A review of image-based insulator defect detection algorithms for transmission lines

• Published in: 2024 5th International Conference on Computer Vision, Image and Deep Learning (CVIDL) pp. 718 - 724
• Main Authors: Li, Xiaomian, Blancaflor, Eric B.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 19-04-2024
• Subjects: Accuracy; Autonomous aerial vehicles; Deep learning; Inspection; Insulator defect detection; Insulators; Power transmission lines; Reviews; YOLOv
• DOI: 10.1109/CVIDL62147.2024.10603625

insulator defect detection plays a very important role in ensuring the safety of transmission lines. Accurate and fast detection algorithms can help operation and maintenance personnel quickly locate the position of defective insulators and replace them in a timely manner. Unmanned aerial vehicles (UAV) are currently the most ideal new type of line inspection method, which can effectively overcome the shortcomings of manual inspection and have been widely used in overhead transmission line inspection. This article focuses on the detection scenarios of insulator defects in overhead transmission lines, summarizes commonly used deep learning object detection algorithms, compares the detection strategies, detection accuracy, and detection speed of different algorithms, analyzes the challenges faced in insulator defect detection in response to the shortcomings of existing insulator detection, and provides prospects.