[1]陈基顺,肖立军,万新宇,等.复杂环境下电力设备红外热图增强与分割研究[J].红外技术,2018,40(11):1112-1118.[doi:10.11846/j.issn.1001_8891.201811016]
 CHEN Jishun,XIAO Lijun,WAN Xinyu,et al.Research on Enhancement and Segmentation of Power Equipment Infrared Heat Map in Complex Environment[J].Infrared Technology,2018,40(11):1112-1118.[doi:10.11846/j.issn.1001_8891.201811016]
点击复制

复杂环境下电力设备红外热图增强与分割研究
分享到:

《红外技术》[ISSN:1001-8891/CN:CN 53-1053/TN]

卷:
40
期数:
2018年第11期
页码:
1112-1118
栏目:
出版日期:
2018-11-21

文章信息/Info

Title:
Research on Enhancement and Segmentation of Power Equipment Infrared Heat Map in Complex Environment

文章编号:
1001-8891(2018)11-1112-07
作者:
陈基顺1肖立军1万新宇1麦锐杰2秦慧平2李磊2
1. 广东电网有限责任公司珠海供电局;
2.华南理工大学电子与信息学院
Author(s):
CHEN Jishun1XIAO Lijun1WAN Xinyu1MAI Ruijie2QIN Huiping2LI Lei2
1.Zhuhai Power Supply Bureau of Guangdong Power Grid Co. Ltd.;
2.School of Electronics and Information Engineering, South China University of Technology

关键词:
电力设备红外热图分割图像增强Retinex模型联合先验信息多尺度结构保留型平滑滤波
Keywords:
power equipmentinfrared heat map segmentationimage enhancementRetinex modeljoint prior informationmulti-scale structure preserving smoothing filter
分类号:
TP391.9;TM743
DOI:
10.11846/j.issn.1001_8891.201811016
文献标志码:
A
摘要:
在户外电力设备维护中,红外热图增强与分割是今后诊断排障智能化发展的关键一环。本文提出复杂环境下电力设备红外热图增强与分割的新模型:采用区域联合先验信息约束和伽马变换对Retinex图像增强模型进行改进;提出多尺度结构保留型平滑滤波,用高斯正则项约束滤波尺寸。新模型不仅可以对隐藏噪声进行估计补偿,增大红外热图的对比度,而且消除了滤波边缘弥散现象,适用于多种尺寸的电力设备分割。实验证实,在复杂环境下相比其他算法,新模型可以得到更为完整、高对比度的红外热图,同时具备去除绝大多数背景干扰的性能。
Abstract:
In the maintenance of outdoor power equipment, infrared heat map segmentation is the key to the intelligent development of equipment diagnosis and obstacle removal in the future. This paper presents a new model of infrared heat map segmentation for power equipment in a complex environment. First, the improved Retinex model is improved using the joint prior information and the gamma transform. Further, the Gaussian regularization is used to constrain the filter size to achieve the multiscale structure-preserving smoothing filter. The new model can not only estimate the hidden noise, compensate the contrast, increase the contrast of the infrared heat map, render an easy observation, but can also apply to different sizes of power equipment and eliminate the filtering edge dispersion. Our experiments have demonstrated that the new model can obtain a more complete infrared heat map and remove most of the background interference compared with other algorithms in complex environments.

参考文献/References:

[1] 汤成艳. 基于红外热像的金属氧化锌避雷器故障检测技术研究[D]. 长沙: 湖南大学, 2016.
TANG Chengyan. Research on the application of Metal Oxide Arrester fault detection based on infrared imaging[D]. Changsha: Hunan University, 2016.
[2] 郝志成, 吴川, 杨航, 等. 基于双边纹理滤波的图像细节增强方法[J]. 中国光学, 2016, 9(4): 423-431.
HAO Zhicheng, WU Chuan, YANG Hang,et al. Image detail enhancement method based on multi-scale bilateral texture filter[J]. Chinese optics, 2016, 9(4): 423-431.
[3] 王浩, 张叶, 沈宏海, 等. 图像增强算法综述[J]. 中国光学, 2017, 10(4): 438-448.
WANG Hao, ZHANG Ye, SHEN Hong-hai, et al. Review of image enhancement algorithms[J]. Chinese Optics, 2017, 10(4): 438-448.
[4] 王门鸿, 杨文陵, 龚建新,等. 基于NSCT和直方图的电力设备红外图像增强[J]. 微处理机, 2016, 37(3):40-43.
WANG Menhong, YANG Wenling, GONG Jianxin, et al. Infrared Image Enhancement of Electric Equipment Based on NSCT and Histogram[J]. Microprocessors, 2016, 37(3): 40-43.
[5] 何玮. 基于Retinex的红外图像预处理系统的研究与实现[D]. 南京: 南京理工大学, 2015.
HE wei. Research and Implementation of Infrared Image Preprocessing System Based on Retinex[D]. Nanjing: Nanjing University, 2015.
[6] 孙劲光, 李扬, 孟祥福, 等. 改进的单尺度Retinex及其在人脸识别中的应用[J]. 计算机应用研究, 2011, 28(12): 4790-4793.
SUN Jinguang, LI Yang, MENG Xiangfu, et al. Improved monoscaleRetinex and application in face recognition[J]. Application Research of Computers, 2011, 28(12): 4790-4793.
[7] 马荣贵, 王卫星, 刘威,等. 结合分数阶微分和暗原色先验及Retinex的去雾算法[J]. 华南理工大学学报: 自然科学版, 2016, 44(9): 16-23.
MA Ronggui, WANG Weixing, LIU Wei, et al. A Haze Removal Algorithm Combining Fractional Differential, Dark Channel Prior and Retinex[J]. Journal of South China University of Technology: Natural Science Edition, 2016, 44(9): 16-23.

相似文献/References:

[1]邹辉,黄福珍.基于FAsT-Match算法的电力设备红外图像分割[J].红外技术,2016,38(1):021.[doi:10.11846/j.issn.1001_8891.201601004]
 ZOU Hui,HUANG Fuzhen.Infrared Image Segmentation for Electrical Equipment Based on FAsT-Match Algorithm[J].Infrared Technology,2016,38(11):021.[doi:10.11846/j.issn.1001_8891.201601004]
[2]李 鑫,崔昊杨,霍思佳,等.基于粒子群优化法的Niblack电力设备红外图像分割[J].红外技术,2018,40(8):780.[doi:10.11846/j.issn.1001_8891.201809010]
 LI Xin,CUI Haoyang,HUO Sijia,et al.Niblack’s Method for Infrared Image Segmentation of Electrical Equipment Improved by Particle Swarm Optimization[J].Infrared Technology,2018,40(11):780.[doi:10.11846/j.issn.1001_8891.201809010]
[3]核猫群红外图像异常检测方法在电力智能巡检中的应用.核猫群红外图像异常检测方法在电力智能巡检中的应用[J].红外技术,2018,40(9):908.[doi:10.11846/j.issn.1001_8891.201809013]
 HU Luona,PENG Yunzhu,SHI Linxin.Anomaly Detection Method of Infrared Images Based on Kernel Cat Swarm Optimization Clustering with Application in Intelligent Electrical Power Inspection[J].Infrared Technology,2018,40(11):908.[doi:10.11846/j.issn.1001_8891.201809013]

备注/Memo

备注/Memo:
收稿日期:2017-11-13;修订日期:2018-04-15.
作者简介:陈基顺(1975-),男,汉族,广东潮阳人,工程师,研究方向为变电运行管理。E-mail:zhcjs2006@163.com。

更新日期/Last Update: 2018-11-20