Luminance Learning for Remotely Sensed Image Enhancement Guided by Weighted Least Squares

被引：29

作者：

Huang, Zhenghua ^{[1
,2
]}

Zhu, Zifan ^{[1
]}

An, Qing ^{[2
]}

Wang, Zhicheng ^{[1
]}

Zhou, Qin ^{[3
]}

Zhang, Tianxu ^{[1
]}

Alshomrani, Ali Saleh ^{[4
]}

机构：

[1] Wuhan Inst Technol, Hubei Key Lab Opt Informat & Pattern Recognit, Wuhan 430205, Peoples R China

[2] Wuchang Univ Technol, Artificial Intelligence Sch, Wuhan 430223, Peoples R China

[3] Wuhan Donghu Univ, Sch Elect & Informat Engn, Wuhan 430212, Hubei, Peoples R China

[4] King Abdulaziz Univ, Dept Math, Math Modelling & Appl Computat Res Grp MMAC, Jeddah 21589, Saudi Arabia

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2022年 / 19卷

基金：

中国国家自然科学基金;

关键词：

Visualization; Convolution; MODIS; Lighting; Image enhancement; Standards; Optical imaging; Contrast improvement; detail preservation; luminance learning; remotely sensed images (RSIs); SENSING IMAGE; HISTOGRAM EQUALIZATION; ILLUMINATION; NETWORK;

D O I：

10.1109/LGRS.2021.3093935

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

Low/high or uneven luminance results in low contrast of remotely sensed images (RSIs), which makes it challenging to analyze their contents. In order to improve the contrast and preserving fine weak details of RSIs, this letter proposes a novel enhancement framework to correct luminance guided by weighted least squares (WLS), including the following key parts. First, an image is separated into a base layer and a detail layer by employing the WLS. Then, a learning network is proposed to correct luminance for the base layer enhancement. Next, an enhancement operator for improving the detail layer is computed by using the original image and the enhanced base layer. Finally, the output image is obtained with a fusion of the enhanced base and detail components. Both quantitatively and qualitatively experimental results verify that the proposed method performs better than the state of the arts in contrast improvement and detail preservation.

引用

页数：5

共 30 条

[1] Transform coefficient histogram-based image enhancement algorithms using contrast entropy [J].

Agaian, Sos S. ;

Silver, Blair ;

Panetta, Karen A. .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (03) :741-758

[2] Learning a Deep Single Image Contrast Enhancer from Multi-Exposure Images [J].

Cai, Jianrui ;

Gu, Shuhang ;

Zhang, Lei .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2018, 27 (04) :2049-2062

[3] Destriping Remote Sensing Image via Low-Rank Approximation and Nonlocal Total Variation [J].

Cao, Wenfei ;

Chang, Yi ;

Han, Guodong ;

Li, Junbing .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2018, 15 (06) :848-852

[4] Preserving brightness in histogram equalization based contrast enhancement techniques [J].

Chen, SD ;

Ramli, A .

DIGITAL SIGNAL PROCESSING, 2004, 14 (05) :413-428

[5] Satellite Image Contrast Enhancement Using Discrete Wavelet Transform and Singular Value Decomposition [J].

Demirel, Hasan ;

Ozcinar, Cagri ;

Anbarjafari, Gholamreza .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2010, 7 (02) :333-337

[6] No-Reference Quality Assessment of Contrast-Distorted Images Based on Natural Scene Statistics [J].

Fang, Yuming ;

Ma, Kede ;

Wang, Zhou ;

Lin, Weisi ;

Fang, Zhijun ;

Zhai, Guangtao .

IEEE SIGNAL PROCESSING LETTERS, 2015, 22 (07) :838-842

[7] Edge-preserving decompositions for multi-scale tone and detail manipulation [J].

Farbman, Zeev ;

Fattal, Raanan ;

Lischinski, Dani ;

Szeliski, Richard .

ACM TRANSACTIONS ON GRAPHICS, 2008, 27 (03)

[8] Remote Sensing Image Enhancement Using Regularized-Histogram Equalization and DCT [J].

Fu, Xueyang ;

Wang, Jiye ;

Zeng, Delu ;

Huang, Yue ;

Ding, Xinghao .

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2015, 12 (11) :2301-2305

[9]

Fu Xueyang, 2014, INT C ACOUSTICS SPE

[10]

Gonzalez R. C., 2017, Digital Image Processing, V4

← 1 2 3 →