一种改进的基于地平线检测的去雾方法

doi:10.3969/j.issn.10062475.2014.09.015

计算机与现代化

一种改进的基于地平线检测的去雾方法

1.四川大学计算机学院，四川成都610065；
2.四川大学视觉合成图形图像技术国防重点学科实验室，四川成都610065

收稿日期:2014-06-05 出版日期:2014-10-10 发布日期:2014-11-04
作者简介:李璐（1991），女，河南南阳人，四川大学计算机学院硕士研究生，CCF会员，研究方向：图形图像处理；通讯作者：兰时勇（1974），男，四川成都人，助理研究员，博士，研究方向：智能交通系统，图形图像处理；张建伟（1971），男，四川成都人，研究员，博导，研究方向：智能交通系统，图形图像处理；李坤（1988），男，河南信阳人，硕士研究生，研究方向：图形图像处理。
基金资助:
国家863计划项目（2013AA013802）

An Improved Haze Removal Method Based on Horizon Detection

1. College of Computer, Sichuan University, Chengdu 610065, China；

2. National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, China

Received:2014-06-05 Online:2014-10-10 Published:2014-11-04

摘要/Abstract

摘要：

雾、霾天气是影响图像和视频质量下降的重要因素，给室外视频任务带来很大不便。考虑到远景视频中地平线的存在，提出一种改进的基于地平线检测的去雾方法。该方法基于暗原色先验理论，

用改进的地平线检测算法，从整幅图像分割出天空区域，得到雾天图像退化物理模型中的大气光部分，再引入容差机制，提高图像去雾质量。而在对传输图的修正过程中采用图像引导滤波代替既占内存

又耗时的软抠图方法。对远景雾天图像的去雾实验表明，该方法改进了原有基于暗原色先验单幅图像去雾方法中白色场景和物体的存在易导致算法无效的限制，有效减小了日周光光晕现象对图像可视化

质量的影响，同时提高了算法速度。

关键词: 远景视频, 地平线检测, 容差, 引导滤波, 去雾

Abstract:

Fog and haze are the important factors that degrade the quality of image and video, which bring great inconvenience to outdoor video tasks. Considering the existence

of horizon in vision video, an improved defogging method based on horizon detection is proposed. It detects the horizon with the theory of dark channel and then segments the sky

region from the whole image to get the light part of the haze imaging model. Parameters are adjusted by introducing faulttolerance to improve image quality. At the same time,

we use imageguided filtering instead of soft matting which consumes both memory and time in transmission correction. As shown in the experiment, this method improves the

vulnerable behavior of origin algorithm in the presence of white scene or objects, the image quality debased by neglecting the obvious halo of diurnal light in distant view

image, and the processing time.

Key words: vision video, horizon detection, faulttolerance, guided filtering, haze removal

中图分类号:

中图分类号： TP391

李璐1，2，兰时勇1，2，张建伟1，2，李坤1，2. 一种改进的基于地平线检测的去雾方法[J]. 计算机与现代化, doi: 10.3969/j.issn.10062475.2014.09.015.

LI Lu1,2, LAN Shiyong1,2， ZHANG Jianwei1,2, LI Kun1,2. An Improved Haze Removal Method Based on Horizon Detection[J]. Computer and Modernization, doi: 10.3969/j.issn.10062475.2014.09.015.

参考文献

［1］
Pizer S M, Ambum E P, Austin J D, et al. Adaptive histogram equalization and its variations［J］. Computer Vision, Graphics, and Image Processing, 1987,39(3):355368. 
［2］ Stark J A. Adaptive image constrast enhancement using generalization of histogram equalization［J］. IEEE Transactions on Image Processing, 2000,9(5):889896.
［3］ Yu Z, Bajaj C. A fast and adaptive method for image contrast enhancement［C］// ICIP’04. 2004,2:10011004.
［4］ Rahman Z, Joban D, Woodell G. Retinex processing for automatic image enhancement［J］. Journal of Electronic Imaging, 2004,13(1):100110.
［5］ Land E H. Recent advances in the Retinex theory and some implication for cortical computations. Color vision and the natural image［J］. Proc. Nat. Acad. Sci,

1983,80(16):51635169. 
［6］ Kocak D M, Dalgleish F R, Caimi F M, et al. A focus on recent developments and trends in underwater imaging［J］. Marine Technology Society Journal, 2008,42(1):5267.
［7］ Oakley J P, Satherley B L. Improving image quality in poor visibility conditions using a physical model for contrast degradation［J］. IEEE Transactions on Image

Processing, 1998,7(2):167179.
［8］ Tan K, Oakley J P. Enchancement of color images in poor visibility conditions［C］//ICIP. 2000,2:788791.
［9］ Narasimhan S G, Nayar S K. Vision and the atmosphere［J］. International Journal of Computer Vision, 2002,48(3):233254.
［10］Narasimhan S G, Nayar S K. Contrast restoration of weather degraded images［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003,25(6):713724.
［11］Schechner Y Y, Narasimhan S G, Nayar S K. Polarizationbased vision through haze［J］. App. Opt., 2003,42(3):511525.
［12］Schechner Y Y, Karpel N. Recovery of underwater visibility and structure by polarization analysis［J］. IEEE Journal of Oceanic Engineering, 2005,30(3):570587.
［13］Tan R T. Visibility in bad weather from a single image［C］//IEEE Conference on Computer Vision and Pattern Recognition. 2008:18.
［14］Fattal R. Single image dehazing［C］//International Conference on Computer Graphics and Interactive Techniques. 2008:19.
［15］〖JP2〗He Kaiming, Sun Jian, Tang Xiaoou. Single image haze removal using dark channel prior［C］//IEEE Conference on Computer Vision and Pattern Recognition. 2009:1956

1963. 
［16］Yuan Hongzhao, Zhang Xiuqiong, Feng Ziliang. Horizon detection in foggy aerial image［C］// Proceeding of 2010 International Conference on Image Analysis and

Signal Processing (IASP). 2010:191194.
［17］He Kaiming, Sun Jian, Tang Xiaoou. Guided image filtering［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(6):13971409.
［18］蒋建国,侯天峰,齐美彬. 改进的基于暗原色先验的图像去雾算法［J］. 电路与系统学报, 2011,4(2):712.
［19］李大鹏,禹晶,肖创柏. 图像去雾的无参考客观质量评测方法［J］. 中国图象图形学报, 2011,16(9):17531757.

[1]	尹相臣, 陈思龙, 李振凯, 张文进, 李桂青. 多尺度密集感受域的GAN图像去雾算法[J]. 计算机与现代化, 2023, 0(03): 11-15.
[2]	李熙莹1,2,3，朱肯钢1,2,3. 结合天空分割和局部透射率优化交通图像去雾算法[J]. 计算机与现代化, 2019, 0(05): 51-.
[3]	包斌1,李亚岗2. 一种改进的基于暗通道先验的图像去雾算法[J]. 计算机与现代化, 2019, 0(02): 27-.
[4]	彭海强，廖华丽. 基于水下视频图像去雾帘的关键帧提取系统[J]. 计算机与现代化, 2015, 0(11): 84-88.

一种改进的基于地平线检测的去雾方法

An Improved Haze Removal Method Based on Horizon Detection

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价