基于自适应动态范围CLAHE的雾天图像增强  

Foggy Image Enhancement Based on Adaptive Dynamic Range CLAHE

作　　者：方丹阳 付青青[1] 吴爱平[1] Fang Danyang;Fu Qingqing;Wu Aiping(School of Electronic Information,The Yangtze University,Jingzhou 434020,Hubei,China)

机构地区：[1]长江大学电子信息学院,湖北荆州434020

出　　处：《激光与光电子学进展》2023年第4期140-147,共8页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(51604038)。

摘　　要：针对雾天图像对比度低、细节模糊的问题,提出了一种自适应动态范围CLAHE的雾天图像增强算法。引入自适应参数T1和T2自动调整图像重分配的范围,对传统的CLAHE进行改进,结合同态滤波改善图像过亮、过暗区域;原始图像通过多尺度细节增强算法进行细节增强处理;将处理后的细节图像与同态滤波处理后的结果相结合,达到图像对比度和细节增强的目的。通过信息熵、局部对比度、平均梯度和运行时间4种客观评价指标对图像结果进行对比分析,主观与客观测试结果表明,所提算法可有效增强图像对比度、凸显细节信息,便于雾天图像信息的提取。To address the problems of low contrasts and fuzzy details in foggy images,an adaptive dynamic range contrast limited adaptive histogram equalization(CLAHE)algorithm for foggy image enhancement is proposed in this paper.Two adaptive parameters T1 and T2 are introduced to automatically adjust the range of image redistribution to improve the traditional CLAHE,and homomorphic filtering is further combined to improve the overlight and overdark regions in the image.The original image is enhanced using a multiscale detail enhancement algorithm.The processed detail image is combined with the result of homomorphic filtering to enhance the image contrast and details.The image results are compared and analyzed based on four objective evaluation indexes including information entropy,local contrast,average gradient,and running time.The subjective and objective test results reveal that the proposed algorithm can effectively enhance the image contrast and highlight the relevant details,which is convenient for image information extraction on foggy days.

关 键 词：图像处理 自适应动态范围 多尺度细节提升 同态滤波 图像增强 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]