Pseudoinvariant feature selection for cross-sensor optical satellite images

Lino Garda Denaro, Bo Yi Lin, Muhammad Aldila Syariz, Lalu Muhamad Jaelani, Chao-Hung Lin

研究成果: Article

摘要

Processing of multitemporal satellite images generally suffers from uncertainties caused by differences in illumination and observation angles, as well as variation in atmospheric conditions. Moreover, satellite images acquired from different sensors contain not only the uncertainties but also disparate relative spectral response. Given that radiometric calibration and correction of satellite images are difficult without ground measurements during data acquisition, this study addresses pseudoinvariant feature selection for relative radiometric normalization (RRN) that minimizes the radiometric differences among images caused by atmospheric and spectral band inconsistencies during data acquisition. The key to a successful RRN is the selection of pseudoinvariant features (PIFs) among bitemporal images. To select PIFs, multivariate alteration detection (MAD) algorithm is adopted with kernel canonical correlation analysis (KCCA) instead of canonical correlation analysis (CCA). KCCA, which assumes that the relation between at-sensor radiance is spatially nonlinear, can obtain more appropriate PIFs for cross-sensor images than that of CCA, which assumes that the relation between the at-sensor radiances of bitemporal image is spatially linear. In addition, a regularization term is added to the optimization of KCCA to avoid trivial solutions and overfitting. Qualitative and quantitative analyses on bitemporal images acquired by Landsat-7 enhanced thematic mapper plus and Landsat-8 operational and imager sensors were conducted to evaluate the proposed method. The experimental results demonstrate the superiority of the proposed KCCA-based MAD to the CCA-based MAD in terms of PIF selection, particularly for images containing significant cloud covers.

原文English
文章編號045002
期刊Journal of Applied Remote Sensing
12
發行號4
DOIs
出版狀態Published - 2018 十月 1

指紋

sensor
radiance
data acquisition
Landsat
analysis
satellite image
cloud cover
calibration
detection
normalisation

All Science Journal Classification (ASJC) codes

  • Earth and Planetary Sciences(all)

引用此文

Denaro, Lino Garda ; Lin, Bo Yi ; Syariz, Muhammad Aldila ; Jaelani, Lalu Muhamad ; Lin, Chao-Hung. / Pseudoinvariant feature selection for cross-sensor optical satellite images. 於: Journal of Applied Remote Sensing. 2018 ; 卷 12, 編號 4.
@article{893c5ec6d9064d748786f13bc70be599,
title = "Pseudoinvariant feature selection for cross-sensor optical satellite images",
abstract = "Processing of multitemporal satellite images generally suffers from uncertainties caused by differences in illumination and observation angles, as well as variation in atmospheric conditions. Moreover, satellite images acquired from different sensors contain not only the uncertainties but also disparate relative spectral response. Given that radiometric calibration and correction of satellite images are difficult without ground measurements during data acquisition, this study addresses pseudoinvariant feature selection for relative radiometric normalization (RRN) that minimizes the radiometric differences among images caused by atmospheric and spectral band inconsistencies during data acquisition. The key to a successful RRN is the selection of pseudoinvariant features (PIFs) among bitemporal images. To select PIFs, multivariate alteration detection (MAD) algorithm is adopted with kernel canonical correlation analysis (KCCA) instead of canonical correlation analysis (CCA). KCCA, which assumes that the relation between at-sensor radiance is spatially nonlinear, can obtain more appropriate PIFs for cross-sensor images than that of CCA, which assumes that the relation between the at-sensor radiances of bitemporal image is spatially linear. In addition, a regularization term is added to the optimization of KCCA to avoid trivial solutions and overfitting. Qualitative and quantitative analyses on bitemporal images acquired by Landsat-7 enhanced thematic mapper plus and Landsat-8 operational and imager sensors were conducted to evaluate the proposed method. The experimental results demonstrate the superiority of the proposed KCCA-based MAD to the CCA-based MAD in terms of PIF selection, particularly for images containing significant cloud covers.",
author = "Denaro, {Lino Garda} and Lin, {Bo Yi} and Syariz, {Muhammad Aldila} and Jaelani, {Lalu Muhamad} and Chao-Hung Lin",
year = "2018",
month = "10",
day = "1",
doi = "10.1117/1.JRS.12.045002",
language = "English",
volume = "12",
journal = "Journal of Applied Remote Sensing",
issn = "1931-3195",
publisher = "SPIE",
number = "4",

}

Pseudoinvariant feature selection for cross-sensor optical satellite images. / Denaro, Lino Garda; Lin, Bo Yi; Syariz, Muhammad Aldila; Jaelani, Lalu Muhamad; Lin, Chao-Hung.

於: Journal of Applied Remote Sensing, 卷 12, 編號 4, 045002, 01.10.2018.

研究成果: Article

TY - JOUR

T1 - Pseudoinvariant feature selection for cross-sensor optical satellite images

AU - Denaro, Lino Garda

AU - Lin, Bo Yi

AU - Syariz, Muhammad Aldila

AU - Jaelani, Lalu Muhamad

AU - Lin, Chao-Hung

PY - 2018/10/1

Y1 - 2018/10/1

N2 - Processing of multitemporal satellite images generally suffers from uncertainties caused by differences in illumination and observation angles, as well as variation in atmospheric conditions. Moreover, satellite images acquired from different sensors contain not only the uncertainties but also disparate relative spectral response. Given that radiometric calibration and correction of satellite images are difficult without ground measurements during data acquisition, this study addresses pseudoinvariant feature selection for relative radiometric normalization (RRN) that minimizes the radiometric differences among images caused by atmospheric and spectral band inconsistencies during data acquisition. The key to a successful RRN is the selection of pseudoinvariant features (PIFs) among bitemporal images. To select PIFs, multivariate alteration detection (MAD) algorithm is adopted with kernel canonical correlation analysis (KCCA) instead of canonical correlation analysis (CCA). KCCA, which assumes that the relation between at-sensor radiance is spatially nonlinear, can obtain more appropriate PIFs for cross-sensor images than that of CCA, which assumes that the relation between the at-sensor radiances of bitemporal image is spatially linear. In addition, a regularization term is added to the optimization of KCCA to avoid trivial solutions and overfitting. Qualitative and quantitative analyses on bitemporal images acquired by Landsat-7 enhanced thematic mapper plus and Landsat-8 operational and imager sensors were conducted to evaluate the proposed method. The experimental results demonstrate the superiority of the proposed KCCA-based MAD to the CCA-based MAD in terms of PIF selection, particularly for images containing significant cloud covers.

AB - Processing of multitemporal satellite images generally suffers from uncertainties caused by differences in illumination and observation angles, as well as variation in atmospheric conditions. Moreover, satellite images acquired from different sensors contain not only the uncertainties but also disparate relative spectral response. Given that radiometric calibration and correction of satellite images are difficult without ground measurements during data acquisition, this study addresses pseudoinvariant feature selection for relative radiometric normalization (RRN) that minimizes the radiometric differences among images caused by atmospheric and spectral band inconsistencies during data acquisition. The key to a successful RRN is the selection of pseudoinvariant features (PIFs) among bitemporal images. To select PIFs, multivariate alteration detection (MAD) algorithm is adopted with kernel canonical correlation analysis (KCCA) instead of canonical correlation analysis (CCA). KCCA, which assumes that the relation between at-sensor radiance is spatially nonlinear, can obtain more appropriate PIFs for cross-sensor images than that of CCA, which assumes that the relation between the at-sensor radiances of bitemporal image is spatially linear. In addition, a regularization term is added to the optimization of KCCA to avoid trivial solutions and overfitting. Qualitative and quantitative analyses on bitemporal images acquired by Landsat-7 enhanced thematic mapper plus and Landsat-8 operational and imager sensors were conducted to evaluate the proposed method. The experimental results demonstrate the superiority of the proposed KCCA-based MAD to the CCA-based MAD in terms of PIF selection, particularly for images containing significant cloud covers.

UR - http://www.scopus.com/inward/record.url?scp=85054958835&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054958835&partnerID=8YFLogxK

U2 - 10.1117/1.JRS.12.045002

DO - 10.1117/1.JRS.12.045002

M3 - Article

AN - SCOPUS:85054958835

VL - 12

JO - Journal of Applied Remote Sensing

JF - Journal of Applied Remote Sensing

SN - 1931-3195

IS - 4

M1 - 045002

ER -