| 引用本文: | 秦 钟,杨建国,王海默,杨佳睿,崔春晖.基于Retinex理论的低照度下输电线路图像增强方法及应用[J].电力系统保护与控制,2021,49(3):150-157.[点击复制] |
| QIN Zhong1,YANG Jianguo,WANG Haimo,YANG Jiarui,CUI Chunhui.Low illumination transmission line image enhancement method and application based on the Retinex theory[J].Power System Protection and Control,2021,49(3):150-157[点击复制] |
|
| 摘要: |
| 为提高低照度环境下输电线路图像视频在线监测设备分析的准确性，提出一种基于Retinex理论的低照度图像增强方法。首先采用改进型同态滤波算法增强低照度图像的RGB分量，然后将图像转换至HSV色彩空间中。对多尺度Retinex算法增强图像进行改进，采用双边滤波函数替代Gaussian函数作为Retinex算法的环绕函数，引入色彩恢复函数进行图像色彩恢复，入射分量采用幂律变换校正，反射分量采用Sigmoid函数处理。最后将图像再转换至RGB空间得到增强后的输电线路图像。对实拍低照度输电线路图片进行仿真处理，结果表明该方法可以有效提高低照度图像的对比度、清晰度和信息熵，并在覆冰预警和异物识别中实现较好的应用。 |
| 关键词: 输电线路 低照度图像 图像增强 多尺度Retinex算法 色彩恢复 HSV色彩空间 |
| DOI：DOI: 10.19783/j.cnki.pspc.200383 |
| 投稿时间：2020-04-11修订日期：2020-05-20 |
| 基金项目:国家电网公司科技项目资助(SGITG-2018ZXCG-FF) |
|
| Low illumination transmission line image enhancement method and application based on the Retinex theory |
| QIN Zhong1,YANG Jianguo,WANG Haimo,YANG Jiarui,CUI Chunhui |
| (1. State Grid Yinchuan Power Supply Company, Yinchuan 750001, China; 2. Yuanyanghu Power Plant of Shenhua
Guoneng Ningxia Coal Power Co., Ltd., Yinchuan 750410, China; 3. State Grid Ningxia Maintenance Company,
Yinchuan 750001, China; 4. Nanjing Youkuo Electric Technology Co., Ltd., Nanjing 211100, China) |
| Abstract: |
| In order to improve the accuracy of transmission line image and video online monitoring equipment analysis resulting in low illumination environment, a low illumination image enhancement method based on the Retinex theory is proposed. First, an improved homomorphic filtering algorithm is used to enhance the RGB component of a low illumination image. Then, the image is converted into the HSV color space. The multi-scale Retinex algorithm is improved to enhance the image. The Gaussian function is replaced by a bilateral filter function as the surrounding function of the Retinex algorithm. The color recovery function is introduced to restore the image color. Finally, the image is converted to the RGB space to obtain the enhanced transmission line image. The simulation results show that this method can effectively improve the contrast, clarity and information entropy of actual low illumination transmission line images. It can also be applied in ice cover warning and foreign body recognition.
This work is supported by the Science and Technology Project of State Grid Corporation of China (No. SGITG- 2018ZXCG-FF). |
| Key words: transmission line low illumination image image enhancement multi-scale Retinex algorithm color restoration HSV color space |
