电子学报 ›› 2015, Vol. 43 ›› Issue (10): 1978-1983.DOI: 10.3969/j.issn.0372-2112.2015.10.015

• 学术论文 • 上一篇    下一篇

基于亮度反馈的彩色雾霾图像增强算法

何林远1,2, 毕笃彦2, 熊磊2, 南栋2, 周理2   

  1. 1. 西安交通大学电子与信息工程学院, 陕西西安 710049;
    2. 空军工程大学航空航天工程学院, 陕西西安 710038
  • 收稿日期:2014-01-10 修回日期:2014-04-01 出版日期:2015-10-25 发布日期:2015-10-25
  • 作者简介:何林远 男,1983年生,河南洛阳人,博士生、讲师,研究方向为图像处理与计算机视觉.E-mail:hal1983@163.com;毕笃彦 男,1962年生,陕西扶风人,教授、博士生导师,研究方向为图像处理与模式识别.E-mail:biduyan@163.com
  • 基金资助:

    国家自然科学基金(No.61175029,No.61203268,No.61202339)

Color Image Haze Removal Algorithm Based on Luminance Feedback

HE Lin-yuan1,2, BI Du-yan2, XIONG Lei2, NAN Dong2, ZHOU Li2   

  1. 1. Department of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China;
    2. Institute of Aeronautics and Astronautics, Air Force Engineering University, Xi'an, Shaanxi 710038, China
  • Received:2014-01-10 Revised:2014-04-01 Online:2015-10-25 Published:2015-10-25

摘要:

针对目前主流去除雾霾算法采用亮度和色度分量分而治之的机制,割裂了二者固有的相关性,致使增强后图像质量不能两者兼顾的问题,本文以人眼视觉特性为依据,提出了一种亮度反馈的增强方法.该方法首先对亮度信息进行区域适应性调整,并对其细节和边缘进行提升,然后将该结果纳入色度信息处理的约束条件,较好的保持了两者间的相关性.实验表明本文算法在去除雾霾后视觉效果优异,具有较好的实用性和较少的计算资源消耗.

关键词: 图像增强, 图像去雾, 亮度反馈, 区域曝光

Abstract:

Through the analysis of the current main of dehazing algorithms, we found that they adapted the divide and conquer strategy to process the luminance and chrominance components, therefore they separated their correlation.To resolve the problem, we performed a sort of method for enhancing and combining the image based on luminance feedback through the human visual characteristics.First, it adjusted the brightness information and lifted the edges and details of original image.Moreover, it regarded the results as constraint conditions which would be used in processing chromatic component for maintain their relevance.Experiments have demonstrated that the proposed method could obtain an excellent result and provide a good practicability and take less time.

Key words: photographic enhancement, image dehazing, luminance feedback, zone system

中图分类号: