Discriminative features based comprehensive detector for defective insulators

Insulators are essential equipment to ensure the safety and reliability of power transmission systems. Defective insulators may cause partial discharge and even lead to serious safety accidents. Hence it is necessary to accurately identify the defective insulator from a string of insulators. However, small defect poses significant challenges for recognizing the defective insulator from a large number of insulators. To address these issues, we collect and annotate the randomly generated defect dataset (RGDD). Further, the discriminative feature learning-based detector (DFLD) is constructed based on the pattern of backbone-neck-head. Specifically, considering the simultaneous existence of many insulators, attention-based bidirectional feature pyramid (ABFP) is designed to capture the discriminative information. Considering the small size of defective part, the efficient receptive field adaptation (ERFA) module is constructed to enhance the perception of contextual information related to defective insulators. Meanwhile, the two-stage detection head is designed to correct the location of defective insulators. It also adapts to the shape variation of insulators by the deformable convolution. On this basis, the keypoints method is introduced to more accurately represent the location of defective insulators. Due to the imbalance between positive and negative samples, the Adaptive Threshold Sample Assignment (ATSA) Strategy is proposed for selecting the best positive samples. DFLD has achieved good detection performance compared with classical object detection networks on the RGDD dataset and CPLID dataset. The ablation experiments are conducted on the RGDD dataset. It is verified that the discriminative features from DFLD can effectively recognize the small defect from insulators.