面向变电设备金属锈蚀检测的分层嵌套标注方法

To solve the ambiguity and uncertainty in the labeling process of power equipment corrosion datasets, a novel hierarchical annotation method (HAM) is proposed. Firstly, large boxes are used to label a large area covering the range of corrosion, provided that the area is visually continuous and adjacent to corrosion that cannot be clearly divided. Secondly, in each labeling box established in the first step, regions with distinct corrosion and relative independence are labeled to form a second layer of nested boxes. Finally, a series of comparative experiments are conducted with other common annotation methods to validate the effectiveness of HAM. The experimental results show that, with the help of HAM, the recall of YOLOv5 increases from 50.79% to 59.41%; the recall of Faster R-CNN+VGG16 increases from 66.50% to 78.94%; the recall of Faster R-CNN+Res101 increases from 78.32% to 84.61%. Therefore, HAM can effectively improve the detection ability of mainstream models in detecting metal corrosion.