Assessment of image fusion procedures using entropy, image quality, and multispectral classification

被引：26

作者：

Roberts, J. Wesley ^{[1
]}

Van Aardt, Jan ^{[2
]}

Ahmed, Fethi ^{[3
]}

机构：

[1] Council for Scientific and Industrial Research, Natural Resources and the Environment, Ecosystems, Forestry and Forest Products Research Centre, P.O.Box 17001, Congella, 4013, South Africa

[2] Cncl. for Sci. and Indust. Res., Nat. Resources and the Environment, Ecosystems, Earth Observation, P.O. Box 395, Pretoria, 0001, South Africa

[3] University of Kwazulu-Natal, School of Environmental Sciences, King George V Avenue, Glenwood, Durban, 4041, South Africa

来源：

Journal of Applied Remote Sensing | 2008年 / 2卷 / 01期

关键词：

The use of disparate data sources within a pixel level image fusion procedure has been well documented for pan-sharpening studies. The present paper explores various image fusion procedures for the fusion of multi-spectral ASTER data and a RadarSAT-1 SAR scene. The research sought to determine which fusion procedure merged the largest amount of SAR texture into the ASTER scenes; while also preserving the spectral content. An additional application based maximum likelihood classification assessment was also undertaken. Three SAR scenes were tested namely; one backscatter scene and two textural measures calculated using grey level co-occurrence matrices (GLCM). Each of these were fused to the ASTER data using the following established approaches; Brovey transformation; Intensity Hue and Saturation; Principal Component Substitution; Discrete wavelet transformation; and a modified discrete wavelet transformation using the IHS approach. Resulting data sets were assessed using qualitative and quantitative (entropy; universal image quality index; maximum likelihood classification) approaches. Results from the study indicated that while all post fusion data sets contained more information (entropy analysis); only the frequency-based fusion approaches managed to preserve the spectral quality of the original imagery. Furthermore results also indicated that the textural (mean; contrast) SAR scenes did not add any significant amount of information to the post-fusion imagery. Classification accuracy was not improved when comparing ASTER optical data and pseudo optical bands generated from the fusion analysis. Accuracies range from 68.4% for the ASTER data to well below 50% for the component substitution methods. Frequency based approaches also returned lower accuracies when compared to the unfused optical data. The present study essentially replicated (pan-sharpening) studies using the high resolution SAR scene as a pseudo panchromatic band. © 2008 Society of Photo-Optical Instrumentation Engineers;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Journal article (JA)

引用

共 50 条

[21] TECHNIQUES FOR MULTISPECTRAL IMAGE CLASSIFICATION
CARLOTTO, MJ
PROCEEDINGS OF THE SOCIETY OF PHOTO-OPTICAL INSTRUMENTATION ENGINEERS, 1985, 528 : 174 - 191
[22] Multispectral Image Filtering Method Based on Image Fusion
Zhang, Wei
Chen, Wei
MIPPR 2015: MULTISPECTRAL IMAGE ACQUISITION, PROCESSING, AND ANALYSIS, 2015, 9811
[23] Decision Fusion for Image Quality Assessment using an Optimization Approach
Oszust, Mariusz
IEEE SIGNAL PROCESSING LETTERS, 2016, 23 (01) : 65 - 69
[24] Optics and radar image fusion based on image quality assessment
Reulke, Ralf
Giaquinto, Gianluca
Giovenco, Marcello
Smart Sensors, Measurement and Instrumentation, 2015, 12 : 83 - 100
[25] Image Quality Assessment Using Multi-Method Fusion
Liu, Tsung-Jung
Lin, Weisi
Kuo, C. -C. Jay
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2013, 22 (05) : 1793 - 1807
[26] Optics and Radar Image Fusion Based on Image Quality Assessment
Reulke, Ralf
Giaquinto, Gianluca
Giovenco, Marcello Maria
Ruess, Dominik
2013 SEVENTH INTERNATIONAL CONFERENCE ON SENSING TECHNOLOGY (ICST), 2013, : 686 - 692
[27] No-reference image quality assessment using fusion metric
Jayashri V. Bagade
Kulbir Singh
Y. H. Dandawate
Multimedia Tools and Applications, 2020, 79 : 2109 - 2125
[28] No-reference image quality assessment using fusion metric
Bagade, Jayashri V.
Singh, Kulbir
Dandawate, Y. H.
MULTIMEDIA TOOLS AND APPLICATIONS, 2020, 79 (3-4) : 2109 - 2125
[29] A Novel Metric for Digital Image Quality Assessment using Entropy-Based Image Complexity
Khanzadi, Pouria
Majidi, Babak
Akhtarkavan, Ehsan
2017 IEEE 4TH INTERNATIONAL CONFERENCE ON KNOWLEDGE-BASED ENGINEERING AND INNOVATION (KBEI), 2017, : 440 - 445
[30] GCFnet: Global Collaborative Fusion Network for Multispectral and Panchromatic Image Classification
Zhao, Hui
Liu, Sicong
Du, Qian
Bruzzone, Lorenzo
Zheng, Yongjie
Du, Kecheng
Tong, Xiaohua
Xie, Huan
Ma, Xiaolong
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60

← 1 2 3 4 5 →