Related Experiment Video
Updated: Jun 13, 2026

Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
Fog-Adaptive-YOLO: A lightweight model for insulator defect detection
Xiaoyuan Jin1,2, Yuzhen Zhao1,2, Wangyu Shen1,2
1Shaanxi Key Laboratory of Liquid Crystal Polymer Intelligent Display, Technological Institute of Materials & Energy Science (TIMES), Xijing University, Xi'an, China.
This study introduces Fog-Adaptive-YOLO, a lightweight network for detecting insulator defects in fog. The model enhances visibility and improves detection accuracy, offering a practical solution for unmanned aerial vehicle inspections.
Area of Science:
- Computer Vision
- Artificial Intelligence
- Electrical Engineering
Background:
- Insulator defect detection using UAVs is challenging in foggy conditions due to complex backgrounds, small targets, and weather interference.
- Existing methods struggle with severe weather, impacting inspection reliability and safety.
Purpose of the Study:
- To develop a lightweight and effective deep learning model for insulator defect detection under foggy weather conditions.
- To improve the accuracy and efficiency of UAV-based infrastructure inspection in adverse environments.
Main Methods:
- Proposed Fog-Adaptive-YOLO, a lightweight detection network incorporating a FogEnhance module for noise suppression and feature enhancement.
- Optimized multi-scale feature extraction and aggregation using C3MSGR and C2fMSGR modules.
- Evaluated performance on self-constructed (InsDef-Fog) and public (IDID_FOG, WM-FOG, RTTS) datasets.
Main Results:
- Achieved 65.4% mAP50 on InsDef-Fog with only 2.74M parameters.
- Obtained 60.3% mAP50 on IDID_FOG and 80.2% mAP50 on WM-FOG.
- Demonstrated stable precision on the RTTS foggy dataset, showing robustness across different scenarios.
Conclusions:
- Fog-Adaptive-YOLO offers a favorable balance between detection accuracy and lightweight efficiency for foggy insulator defect detection.
- The proposed model is well-suited for practical UAV-based inspection tasks in adverse weather conditions.
- The network effectively suppresses fog noise and enhances weak defect features, outperforming existing methods.
Related Concept Videos
Lumber Defects
Shakes are minor fractures that run along or across the wood's annual rings, while wane is...
Capacitor With A Dielectric
Dielectrics are non-conducting materials with no free or loosely bound electrons. When a dielectric is...
Detection of Gross Error: The Q Test
Types of Errors: Detection and Minimization
Absolute error in a measurement is the numerical difference from the true or central value. Relative error is the ratio between absolute error and the true or central value, expressed as a percentage.
Errors can be classified by source, magnitude, and sign. There are three types of errors: systematic, random, and gross.
Systematic or...
Insulation Coordination
Electrostatic Boundary Conditions in Dielectrics
Consider a case where both the mediums across a boundary are two different dielectric materials. Recall that the electric field and electric displacement are proportional and related through the material's permittivity.