Image processing‐based noise‐resilient insulator defect detection using YOLOv8x

Abstract Accurate and efficient insulator defect detection is critical for power grid reliability, but it can be affected by the presence of noises in captured images and can be difficult to employ for real‐time operation due to the slow processing of the detection scheme. This paper proposes a nove...

Full description

Saved in:
Bibliographic Details
Main Authors: Shagor Hasan, Md. Abdur Rahman, Md. Rashidul Islam, Animesh Sarkar Tusher
Format: Article
Language:English
Published: Wiley 2024-12-01
Series:IET Smart Grid
Subjects:
Online Access:https://doi.org/10.1049/stg2.12199
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850119620303781888
author Shagor Hasan
Md. Abdur Rahman
Md. Rashidul Islam
Animesh Sarkar Tusher
author_facet Shagor Hasan
Md. Abdur Rahman
Md. Rashidul Islam
Animesh Sarkar Tusher
author_sort Shagor Hasan
collection DOAJ
description Abstract Accurate and efficient insulator defect detection is critical for power grid reliability, but it can be affected by the presence of noises in captured images and can be difficult to employ for real‐time operation due to the slow processing of the detection scheme. This paper proposes a novel framework based on the YOLOv8x object detection scheme, addressing the challenge of detecting small defects in complex aerial images and providing a noise mitigation scheme. A Gaussian blur and Laplacian sharpening‐based hybrid scheme is proposed to mitigate the impacts of noises in insulator images. Experimental results indicate that the proposed framework can achieve a mean average precision (mAP) of 98.4% on noise‐free images, surpassing benchmark models, such as YOLOv5x and YOLOv7 by 2.1% and 3.9%, respectively. Also, while the performance of a conventional system can decrease to a mAP of 93.3% in the worst case, the implementation of the proposed mitigation scheme ensures a mAP of 96.7% for that case. With an inference speed of 56.9 ms per image, this approach offers a promising solution for real‐time power line inspection, contributing to enhanced power grid maintenance and safety.
format Article
id doaj-art-4cd4dd7230dd44d682a253f008ce18ef
institution OA Journals
issn 2515-2947
language English
publishDate 2024-12-01
publisher Wiley
record_format Article
series IET Smart Grid
spelling doaj-art-4cd4dd7230dd44d682a253f008ce18ef2025-08-20T02:35:35ZengWileyIET Smart Grid2515-29472024-12-01761036105310.1049/stg2.12199Image processing‐based noise‐resilient insulator defect detection using YOLOv8xShagor Hasan0Md. Abdur Rahman1Md. Rashidul Islam2Animesh Sarkar Tusher3Department of Electrical & Electronic Engineering Rajshahi University of Engineering & Technology Rajshahi BangladeshDepartment of Electrical & Electronic Engineering Rajshahi University of Engineering & Technology Rajshahi BangladeshDepartment of Electrical & Electronic Engineering Rajshahi University of Engineering & Technology Rajshahi BangladeshDepartment of Electrical & Electronic Engineering Rajshahi University of Engineering & Technology Rajshahi BangladeshAbstract Accurate and efficient insulator defect detection is critical for power grid reliability, but it can be affected by the presence of noises in captured images and can be difficult to employ for real‐time operation due to the slow processing of the detection scheme. This paper proposes a novel framework based on the YOLOv8x object detection scheme, addressing the challenge of detecting small defects in complex aerial images and providing a noise mitigation scheme. A Gaussian blur and Laplacian sharpening‐based hybrid scheme is proposed to mitigate the impacts of noises in insulator images. Experimental results indicate that the proposed framework can achieve a mean average precision (mAP) of 98.4% on noise‐free images, surpassing benchmark models, such as YOLOv5x and YOLOv7 by 2.1% and 3.9%, respectively. Also, while the performance of a conventional system can decrease to a mAP of 93.3% in the worst case, the implementation of the proposed mitigation scheme ensures a mAP of 96.7% for that case. With an inference speed of 56.9 ms per image, this approach offers a promising solution for real‐time power line inspection, contributing to enhanced power grid maintenance and safety.https://doi.org/10.1049/stg2.12199artificial intelligence and data analyticsfeature extractionpattern classificationpower system reliabilitypower transmission
spellingShingle Shagor Hasan
Md. Abdur Rahman
Md. Rashidul Islam
Animesh Sarkar Tusher
Image processing‐based noise‐resilient insulator defect detection using YOLOv8x
IET Smart Grid
artificial intelligence and data analytics
feature extraction
pattern classification
power system reliability
power transmission
title Image processing‐based noise‐resilient insulator defect detection using YOLOv8x
title_full Image processing‐based noise‐resilient insulator defect detection using YOLOv8x
title_fullStr Image processing‐based noise‐resilient insulator defect detection using YOLOv8x
title_full_unstemmed Image processing‐based noise‐resilient insulator defect detection using YOLOv8x
title_short Image processing‐based noise‐resilient insulator defect detection using YOLOv8x
title_sort image processing based noise resilient insulator defect detection using yolov8x
topic artificial intelligence and data analytics
feature extraction
pattern classification
power system reliability
power transmission
url https://doi.org/10.1049/stg2.12199
work_keys_str_mv AT shagorhasan imageprocessingbasednoiseresilientinsulatordefectdetectionusingyolov8x
AT mdabdurrahman imageprocessingbasednoiseresilientinsulatordefectdetectionusingyolov8x
AT mdrashidulislam imageprocessingbasednoiseresilientinsulatordefectdetectionusingyolov8x
AT animeshsarkartusher imageprocessingbasednoiseresilientinsulatordefectdetectionusingyolov8x