Traditional method of insulator defect identification is manually operated, which has low efficiency and high cost. Therefore, an automatic method of insulator defect identification is proposed in this paper. Firstly, image segmentation was operated by classification method of Random Forest (RF) to realize the object recognition of the insulator. Then, the method of Convolutional Neural Network (CNN) was adopted to classify the normal and defect states of insulators, and finally, the location of self-explosion defect identification was realized by Faster Region-Convolutional Neural Network (Faster R-CNN). A large number of images of insulators taken by Unmanned Aerial Vehicle (UAV) were used as experimental data to verify the method. The results show that the method in this paper could efficiently identify the defects of insulators, and the recognition rate reached 89.0%. The results can provide some references for the research of insulator defect identification of transmission lines.

Aiming at the problems of low accuracy and poor generalization ability of insulator defect detection in complex aerial images by existing insulator defect detection algorithms, the possibility of using semantic segmentation technology to simplify insulator features in complex images is explored. The semantic segmentation model DeepLabv3 is cascaded with the target detector yolov3 to realize the semantic segmentation of insulators in aerial images and the detection of defects. The experimental results show that the use of the strategy of semantic segmentation and target detection can increase the accuracy of insulator defect detection by 12.58%, which effectively improves the performance of the detection model.

No abstract