelligent maintenance of substation infrastructure.