基于光学厚度代理模型的雾浓度估计及图像去雾

doi:10.3969/j.issn.1000-1093.2019.07.012

兵工学报 ›› 2019, Vol. 40 ›› Issue (7): 1425-1433.doi: 10.3969/j.issn.1000-1093.2019.07.012

基于光学厚度代理模型的雾浓度估计及图像去雾

李春明，姜雨彤，宋海平，纪超，郭猛，朱琳

(中国北方车辆研究所, 北京 100072)

收稿日期:2018-08-20 修回日期:2018-08-20 上线日期:2019-09-03
通讯作者: 姜雨彤(1987—)，女，工程师，博士 E-mail:jiangyutong201@163.com
作者简介:李春明(1964—)，男，研究员，博士，中国兵器工业集团首席专家。E-mail: chmli@noveri.com.cn
基金资助:
国家自然科学基金项目（61801439）

Research on Optical Depth Surrogate Model-based Method for Estimating Fog Density and Removing Fog Effect from Images

LI Chunming， JIANG Yutong， SONG Haiping， JI Chao， GUO Meng， ZHU Lin

(China North Vehicle Research Institute, Beijing 100072, China)

Received:2018-08-20 Revised:2018-08-20 Online:2019-09-03

摘要/Abstract

摘要： 图像是现代化战争的重要信息来源，雾天环境下图像质量下降，严重妨碍战场侦察识别能力。为提高雾气环境下图像有效利用性，开展了基于光学厚度代理模型的雾浓度估计及图像去雾方法研究。针对雾天图像的相关特征，提出一个与雾气浓度紧密相关的饱和度-亮度联合特征，通过敏感度分析，确定暗通道、饱和度-亮度和色度为3个重要的雾相关特征，建立了以雾相关特征为自变量、光学厚度为目标函数的代理模型；基于光学厚度估计代理模型，提出了一种雾浓度估计方法；同时将代理模型预测的光学厚度估计值代入大气散射模型中对去雾图像进行求解。实验结果表明，该方法在雾浓度估计准确度、去雾处理效果方面优于现有方法。

关键词: 图像去雾, 光学厚度, 雾浓度, 代理模型

Abstract: The images are vulnerable to suspended particles in the atmosphere, and the quality of image captured in fog is deteriorated to lead to many difficulties for battlefield reconnaissance and recognition. Various fog-related image features are investigated, and a novel feature based on chroma, saturation, and Brightness value color space which correlates well with the fog density is proposed. The surrogate-based method is used to build a refined polynomial regression model for optical depth with informative fog-related features, including the dark-channel, saturation-value, and chroma. An effective method for fog density estimation and image defogging is proposed based on the surrogate model. Experimental validations prove that the proposed method has better effect than conventional methods in both quantitation and quality, and leads to great improvements in real-time image defogging. Key

Key words: imagedefogging, opticaldepth, fogdensity, surrogatemodel

中图分类号:

TP391.413

李春明，姜雨彤，宋海平，纪超，郭猛，朱琳. 基于光学厚度代理模型的雾浓度估计及图像去雾[J]. 兵工学报, 2019, 40(7): 1425-1433.

LI Chunming， JIANG Yutong， SONG Haiping， JI Chao， GUO Meng， ZHU Lin. Research on Optical Depth Surrogate Model-based Method for Estimating Fog Density and Removing Fog Effect from Images[J]. Acta Armamentarii, 2019, 40(7): 1425-1433.

参考文献

［1］李力, 金伟其, 黄有为, 等. 一种低对比度可见光超视距成像的实时图像增强方法[J]. 兵工学报, 2010, 31(2):242-247.
LI L, JIN W Q, HUANG Y W, et al. Real-time image enhancement processing methods of low contrast visible light over-the-horizon imaging[J]. Acta Armamentarii, 2010, 31(2):242-247. (in Chinese)
[2］ POMERLEAU D. Visibility estimation from a moving vehicle using the RALPH vision system[C]∥Proceedings of IEEE Conference on Intelligent Transportation Systems. Boston, MA, US:IEEE, 1997: 906-911.
[3］ HAUTIERE N, TAREL J P, LAVENANT J, et al. Automatic fog detection and estimation of visibility distance through use of an onboard camera[J]. Machine Vision and Applications, 2006, 17(1): 8-20.
[4］ CARAFFA L, TAREL J. Daytime fog detection and density estimation with entropy minimisation[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences,2014, II-3: 25-31.
[5］ CHOI L K, YOU J, BOVIK A C. Referenceless perceptual fog density prediction model[J]. Proceedings of SPIE, 2014, 9014: 90140H.
[6］ CHOI L K, YOU J, BOVIK A C. Referenceless prediction of perceptual fog density and perceptual image defogging[J]. IEEE Transactions on Image Processing, 2015, 24(11): 3888-3901.
[7］ SONG Y F, LI J, WANG X G, et al. Single image dehazing using ranking convolutional neural network[J]. IEEE Transactions on Multimedia, 2018, 20(6): 1548-1560.
[8］ QIN M J, XIE F Y, LI W, et al. Dehazing for multispectral remote sensing images based on a convolutional neural network with the residual architecture[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2018, 11(5): 1645-1655.
[9］ HE K M, SUN J, TANG X O. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353.

[10］ TANG K T, YANG J C, WANG J. Investigating haze-relevant features in a learning framework for image dehazing[C]∥Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, US: IEEE, 2014: 2995-3002.
[11］ TAN X, SUN C M, PHAM T D. Multipoint filtering with local polynomial approximation and range guidance[C]∥Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, US: IEEE, 2014: 2941-2948.
[12］ AN X Y, SONG B W, MAO Z Y, et al. Layout optimization design of two vortex induced piezoelectric energy converters (VIPECs) using the combined Kriging surrogate model and particle swarm optimization method[J]. Energies, 2018, 11(8): 1-22.
[13］ SHYY W, PAPILA N, VAIDYANATHAN R, et al. Global design optimization for aerodynamics and rocket propulsion components[J]. Progress in Aerospace Sciences, 2001, 37(1): 59-118.
[14］ SOBOL I M. Global sensitivity indices for nonlinear mathematical models and their Monte Carlo estimates[J]. Mathematics and Computers in Simulation, 2001, 55(1/2/3): 271-280.
[15］ ZHU Q S, MAI J M, SHAO L. A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Transactions on Image Processing, 2015, 24(11): 3522-3533.

第40卷
第7期2019 年7月兵工学报ACTA
ARMAMENTARIIVol.40No.7Jul.2019

[1]	吴则良，叶建川，王江，金忍. 基于深度自动编码器神经网络的飞行器翼型参数降维与优化设计[J]. 兵工学报, 2022, 43(6): 1326-1336.
[2]	姜雨彤，宋海平，王光辉. 基于质量评价最优的无人机航拍图像去雾方法[J]. 兵工学报, 2022, 43(1): 148-158.
[3]	梁静，贾慧民，苏瑞巩，唐吉龙，房丹，冯海通，张宝顺，魏志鹏. 垂直腔面发射半导体激光器腔模位置对器件输出波长的影响研究[J]. 兵工学报, 2019, 40(12): 2482-2487.
[4]	周欢，丁智坚，郑伟. 沿临近空间机动弹道的扰动引力重构模型优化[J]. 兵工学报, 2018, 39(12): 2371-2379.
[5]	萧辉，杨国来，孙全兆. 火炮多柔体动力学结构优化研究[J]. 兵工学报, 2017, 38(1): 27-34.
[6]	王悦，白春华，李斌，刘雪岭. 密闭空间瞬态液雾粒径及浓度测量实验研究[J]. 兵工学报, 2015, 36(9): 1665-1670.
[7]	孙泽刚，肖世德，王德华，许明恒. 液压滑阀V型节流槽气穴流仿真分析及结构优化研究[J]. 兵工学报, 2015, 36(2): 345-354.

基于光学厚度代理模型的雾浓度估计及图像去雾

Research on Optical Depth Surrogate Model-based Method for Estimating Fog Density and Removing Fog Effect from Images

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价