Electrical Equipment Infrared Image Enhancement of NSST Domain Based on MVOtsu and Log-type Fuzzy Membership Function

ZHU Ying; WANG Xin; WANG Aiping; SU Lian

doi:10.13296/j.1001-1609.hva.2020.09.026

您当前的位置：

首页 >

文章列表页 >

Electrical Equipment Infrared Image Enhancement of NSST Domain Based on MVOtsu and Log-type Fuzzy Membership Function

更新时间：2025-04-26

- Electrical Equipment Infrared Image Enhancement of NSST Domain Based on MVOtsu and Log-type Fuzzy Membership Function
- High VoltageApparatus Vol. 56, Issue 9, Pages: 179-185(2020)
- 作者机构：
  
  1. 上海交通大学电工与电子技术中心
  2. 国网四川省电力有限公司巴中供电公司
- 作者简介：
- 基金信息：
- DOI：10.13296/j.1001-1609.hva.2020.09.026
  CLC： TM50;TP391.41
- Published：2020
- 稿件说明：
移动端阅览
[1]朱颖,王昕,王爱平,粟莲.基于MVOtsu和对数型模糊隶属度函数的电力设备NSST域红外图像增强[J].高压电器,2020,56(09):179-185.

ZHU Ying, WANG Xin, WANG Aiping, et al. Electrical Equipment Infrared Image Enhancement of NSST Domain Based on MVOtsu and Log-type Fuzzy Membership Function[J]. High voltageapparatus, 2020, 56(9): 179-185.
[1]朱颖,王昕,王爱平,粟莲.基于MVOtsu和对数型模糊隶属度函数的电力设备NSST域红外图像增强[J].高压电器,2020,56(09):179-185. DOI： 10.13296/j.1001-1609.hva.2020.09.026.

ZHU Ying, WANG Xin, WANG Aiping, et al. Electrical Equipment Infrared Image Enhancement of NSST Domain Based on MVOtsu and Log-type Fuzzy Membership Function[J]. High voltageapparatus, 2020, 56(9): 179-185. DOI： 10.13296/j.1001-1609.hva.2020.09.026.

摘要

针对电力设备红外图像细节模糊、边缘不清等问题

提出了一种基于非下采样剪切波变换（nonsubsampled shearlet transform

NSST）域的电力设备红外图像处理方法。该方法采用NSST将原始图像分为高频部分和低频部分。为了精确分割低频电力设备与背景环境并提高二者对比度

低频部分设计了一种结合均值与方差的MVOtsu（mean and variation otsu）算法

并分别对设备和背景进行线性增强和直方图均衡增强。为了增强高频边缘细节

抑制非边缘噪声

高频部分提出一种对数型模糊隶属度函数

将隶属度值域下界拓展到0

解决经典Pal-King隶属度增强后逆映射时低灰度值区域扁平化问题。最后按照NSST变换合成增强结果。该算法与相关算法相比

边缘强度、信息熵、对比度、标准差等评价指标至少增长15.06%、2.03%、33.78%、1.28%。实验结果表明:文中算法能有效的提高电力设备红外图像整体对比度

对细节和边缘增强效果明显

便于人眼识别和智能故障定位

适用于变电站、巡线等多种环境红外图像增强处理。

Abstract

In order to solve the problems of fuzzy detail and fuzzy edge of infrared image of electrical equipment

an infrared image processing method based on NSST（non-subsampled shearlet transform

NSST） is proposed.This method divides the original image into high frequency part and low frequency part.For accurately dividing the lowfrequency part into target device and the background and improving the contrast

a MVOtsu（mean and variation otsu）algorithm combining mean and variance is designed

and use the linear enhancement and the histogram enhancement to enhance the equipment and background.For enhancing the high frequency edge details and suppress nonedge noise

a logarithmic fuzzy membership function is proposed

it can expand the lower bound of high frequency membership to 0

and this algorithm can solve the problem of flattening of low gray value area in the inverse mapping of classic Pal-King membership.Finally

in accordance with the NSST inverse transformation reconstruct enhanced results.Comparing the proposed method with related algorithm

the intensity of edge

information entropy

contrast

and standard deviation can be improves at least 15.06%

2.03%

33.78%

1.28% respectively.Experimental results show that the algorithm can effectively improve the overall electrical equipment infrared image contrast

detail and edge enhancement effect is obvious

convenience of human eye identification and fault location

suitable for transformer substation

patrol and other infrared image enhancement processing.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Application and Development of the Vibration Analysis in the Condition Monitoring of Electrical Equipment

Discussion on the Problems in the Standard DL/T 596—1996 with Solutions

Application of Infrared Thermal Imaging Technology to Condition-based Maintenance of Power Equipment

Research Progress of Environmentally Friendly SF₆ Substitute Medium in Electrical Equipments

Zero Insulator Detectionbased on the Infrared Imaging Technology

Related Author

JIA Shen-li

ZHONG Bo

MENG Yong-peng

DONG Jia-bin

YANG Dian-cheng

MA Xiao-wei

HU Yu-rong

JIA Feng-ming

Related Institution

State Key Laboratory of Electrical Insulation for Power Equipment, Xi’an Jiaotong University

Shaanxi Normal University

Yunnan Electric Power Test Research Group Ltd.

Maintenance Company of Anhui Electric Power Company

School of Electrical Engineering, Shenyang University of Technology

⁰