基于Levy-SOA自适应阈值分割和改进引导滤波的NSST图像增强  

NSST Image Enhancement Based on Levy-SOA Adaptive Threshold Segmentation and Improved Guided Filtering

作　　者：孙晨 王昕[2] 蒋国臻 SUN Chen;WANG Xin;JIANG Guozhen(School of Electrical Engineering,Shanghai University of Electric Power,Shanghai 200090,China;Center of Electrical and Electronic Technology,Shanghai Jiao Tong University,Shanghai 200240,China;Jiande Power Supply Company,State Grid Zhejiang Electric Power Co.,Ltd.,Jiande 310000,China)

机构地区：[1]上海电力大学电气工程学院,上海200090 [2]上海交通大学电工与电子技术中心,上海200240 [3]国网浙江省电力有限公司建德供电公司,浙江建德310000

出　　处：《控制工程》2024年第7期1297-1304,共8页Control Engineering of China

基　　金：国家自然科学基金资助项目(61673268)。

摘　　要：针对电气设备红外图像对比度不高、含噪声等问题,提出了一种非下采样剪切波变换(non-subsampled shearlet transform,NSST)域下的红外图像增强算法。首先,通过NSST将图像分解为低频分量和高频分量。然后,利用基于Levy-海鸥优化算法(Levy-seagull optimization algorithm,Levy-SOA)的自适应阈值分割算法将低频分量分割成背景区域和目标设备区域,并分别对其进行直方图均衡化处理和线性增强;利用改进引导滤波算法对高频分量进行去噪处理。最后,对处理后的低频分量和高频分量进行NSST重构,得到最终的增强图像。实验结果表明,所提算法在一定程度上改善了图像视觉效果,保证了图像本身的质量,有助于后续电气设备的温度状态评估、异常分析、故障定位和诊断。To solve the problems of low contrast and noise in infrared images of electrical equipment,an infrared image enhancement algorithm in non-subsampled shearlet transform(NSST)domain is proposed.Firstly,the image is decomposed into the low-frequency component and high-frequency component by NSST.Then,an adaptive threshold segmentation algorithm based on Levy-seagull optimization algorithm(Levy-SOA)is used to divide the low-frequency component into background region and target device region,and the histogram equalization and linear enhancement are carried out for the two parts respectively.The improved guided filtering algorithm is used to denoise the high-frequency component.Finally,the processed low-frequency and high-frequency components are reconstructed by NSST to obtain the final enhanced image.The experimental results show that the proposed algorithm can improve the visual effect of the image to a certain extent,ensure the image quality,and contribute to the subsequent temperature state evaluation,anomaly analysis,fault location and diagnosis of electrical equipment.

关 键 词：电气设备 NSST Levy-SOA 改进引导滤波 

分 类 号：TK38[动力工程及工程热物理—热能工程] TP44[自动化与计算机技术]