Automatic Calculation of Graphic Area Change Rate for Icing Overhead Power Line Insulators Based on Bounding Box Automatic Matching and GrabCut Contour Automatic Segmentation

Abstract

Image monitoring of icing insulators is valuable for ice-disaster risk management of overhead power lines. This paper proposes an automatic calculation method of graphic area change rate for icing insulators to address laborious manual viewing, computational complexity, poor generalization, weak interpretability, and label data demand of existing approaches. The method automatically identifies insulators in monitoring images by the trained YOLOv5 model, matches the ice-free and test images taken by the same terminal at the same angle utilizing intersection over union of identified bounding boxes, and segments them using an improved GrabCut algorithm. In the segmentation maps, insulator string contours before and after icing are automatically detected to compute the graphic area change rate. The graphic area change rate of insulators in 815 images monitored by 22 terminals from December 2017 to February 2018 is automatically calculated, which is separately data-fused with the tension monitoring value and equivalent ice thickness collected closest to the image acquisition time to obtain the 22 terminals' time series correlations. The correlations approximately follow normal distributions with mathematical expectations of 0.70 and 0.68 and reach 0.95 and 0.94 for high-quality image samples, respectively, verifying the effectiveness. The method enables real-time evaluation of insulators' icing degrees.