基于加权近红外图像融合的单幅图像除雾方法

doi:10.11896/jsjkx.200300068

计算机科学 ›› 2020, Vol. 47 ›› Issue (8): 241-244.doi: 10.11896/jsjkx.200300068

• 计算机图形学&多媒体 • 上一篇下一篇

基于加权近红外图像融合的单幅图像除雾方法

朱珍¹, 黄锐², 臧铁钢³, 卢世军⁴

1 广东工程职业技术学院信息工程学院广州 510520
2 北京理工大学计算机学院北京 100081
3 南京航空航天大学机电学院南京 210016
4 中山大学地理科学与规划学院广州 510275

出版日期:2020-08-15 发布日期:2020-08-10
通讯作者: 朱珍(44511245@qq.com)
基金资助:
国家自然基金项目(61274085);广东省科学技术厅项目(2014A010103008, 2016B090918021);广东省教育厅重点科研平台和科研项目(2018GKQNCX009);广东省教育厅项目品牌专业项目(2016gzpp031)

Single Image Defogging Method Based on Weighted Near-InFrared Image Fusion

ZHU Zhen¹, HUANG Rui², ZANG Tie-gang³, LU Shi-jun⁴

1 School of Information Technology, Guangdong Engineering Polytechnic College, Guangzhou 510520, China
2 School of Computer Science & Technology, Beijing Institute of Technology, Beijing 100081, China
3 School of Mechatronics, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
4 School of Geography and Planning, Sun Yat-Sen University, Guangzhou 510275, China

Online:2020-08-15 Published:2020-08-10
About author:ZHU Zhen, born in 1980, master, associa-te professor.Her main research intere-sts include algorithm design and analysis, image processing, database application, and software engineering.
Supported by:
This work was supported by the National Natural Science Foundation of China(61274085), Guangdong Provincial Science and Technology Department Project(2014A010103008, 2016B090918021), Guangdong Provincial Education Department Project(2018GKQNCX009) and Guangdong Provincial Education Department Project(2016gzpp031).

摘要/Abstract

摘要： 传统图像除雾方法存在无雾区域中图像对比度过高的问题, 导致在某些情况下生成的图像视觉效果不够自然。为了得到自然清晰的除雾图像, 提出了一种基于加权近红外(Near-InFrared, NIR)图像融合的新型单幅图像除雾方法, 通过将NIR图像的细节成分融合到同一场景的可见光图像中来恢复图像对比度, 并使用透射图对NIR图像进行加权, 从而防止无雾区域出现过度增强。实验结果表明, 相比传统的单幅图像除雾方法, 所提方法可以有效地恢复图像对比度, 并且不会过分强化无雾区域, 具有更高的PSNR值和SSIM值。

关键词: PSNR, SSIM, 加权, 近红外图像, 图像去雾, 图像融合

Abstract: The traditional image defogging method has the problem that the image contrast in the fog-free area is too high, which causes the generated image visual effect is unnatural in some cases.In order to obtain natural and clear defogging images, a new single image defogging method based on weighted near-infrared(NIR) image fusion is proposed.Image contrast is restored by fusing the detail components of NIR images into visible images of the same scene.The NIR image is weighted using the transmission map to prevent excessive enhancement in the fog-free region.The experimental results show that compared with the traditional single image defogging methods, the proposed method can effectively restore the image contrast, does not excessively strengthen the fog-free area, and has higher PSNR and SSIM values.

Key words: Image defogging, Image fusion, Near-infrared image, PSNR, SSIM, Weighting

中图分类号:

TP391

朱珍, 黄锐, 臧铁钢, 卢世军. 基于加权近红外图像融合的单幅图像除雾方法[J]. 计算机科学, 2020, 47(8): 241-244. https://doi.org/10.11896/jsjkx.200300068

ZHU Zhen, HUANG Rui, ZANG Tie-gang, LU Shi-jun. Single Image Defogging Method Based on Weighted Near-InFrared Image Fusion[J]. Computer Science, 2020, 47(8): 241-244. https://doi.org/10.11896/jsjkx.200300068

参考文献

[1] JIANG H Z, YOON S C, ZHUANG H.Predicting Color Traits of Intact Broiler Breast Fillets Using Visible and Near-Infrared Spectroscopy[J].Food Analytical Methods, 2017, 10(10):1-9.
[2] GU Y, YANG X, GAO Y.A Novel Total Generalized Variation Model for Image Dehazing[J].Journal of Mathematical Imaging and Vision, 2019, 61(6):1-13.
[3] XU L, HAN J, WANG T, et al.Global Image Dehazing via Frequency Perception Filtering[J].Journal of Circuits Systems & Computers, 2019, 28(9):1-11.
[4] NI W P, GAO X B, WANG Y.Single satellite image dehazing via linear intensity transformation and local property analysis[J].Neurocomputing, 2015, 175(6):25-39.
[5] HOU J, NING L, LING Y.Single image dehazing for visible remote sensing based on tagged haze thickness maps[J].Remote Sensing Letters, 2018, 9(7):156-165.
[6]HE K M, SUN J, FELLO W.Single Image Haze Removal UsingDark Channel Prior[J].IEEE Transactions on Pattern Analysis &Machine Intelligence, 2011, 33(12):2341-2353.
[7] CHENG D S, LIU H, ZHANG Y Q, et al.Single image defogging method combining adaptive dark channel prior and image fusion strategy [J].Journal of Harbin Institute of Technology, 2016, 48(11):35-40.
[8] STEPHAN J, NANKO V, WLADIMIR T.Near-infrared cut-off filters based on CMOS nanostructures for ambient light sensors and image sensors[J].Proceedings of SPIE-The International Society for Optical Engineering, 2014, 8994(9):2212-2212.
[9] ASHISH V V, VIKRAM M G.Visible and NIR image fusion using weight-map-guided Laplacian-Gaussian pyramid for improving scene visibility[J].Sadhana, 2017, 42(7):1-20.
[10]MIAO Q G, LI Y N.Research Status and Prospect of Image Dehazing Algorithm [J].Journal of Frontiers of Computer Science, 2017(11):7-14.
[11]LEX S, CL’EMENT F, SABINE S.Color image dehazing using the near-infrared∥2009 16th IEEE International Conference on Image Processing(ICIP).Cairo, 2009:1629-1632.
[12]ZHAO S N, WEI W B, PAN Z K, et al.Dehazing of a single color image based on dark primary color prior and MTV model [J].Computer Science, 2018, 45(3):274-276, 282.
[13]WEI Z L, XU G Y, ZHANG S X, et al.Dehazing Image Quality Evaluation System Based on MATLAB [J].Journal of Heilongjiang Institute of Technology(Comprehensive Edition), 2019, 19(8):36-39.
[14]LV X N, LIU Y Y, TAN Z, et al.A polarizing universal multiscale real-time image dehazing algorithm [J].Acta Photonica Sinica, 2019(8):111-121.
[15]WU D, ZHU Q S.The latest research progress of image defogging [J].Acta Automatica Sinica, 2015(2):221-239.
[16]ZHANG D Y, JU M Y, WANG X M.A Fast Image Dehazing Algorithm Based on Dark Channel Prior [J].Chinese Journal of Electronics, 2015, 43(7):1437-1443.
[17]LIANG J X, WAN X X, LIU Q.Research on the registrationmethod of visible light broadband spectral image based on SIFT algorithm [J].Journal of Hunan University of Technology, 2015(2):57-63.
[18]JIANG Y T, SUN C M, ZHAO Y.Fog Density Estimation and Image Defogging Based on Surrogate Modeling for Optical Depth[J].IEEE Transactions on Image Processing, 2017, 26(7):3397-3409.
[19]LONG J, SHI Z, TANG W, et al.Single Remote Sensing Image Dehazing[J].IEEE Geoence & Remote Sensing Letters, 2013, 11(1):59-63.
[20]CHENG D S, LIU H, ZHANG Y Q, et al.Single image defogging method combining adaptive dark channel prior and image fusion strategy [J].Journal of Harbin Institute of Technology, 2016, 48(11):36-40.
[21]SINGH D, KUMAR V, KAUR M.Single image dehazing using gradient channel prior[J].Applied Intelligence, 2019, 49(8):4276-4293.

相关文章 15

[1]	杨文坤, 原晓佩, 陈小锋, 郭睿. 三维激光雷达点云空间多特征分割 Spatial Multi-feature Segmentation of 3D Lidar Point Cloud 计算机科学, 2022, 49(8): 143-149. https://doi.org/10.11896/jsjkx.210300275
[2]	来腾飞, 周海洋, 余飞鸿. 视频流的实时景深延拓算法 Real-time Extend Depth of Field Algorithm for Video Processing 计算机科学, 2022, 49(6A): 314-318. https://doi.org/10.11896/jsjkx.201100187
[3]	赵明华, 周童童, 都双丽, 石争浩. 基于虚拟曝光方法的单幅逆光图像增强 Single Backlit Image Enhancement Based on Virtual Exposure Method 计算机科学, 2022, 49(6A): 384-389. https://doi.org/10.11896/jsjkx.210400243
[4]	高元浩, 罗晓清, 张战成. 基于特征分离的红外与可见光图像融合算法 Infrared and Visible Image Fusion Based on Feature Separation 计算机科学, 2022, 49(5): 58-63. https://doi.org/10.11896/jsjkx.210200148
[5]	颜敏, 罗晓清, 张战成. 基于光传输模型学习的红外和可见光图像融合网络设计 Infrared and Visible Image Fusion Network Based on Optical Transmission Model Learning 计算机科学, 2022, 49(4): 215-220. https://doi.org/10.11896/jsjkx.210200174
[6]	官铮, 邓扬琳, 聂仁灿. 光谱重建约束非负矩阵分解的高光谱与全色图像融合 Non-negative Matrix Factorization Based on Spectral Reconstruction Constraint for Hyperspectral and Panchromatic Image Fusion 计算机科学, 2021, 48(9): 153-159. https://doi.org/10.11896/jsjkx.200900054
[7]	黄晓生, 徐静. 基于PCANet的非下采样剪切波域多聚焦图像融合 Multi-focus Image Fusion Method Based on PCANet in NSST Domain 计算机科学, 2021, 48(9): 181-186. https://doi.org/10.11896/jsjkx.200800064
[8]	田嵩旺, 蔺素珍, 杨博. 基于多判别器的多波段图像自监督融合方法 Multi-band Image Self-supervised Fusion Method Based on Multi-discriminator 计算机科学, 2021, 48(8): 185-190. https://doi.org/10.11896/jsjkx.200600132
[9]	何涛, 赵停, 徐鹤. 基于暗通道先验的单幅图像去雾新算法 Novel Algorithm of Single Image Dehazing Based on Dark Channel Prior 计算机科学, 2021, 48(7): 219-224. https://doi.org/10.11896/jsjkx.200700160
[10]	石先让, 宋廷伦, 唐得志, 戴振泳. 一种新颖的单目视觉深度学习算法:H_SFPN Novel Deep Learning Algorithm for Monocular Vision:H_SFPN 计算机科学, 2021, 48(4): 130-137. https://doi.org/10.11896/jsjkx.200400090
[11]	储杰, 张正军, 汤鑫瑶, 黄振生. 基于加权样本和共识率的标记传播算法 Label Propagation Algorithm Based on Weighted Samples and Consensus-rate 计算机科学, 2021, 48(3): 214-219. https://doi.org/10.11896/jsjkx.191200103
[12]	王丽芳, 王蕊芳, 蔺素珍, 秦品乐, 高媛, 张晋. 基于双残差超密集网络的多模态医学图像融合 Multimodal Medical Image Fusion Based on Dual Residual Hyper Densely Networks 计算机科学, 2021, 48(2): 160-166. https://doi.org/10.11896/jsjkx.200400095
[13]	王同森, 史勤忠, 王得法, 董硕, 杨国为, 于腾. 基于光源区域自适应的夜间去雾方法 Nighttime Image Dehazing Method Based on Adaptive Light Source Region 计算机科学, 2021, 48(11A): 327-333. https://doi.org/10.11896/jsjkx.210300072
[14]	张天瑞, 魏铭琦, 高秀秀. 基于IPSO-WRF的选择性激光烧结件气泡溶解时间预测模型 Prediction Model of Bubble Dissolution Time in Selective Laser Sintering Based on IPSO-WRF 计算机科学, 2021, 48(11A): 638-643. https://doi.org/10.11896/jsjkx.210300080
[15]	杨坤, 张娟, 方志军. 基于多补丁和多尺度层级聚合网络的快速非均匀图像去雾 Multi-patch and Multi-scale Hierarchical Aggregation Network for Fast Nonhomogeneous ImageDehazing 计算机科学, 2021, 48(11): 250-257. https://doi.org/10.11896/jsjkx.200900058

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于加权近红外图像融合的单幅图像除雾方法

Single Image Defogging Method Based on Weighted Near-InFrared Image Fusion

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0