Please wait a minute...
 
Remote Sensing for Natural Resources    2024, Vol. 36 Issue (2) : 70-79     DOI: 10.6046/zrzyyg.2023010
|
An intelligent color enhancement method for high-resolution remote sensing images of the coastal zone of an island
ZHAO Binru1(), NIU Siwen2, WANG Liyan1, YANG Xiaotong1, JIAO Hongbo1, WANG Zike1()
1. National Marine Data and Information Service, Tianjin 300012, China
2. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430000, China
Download: PDF(20100 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

The original high-spatial-resolution remote sensing images of coastal zones of islands often exhibit a gray tone, color cast, and indistinguishable surface feature information. In response to the increasing demand for geographic information security of coastal zones of islands, this study aims to obtain timely clear remote sensing images with rich information, moderate contrast, and uniform brightness for island reefs. Hence, it proposed an intelligent color enhancement method by combining deep learning with improved histogram matching for high-spatial-resolution remote sensing images of coastal zones of islands. First, data resampling and adaptive chunking were performed to obtain thinned images. Then, the MBLLEN network was applied to enhance the thinned images with true color. Finally, an improved histogram matching method was employed for color mapping of original images, obtaining remote sensing images with consistent colors and rich details conforming to human vision. The color-matching effects of these obtained remote sensing images were evaluated using both subjective and objective methods. The results show that compared to other commonly used color-matching methods like Retinex, HE, and MASK, the method proposed in this study yielded more satisfactory results characterized by consistent colors and rich details conforming to human vision. Therefore, the proposed method can effectively improve the visual effects of high-spatial-resolution remote sensing images of coastal zones of islands, effectively retain the details of original surface features, and significantly enhance color-matching efficiency.

Keywords remote sensing image of the coastal zone of an island      MBLLEN      histogram matching      color mapping     
ZTFLH:  TP79  
Issue Date: 14 June 2024
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Binru ZHAO
Siwen NIU
Liyan WANG
Xiaotong YANG
Hongbo JIAO
Zike WANG
Cite this article:   
Binru ZHAO,Siwen NIU,Liyan WANG, et al. An intelligent color enhancement method for high-resolution remote sensing images of the coastal zone of an island[J]. Remote Sensing for Natural Resources, 2024, 36(2): 70-79.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2023010     OR     https://www.gtzyyg.com/EN/Y2024/V36/I2/70
Fig.1  Location of the study area
Fig.2  General flow chart of technology
Fig.3  Image resampling and adaptive blocking
Fig.4  MBLLEN network structure
Fig.5  Partial minimum object of interest color unit
Fig.6  Contrast of true color enhancement effect of thinning image
Fig.7  Comparison of results before and after high resolution image tinting
Fig.8-1  Images and histograms before and after color scale compensation in some areas
Fig.8-2  Images and histograms before and after color scale compensation in some areas
Tab.1  Comparison of color matching results using different methods
影像名 方法 均值 标准差 色彩丰富度 变异系数 信息熵 峰值信噪比
影像1 原始 31.921 27.800 5.000 87.100 6.017
Retinex 74.010 44.540 13.411 60.193 7.331 16.241
HE 132.320 66.883 20.112 50.541 7.191 7.972
Mask 38.792 23.684 8.422 61.042 5.773 24.013
本文算法 88.050 56.421 25.615 64.086 7.434 12.993
影像2 原始 27.700 27.429 5.212 99.038 5.611
Retinex 60.122 42.781 10.313 71.152 7.722 18.822
HE 121.603 61.734 19.153 50.763 7.321 8.650
Mask 22.592 19.681 6.930 87.114 6.171 25.530
本文算法 82.638 62.723 26.338 75.900 7.827 13.830
影像3 原始 30.262 22.010 1.700 72.720 5.770
Retinex 61.795 41.362 11.202 66.932 7.520 16.330
HE 122.326 60.911 20.411 49.792 7.190 8.011
Mask 23.202 15.646 6.353 67.411 5.382 25.582
本文算法 85.531 58.442 23.370 68.333 7.400 12.892
影像4 原始 34.710 28.105 11.511 80.963 6.143
Retinex 77.172 45.872 14.882 59.444 7.331 18.420
HE 142.331 68.830 23.122 48.362 7.691 7.990
Mask 41.162 23.090 8.821 56.102 5.653 26.612
本文算法 90.351 63.892 27.270 70.713 7.773 12.671
拼合后影像 原始 30.216 26.383 6.881 79.665 5.897
Retinex 68.673 43.009 12.177 65.110 7.430 17.071
HE 136.377 64.113 20.091 49.989 7.200 8.003
Mask 35.535 20.587 7.689 72.213 5.962 25.451
本文算法 86.721 60.080 25.556 68.839 7.509 13.156
Tab.2  Evaluation indicators for color mixing results of different algorithms
[1] 李晓敏, 张杰, 马毅, 等. 粤西海岛海岸带典型地类SPOT-5影像解译标志[J]. 海洋通报, 2011, 30(4):447-450,455.
[1] Li X M, Zhang J, Ma Y et al. Interpretation marks of SPOT-5 image on typical target types of islands and coastal zone in western Guangdong[J]. Marine Science Bulletin, 2011, 30(4):447-450,455.
[2] 余磊. 光学遥感卫星色彩一致性合成影像生成关键技术研究[D]. 武汉: 武汉大学, 2017.
[2] Yu L. Key technology on color balancing for creation of color consistency synthetic products with optical remote sensing imagery[D]. Wuhan: Wuhan University, 2017.
[3] 武彬, 江家宝. 基于链接突触计算网络的遥感图像对比度增强算法[J]. 计算机应用与软件, 2020, 37(4):214-219.
[3] Wu B, Jiang J B. Contrast enhancement algorithm of remote sensing images based on linking synaptic computation network[J]. Computer Applications and Software, 2020, 37(4):214-219.
[4] 张星铭, 孙文邦, 岳广. 基于色彩恒常理论的多光谱图像真彩色复原技术[J]. 兵器装备工程学报, 2020, 41(11):248-256.
[4] Zhang X M, Sun W B, Yue G. True color restoration of multispectral image based on color constancy[J]. Journal of Ordnance Equipment Engineering, 2020, 41(11):248-256.
[5] 元建胜. 面向大规模02C卫星影像的色彩处理技术[J]. 海洋测绘, 2017, 37(1):66-70.
[5] Yuan J S. Color consistency processing technology of large-scale 02C satellite images[J]. Hydrographic Surveying and Charting, 2017, 37(1):66-70.
[6] 韩宇韬. 数字正射影像镶嵌中色彩一致性处理的若干问题研究[D]. 武汉: 武汉大学, 2014.
[6] Han Y T. Research on key technology of color consistency processing for digtial ortho map mosaicing[D]. Wuhan: Wuhan University, 2014.
[7] 张荞, 张艳梅, 蒙印. 基于直方图匹配的多源遥感影像匀色研究[J]. 地理空间信息, 2020, 18(12):54-57,7.
[7] Zhang Q, Zhang Y M, Meng Y. Research on color uniforming for multi-source remote sensing images based on histogram matching method[J]. Geospatial Information, 2020, 18(12):54-57,7.
[8] Rizzi A, Gatta C, Marini D. From Retinex to automatic color equalization:Issues in developing a new algorithm for unsupervised color equalization[J]. Journal of Electronic Imaging, 2004, 13(1):75-84.
[9] 袁修孝, 韩宇韬, 方毅. 改进的航摄影像Mask匀光算法[J]. 遥感学报, 2014, 18(3):630-641.
[9] Yuan X X, Han Y T, Fang Y. Improved Mask dodging algorithm for aerial imagery[J]. Journal of Remote Sensing, 2014, 18(3):630-641.
[10] 曹彬才, 朱宝山, 李润生, 等. 用于单幅影像匀光的Wallis算法[J]. 测绘科学技术学报, 2012, 29(5):373-377.
[10] Cao B C, Zhu B S, Li R S, et al. Wallis algorithm for single image dodging[J]. Journal of Geomatics Science and Technology, 2012, 29(5):373-377.
[11] 李德仁, 王密, 潘俊. 光学遥感影像的自动匀光处理及应用[J]. 武汉大学学报(信息科学版), 2006, 31(9):753-756.
[11] Li D R, Wang M, Pan J. Auto-dodging processing and its application for optical RS images[J]. Geomatics and Information Science of Wuhan University, 2006, 31(9):753-756.
[12] 王密, 潘俊. 一种数字航空影像的匀光方法[J]. 中国图象图形学报, 2004, 9(6):744-748.
[12] Wang M, Pan J. A method of removing the uneven illumination for digital aerial image[J]. Journal of Image and Graphics, 2004, 9(6):744-748.
[13] Orsini G, Ramponi G, Carrai P, et al. A modified retinex for image contrast enhancement and dynamics control[C]// International Conference on Image Processing.IEEE, 2003:393-398.
[14] Lam E Y. Combining gray world and retinex theory for automatic white balance in digital photography[C]// Proceedings of the Ninth International Symposium on Consumer Electronics,2005.(ISCE 2005).IEEE, 2005:134-139.
[15] Seow M J, Asari V K. Ratio rule and homomorphic filter for enhancement of digital colour image[J]. Neurocomputing, 2006, 69(7/8/9):954-958.
[16] Hsia S C, Chen M H, Chen Y M. A cost-effective line-based light-balancing technique using adaptive processing[J]. IEEE Transactions on Image Processing A Publication of the IEEE Signal Processing Society, 2006, 15(9):2719-2729.
[17] 李国. 基于遗传算法的遥感影像增强技术研究[D]. 郑州: 解放军信息工程大学, 2012.
[17] Li G. The study of remote sensing image enhancement based on genetic algorithms[D]. Zhengzhou: Information Engineering University, 2012.
[18] Li Q Q, Lu Y, Hu S B, et al. Review of remotely sensed geoenvironmental monitoring of coastal zones[J]. Journal of Remote Sensing, 2016, 20(5):1216-1229.
[19] Lyu F F, Lu F, Wu J H, et al. MBLLEN:Low-light image/video enhancement using CNNs[C]// British MachineVision Conference.IEEE, 2018:.220-233.
[20] 陈建乐, 刘济林, 叶建洪, 等. 多视点视频中基于局部直方图匹配的亮度和色差校正[J]. 中国图象图形学报, 2007, 12(11):1992-1999.
[20] Chen J L, Liu J L, Ye J H, et al. Luminance and chrominance correction for multi-view video using overlapped local histogram matching[J]. Journal of Image and Graphics, 2007, 12(11):1992-1999.
[21] 周妍, 李庆武, 霍冠英. 基于非下采样Contourlet变换系数直方图匹配的自适应图像增强[J]. 光学精密工程, 2014, 22(8):2214-2222.
[21] Zhou Y, Li Q W, Huo G Y. Adaptive image enhancement based on NSCT coefficient histogram matching[J]. Optics and Precision Engineering, 2014, 22(8):2214-2222.
[22] 孙立辉, 张竟雄. 基于高斯平滑直方图匹配的图像间匀光算法[J]. 信息与电脑(理论版), 2021, 33(21):45-47.
[22] Sun L H, Zhang J X. Uniform light between images based on Gaussian smooth histogram matching[J]. China Computer and Communication, 2021, 33(21):45-47.
[23] 丁春秋. 基于混合直方图匹配的多相机色彩校正[D]. 南京: 南京大学, 2021.
[23] Ding C Q. Multi-camera color correction via hybrid histogram matching[D]. Nanjing: Nanjing University, 2021.
[24] 卢其剑. 基于区域网平差的遥感影像色彩均衡算法研究[D]. 南昌: 东华理工大学, 2020.
[24] Lu Q J. Research on remote sensing image color equalization method based on block adjustment[D]. Nanchang: East China University of Technology, 2020.
[25] Hasler D, Suesstrunk S E. Measuring colorfulness in natural images[J]. Hunman Vision and Electronic Imaging, 2003, 6(17):87-96.
[1] YANG Hang, Zhang-Xia, He-Hai-Xia, Zhang-Li-Fu, Tong-Qing-Xi. The Optimal Choice of Edge-Radiation-Distortion Correction Methods
for OMIS-II Hyperspectral Images
[J]. REMOTE SENSING FOR LAND & RESOURCES, 2010, 22(2): 17-21.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech