变电站低照度场景红外可见光图像融合  

Infrared visible light image fusion in low light scenarios of substations

作　　者：赵杰 陈嘉晋 ZHAO Jie;CHEN Jiajin(School of Electrical and Control Engineering,Heilongjiang University of Science and Technology,Harbin 150022)

机构地区：[1]黑龙江科技大学电气与控制工程学院,哈尔滨150022

出　　处：《电气技术》2025年第3期22-29,共8页Electrical Engineering

基　　金：省属高校科研业务费项目(2022-KYYWF-0551)。

摘　　要：低照度环境会导致变电站采集图像出现视觉质量低、细节损失、对比度低等问题,影响后续设备检测与监控等工作,因此本文提出一种基于低照度图像增强和非下采样轮廓波变换(NSCT)与离散余弦变换(DCT)技术的图像融合方法。首先,基于伽马参数对可见光图像进行自适应图像调节,增强可视度;然后,由NSCT将图像分解为高低频系数,对高频系数采用Sobel算子进行边缘信息提取,对低频系数采用改进DCT-离散傅里叶变换(DFT)进行分解整合,再对分解的振幅频谱与相位频谱分别采用对比度增强加权与基于奇异值分解(SVD)的局部能量最优规则进行融合;最后,由NSCT反变换得到融合图像。利用三组变电站常见设备图像,将所提方法与其他算法进行对比,结果表明本文所提方法的平均梯度、信息熵、互信息等指标更优。The image acquisition of substations in low light environments can lead to problems such as low visual quality,loss of details,and low contrast,which in turn affect the subsequent detection and monitoring of equipment.A fusion method based on low light image enhancement and nonsubsampling contourlet transform(NSCT)and discrete cosine transform(DCT)technology is proposed in this paper.Firstly,adaptive image adjustment is performed on visible light images based on gamma parameters to enhance visibility.Then NSCT decomposes the image into high and low frequency coefficients.For high-frequency coefficients,edge information extraction based on Sobel operator is used,and for low-frequency coefficients,improved DCT-DFT is used for decomposition and integration.The decomposed amplitude spectrum and the phase spectrum are fused using contrast enhancement weighting and local energy optimization rule based on singular value decomposition(SVD),respectively.Finally,the fused image is obtained by NSCT inverse transformation.Three sets of images of common equipment in substations are used to compare the proposed method with other algorithms.The results show that this proposed method performs better in indicators such as average gradient,information entropy and mutual information.

关 键 词：图像融合 低照度图像 非下采样轮廓波变换(NSCT) 离散余弦变换(DCT) 奇异值分解(SVD) 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TN219[自动化与计算机技术—计算机科学与技术] TM63[电子电信—物理电子学]