Can I read Insulators’ Identification and Missing Defect Detection in Aerial Images Based on Cascaded YOLO Models on EtoBox?

Insulators’ Identification and Missing Defect Detection in Aerial Images Based on Cascaded YOLO Models by Jingjing Liu; Chuanyang Liu; Yiquan Wu; Zuo Sun; Huajie Xu is a Computer Science article available to read on EtoBox.

What is Insulators’ Identification and Missing Defect Detection in Aerial Images Based on Cascaded YOLO Models about?

Insulators identi cation and their missing defect detection are of paramount importance for the intelligent inspection of highvoltage transmission lines. As the backgrounds are complex, some insulators may be occluded, and the missing defect of the insulator is so small that it is not easily detected from aerial images with di erent backgrounds. To address the above issues, in this study, a cascaded You Only Look Once (YOLO) models are mainly explored to perform insulators and their defect detection in aerial images. Firstly, the datasets used for insulators location and missing defect detection are created. Secondly, a new model is proposed to locate the position of insulators, which is improved in the feature extraction network and multisacle prediction network based on previous YOLOv3-dense model. An improved YOLOv4-tiny model is used to conduct missing defect detection on the detected insulators. And then, the proposed YOLO models are trained and tested on the built datasets, respectively. Finally, the nal models are cascaded for insulators identi cation and their missing defect detection. e average precision of missing defect detection can reach 98.4%, which is 5.2% higher tha

Who reads Insulators’ Identification and Missing Defect Detection in Aerial Images Based on Cascaded YOLO Models?

Author

Jingjing Liu; Chuanyang Liu; Yiquan Wu; Zuo Sun; Huajie Xu

Published

2022

Language

EN

Field

Computer Science (Physical Sciences)