[1]王燕妮,杨小宝.基于天空区域识别的图像去雾改进算法[J].探测与控制学报,2020,42(02):71.[doi:.]
 WANG Yanni,YANG Xiaobao.An Improved Algorithm of Image Dehazing Based on Sky Region Recognition[J].,2020,42(02):71.[doi:.]
点击复制

基于天空区域识别的图像去雾改进算法()
分享到:

《探测与控制学报》[ISSN:1008-1194/CN:61-1316/TJ]

卷:
42
期数:
2020年02
页码:
71
栏目:
出版日期:
2020-04-15

文章信息/Info

Title:
An Improved Algorithm of Image Dehazing Based on Sky Region Recognition
文章编号:
1008-1194(2020)02-0071-08
作者:
王燕妮杨小宝
西安建筑科技大学信息与控制工程学院,陕西 西安 710055
Author(s):
WANG YanniYANG Xiaobao
School of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an 710055,China
关键词:
图像去雾暗通道先验天空识别阈值分割引导滤波
Keywords:
image defogging DCP sky recognition threshold segmentation guided filter
分类号:
TP391
DOI:
.
文献标志码:
A
摘要:
针对暗通道先验(DCP)去雾算法去雾后物体边缘存在的“块效应”、光晕以及部分区域出现的颜色失真等问题,提出一种基于天空区域识别的DCP去雾改进算法。该方法通过设定的亮度阈值和灰度阈值识别分割出天空区域,根据天空区域在整幅图像中的占比情况合理计算大气光值,修正透射率计算公式并引入引导滤波进行优化以达到去雾目的。通过Matlab软件对算法性能进行仿真,实验表明,改进方法相比其他去雾算法不仅可以显著改善天空颜色失真和块效应等现象,并且除雾后图像具有完整的细节和较高的清晰度以及较低的运行时间。
Abstract:
Aiming at “block effect” question of at object edge, halo and color distortion in partial sky regions after dehazing algorithm of Dark Channel Prior (DCP), an improved algorithm based on sky region recognition was proposed. The method identified sky region by the given brightness threshold and gray threshold, and atmospheric light value was calculated according to sky proportion in the whole image, and then the transmittance calculation formula was corrected and guiding filter was introduced to optimize it. Simulation results of algorithm performance by MATLAB software showed that the improved algorithm could obviously improve the phenomenon of sky region distortion and block effect, which made the defogged images of complete details, higher definition and algorithm efficiency.

参考文献/References:

[1]吴迪,朱青松.图像去雾的最新研究进展[J].自动化学报,2015,41:221-239.
[2]高原原,马超,潘博文.视觉物联网中图像去雾方法研究综述与展望[J].信息通信技术与政策,2019(4):6-11.
[3]Xu Zhiyuan,Liu Xiaoming,Chen Xiaonan.Fog removal from video sequences using contrast limited adaptive histogram equalization[C]//IEEE International Conference on Computational Intellig-ence and Software Engineering.USA:IEEE,2009:1-4.
[4]姜柏军,钟明霞.改进的直方图均衡化算法在图像增强中的应用[J].激光与红外,2014,29(6):701-706.
[5]董静薇,赵春丽,海博.融合同态滤波和小波变换的图像去雾算法研究[J].哈尔滨理工大学报,2019,1(1):66-70.
[6]Choi D H,Jang I H.Color image enhancement using single-scale retinex based on an improved image formation model[C]//16th European Signal Processing Conference,2008:1-5.
[7]郭瑞,党建武,沈瑜,等.改进的单尺度Retinex图像去雾算法[J].兰州交通大学学报,2018,191(6):69-75.
[8]Tan R T.Visibility in bad weather from a single image[C]//IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2008:1-8.
[9]Tarel J,Hautiere N,Caraffa L,et al.Vision enhancement in homogeneous and heterogeneous fog[J].IEEE Intelligent Transportation Systems Magazine,2012,4(2):6-20.
[10]He K,Sun J,Tang X.Single image haze removal using dark channel prior[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2011,33(12):2341-2353.
[11]He KM, Sun J, Tang XO.Fast matting using large kernel matting Laplacian matrices.[C]//Proceed-ings of IEEE Conference on Computer Vision and Pattern Recognition.USA:IEEE,2010:2165-2172.
[12]NARASIMHAN S G,NAYAR S K.Contrast restoration of weather degraded images[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,2003,25(6):713-724.
[13]孙伟,李大健,刘宏娟,等.基于大气散射模型的单幅图像快速去雾[J].光学精密工程,2013,21(4):1040-1046.
[14]李加元,胡庆武,艾明耀,等.结合天空识别和暗通道原理的图像去雾[J].中国图象图形学报,2015,20(4):514-519.
[15]申铉京,刘翔,陈海鹏.基于多阈值Otsu准则的阈值分割快速计算[J].电子与信息学报,2016,10(3):108-113.
[16]WANG Guangyi,REN Guanghui,JIANG Lihui, et al.Single image dehazing algorithms based on sky region segmentation[J].Information Technology Journal,2013,12(6):1168-1175.
[17]曾致远,周亚同,池越,等.天空优化的数字图像暗通道先验去雾算法[J].激光与光电子学进展,2018(8):261-267.
[18]王一帆,尹传历,黄义明,等.基于双边滤波的图像去雾[J].中国图象图形学报,2014,19(3):386-392.
[19]李大鹏,禹晶,肖创柏.图像去雾的无参考客观质量测评方法[J].中国图像图形学报,2011,16(9):1753-1757.

备注/Memo

备注/Memo:
收稿日期:2019-10-28
基金项目:陕西省自然科学基础研究项目资助(2018JM5127;2020JM499)
作者简介:王燕妮(1975—),女,陕西渭南人,博士,副教授,研究方向:信号与信息处理。E-mail:wangyn02@126.com
更新日期/Last Update: 2020-05-15