期刊
APPLIED SCIENCES-BASEL
卷 11, 期 10, 页码 -出版社
MDPI
DOI: 10.3390/app11104647
关键词
fault detection; aerial image; complex background; deep learning; image processing; intelligent inspection
类别
资金
- National Nature Science Founding of China [61573183]
- Major Natural Research Project of Anhui Provincial [KJ2019ZD63]
- Excellent Young Talents support plan in Colleges of Anhui Province [gxyq 2019109, gxgnfx 2019056]
Insulator fault detection is crucial for high-voltage transmission lines, and a modified YOLO model, CSPD-YOLO, outperformed YOLO-v3 and YOLO-v4 in accuracy. By enhancing feature reuse and propagation, the CSPD-YOLO model demonstrated improved performance in detecting insulator faults in aerial images with complex backgrounds.
Insulator fault detection is one of the essential tasks for high-voltage transmission lines' intelligent inspection. In this study, a modified model based on You Only Look Once (YOLO) is proposed for detecting insulator faults in aerial images with a complex background. Firstly, aerial images with one fault or multiple faults are collected in diverse scenes, and then a novel dataset is established. Secondly, to increase feature reuse and propagation in the low-resolution feature layers, a Cross Stage Partial Dense YOLO (CSPD-YOLO) model is proposed based on YOLO-v3 and the Cross Stage Partial Network. The feature pyramid network and improved loss function are adopted to the CSPD-YOLO model, improving the accuracy of insulator fault detection. Finally, the proposed CSPD-YOLO model and compared models are trained and tested on the established dataset. The average precision of CSPD-YOLO model is 4.9% and 1.8% higher than that of YOLO-v3 and YOLO-v4, and the running time of CSPD-YOLO (0.011 s) model is slightly longer than that of YOLO-v3 (0.01 s) and YOLO-v4 (0.01 s). Compared with the excellent object detection models YOLO-v3 and YOLO-v4, the experimental results and analysis demonstrate that the proposed CSPD-YOLO model performs better in insulator fault detection from high-voltage transmission lines with a complex background.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据