基于像素级和块级的低照度图像增强  

A Low-light Image Enhancement Algorithm Based on Pixel Level and Block Level

作　　者：王时巨 王欣 鞠铭烨[1] WANG Shi-ju;WANG Xin;JU Ming-ye(School of Internet of Things,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)

机构地区：[1]南京邮电大学物联网学院,江苏南京210003

出　　处：《计算机技术与发展》2023年第3期34-40,48,共8页Computer Technology and Development

基　　金：国家自然科学基金资助项目(61902198);江苏省自然科学基金(BK20190730);南京邮电大学科研启动基金(NY219135)。

摘　　要：针对低照度图像对比度低、亮度弱、色彩暗淡等问题,提出一种基于像素级和块级的低照度图像增强算法。该算法在HSV空间对亮度通道和饱和度通道分别进行像素级、块级增强。前者通过伽马校正构造一种新的像素级增强模型,其采用增强矩阵代替单一伽马值,并结合大气散射模型与全局搜索策略求得模型中的未知参数,进而对亮度通道进行像素级增强;后者着重关注色彩饱和度的提升,将饱和度通道分为若干块,假设每一块具有相同的增强因子,利用约束信息对每个块采用局部一维搜索策略确定其值。将处理后的各通道分量转化至RGB空间,获得最终增强结果。该算法有效结合了像素级处理的低复杂度和块级处理的信息丰富度等优势,且不需要任何的训练过程。实验结果表明,在合成数据集与真实场景下,所提算法对亮度的提升和色彩的恢复均有明显改善,在客观评价指标上同样取得优异性能。Images captured under poor illumination or at night time have weak brightness and dim color.To resolve this,a low-light image enhancement algorithm based on pixel level and block level is proposed,which enhances the brightness channel and saturation channel at pixel level and block level respectively in HSV space.The former constructs a new brightness channel pixel level enhancement model via gamma correction,which uses the enhancement matrix to substitute a single gamma value.Furthermore,a method combining an atmospheric scattering model and global search strategy is proposed to solve the parameters.The latter divides the saturation channel into several blocks to improve the color saturation.Specifically,it assumes that each block has the same enhancement factors,which are obtained by using the one-dimensional local retrieval strategy of constraint information.The processed channels are converted into RGB space to achieve the end result.The proposed algorithm effectively combines the benefits of low complexity of pixel level processing and information richness of block level processing,and does not require any training process.Experiments show that the proposed algorithm can dramatically improve the brightness and color saturation in synthetic datasets and real scenes,and also achieve excellent performance in objective metrics.

关 键 词：图像增强 HSV色彩空间 伽马校正 大气散射模型 导向滤波 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]