欢迎访问《图学学报》 分享到：
图学学报

图学学报

• 视觉与图像 • 上一篇    下一篇

基于高阶马尔科夫随机场的单幅图像去雾算法

  

  1. 1. 天津市复杂系统控制理论及应用重点实验室，天津 300384；
    2. 天津理工大学自动化学院，天津 300384
  • 出版日期:2017-10-31 发布日期:2017-11-03

Single Image Defogging Algorithm Based on High-Order Markov Random Fields

  1. 1. Tianjin Key Laboratory for Control Theory & Applications in Complicated Industry Systems, Tianjin 300384, China;
    2. School of Electrical Engineering, Tianjin University of Technology, Tianjin 300384, China
  • Online:2017-10-31 Published:2017-11-03

PDF (PC)

416

摘要： 针对基于暗通道先验的图像去雾算法先验信息不足和在天空等大面积白色物体区
域失效的问题，提出了一种基于高阶马尔科夫随机场(MRF)的单幅图像去雾算法。首先根据雾
天景物成像特点将雾霾图像分割为亮区域和暗区域；然后根据区域不同改进和衰减暗通道，并
通过暗通道先验获取传输图；最后利用高阶 MRF 对传输图进行优化，解决其先验信息不足的
问题。实验结果表明，本文算法可有效改善暗通道先验失效导致的去雾图像部分失真现象，同
时恢复的图像清晰度更高、细节更丰富。

关键词: 图像去雾, 暗通道先验, IMSRM 算法, 高阶马尔科夫随机场

Abstract: Aim to based on the dark channel prior image defogging algorithm lack of prior
information and such as the large white object region failure problems, put forward a single image
defogging algorithm based on high-order Markov random fields (MRF). According to the imaging
characteristics of the fog haze image into the bright region and dark region. Then according to the
different areas of improvement and the attenuation of the dark channel, and through the dark channel
prior to obtain the transmission map. Finally use high-order MRF to optimize transmission diagram,
solve the problem of insufficient information of their experience. The experimental results show that
the proposed algorithm can effectively improve the partial distortion caused by the prior failure of the
dark channel, and the restored image has higher resolution and more detail.

Key words: image defogging, dark channel prior, IMSRM algorithm, high-order Markov random
fields