Pseudoinvariant feature selection for cross-sensor optical satellite images

Denaro, Lino Garda; Lin, Bor-Luh; Syariz, Muhammad Aldila; Jaelani, Lalu Muhamad; Lin, Ching Hsuan

doi:10.1117/1.jrs.12.045002

Cited by 5 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where and are replaced by ( ) × and ( ) × with the mapping function and = ( ) ( ) and = ( ) ( ). The more detailed equation, the readers are suggested to read kernel canonical correlation analysis [1]. Therefore, according to [1], the PIFs selection is done by normalization on MAD in higher dimension denoted by,…”

Section: Pseudo-invariant Feature Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Canonical Correlation Analysis and Regression for Radiometric Normalization of Cross-Sensor Satellite Images

Denaro

Lin

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. Relative radiometric normalization (RRN) minimizes radiometric differences among images caused by inconsistencies of acquisition condition. In this study, a cross-sensor RRN method is proposed for optical satellite images from Landsat 8 OLI (L8) and Landsat 7 ETM+ (L7) sensors. The data from these two sensors have different pixel depths. Therefore, a rescaling on the radiometry resolution is performed in the preprocessing. Then, multivariate alteration detection (MAD) based on kernel canonical correlation analysis (KCCA) is adopted, which is called KCCA-based MAD, to select pseudo-invariant features (PIFs). The process of RRN is performed by using polynomial regression with Gaussian weighted regression. In experiments, qualitative and quantitative analyses on images from different sensors are conducted. The experimental result demonstrates the superiority of the proposed nonlinear transformation, in terms of regression quality and radiometric consistency, compared with RRN using linear regression.

show abstract

Section: Pseudo-invariant Feature Selectionmentioning

confidence: 99%

“…Remote sensing based on satellite images is one of the techniques to analyze the earth spatial condition. Landsat program is the one having the longest history [1]. Landsat 1 was launched in 1972, and the last generation is Landsat 8 which was launched in 2013 and is currently still operating [2].…”

Section: Introductionmentioning

confidence: 99%

Hybrid Canonical Correlation Analysis and Regression for Radiometric Normalization of Cross-Sensor Satellite Images

Denaro

Lin

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…The absolute correction predicts and removes the scattering due to gases and aerosols in the atmosphere [15,16], and several models have been proposed for water bodies [17][18][19]. By contrast, the relative correction minimizes numerical differences among images using image processing techniques [20][21][22][23].…”

Section: Introductionmentioning

confidence: 99%

WaterNet: A Convolutional Neural Network for Chlorophyll-a Concentration Retrieval

et al. 2020

Self Cite

View full text Add to dashboard Cite

The retrieval of chlorophyll-a (Chl-a) concentrations relies on empirical or analytical analyses, which generally experience difficulties from the diversity of inland waters in statistical analyses and the complexity of radiative transfer equations in analytical analyses, respectively. Previous studies proposed the utilization of artificial neural networks (ANNs) to alleviate these problems. However, ANNs do not consider the problem of insufficient in situ samples during model training, and they do not fully utilize the spatial and spectral information of remote sensing images in neural networks. In this study, a two-stage training is introduced to address the problem regarding sample insufficiency. The neural network is pretrained using the samples derived from an existing Chl-a concentration model in the first stage, and the pretrained model is refined with in situ samples in the second stage. A novel convolutional neural network for Chl-a concentration retrieval called WaterNet is proposed which utilizes both spectral and spatial information of remote sensing images. In addition, an end-to-end structure that integrates feature extraction, band expansion, and Chl-a estimation into the neural network leads to an efficient and effective Chl-a concentration retrieval. In experiments, Sentinel-3 images with the same acquisition days of in situ measurements over Laguna Lake in the Philippines were used to train and evaluate WaterNet. The quantitative analyses show that the two-stage training is more likely than the one-stage training to reach the global optimum in the optimization, and WaterNet with two-stage training outperforms, in terms of estimation accuracy, related ANN-based and band-combination-based Chl-a concentration models.

show abstract

“…The absolute method converts digital numbers or the top of the atmospheric reflectance of the satellite images to the surface reflectance [6]- [10]. By contrast, the relative method transforms the digital numbers or the top of the atmospheric reflectance of the images to a common level, thereby minimizing the radiometric differences among images [2], [11]- [18]. The advantage of the relative radiometric correction [or relative radiometric normalization (RRN)] over the absolute method is that such requirements as atmospheric correction model and in situ ground measurements can be avoided.…”

Section: Introductionmentioning

confidence: 99%

“…This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0/ Several studies [11], [19], [24], [25] addressed the issue of nonlinear radiometric normalization for bitemporal images with significant land-cover changes or for cross-sensor images based on the nonlinear assumption. The radiometric differences between images are considered nonlinear and kernel CCA (KCCA) is utilized to extract PIFs by projecting images into a high-dimensional feature space in which linearity exists in the projected data.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Canonical Correlation Analysis and Regression for Radiometric Normalization of Cross-Sensor Satellite Imagery

Denaro

Lin

2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Radiometric normalization is a fundamental preprocessing step for the analysis of multitemporal and multisensor satellite images. Some of the previous radiometric normalization studies addressed the elimination of spectral differences between bitemporal or cross-sensor images by performing canonical correlation analysis (CCA) or its generalization called kernel CCA (KCCA). The KCCA-based normalization methods, which assume that the relation between at-sensor radiances is spatially nonlinear, can successfully extract pseudoinvariant features (PIFs) for bitemporal images with nonlinear differences caused by seasonal variation and for bitemporal images acquired by different sensors with different spectral centers and bandwidths of spectral bands. However, these methods did not consider the problems of high computation and storage costs induced by the huge size of kernel matrices and the overfitting problem caused by nonlinear regression, making the methods infeasible for satellite images of large sizes. To solve these problems, a hybrid CCA with hybrid regression model is proposed, which can preserve the characteristics of nonlinear CCA and regression while reducing time and space complexity and solving overfitting problems. Cross-sensor images acquired by Landsat-7 Enhanced Thematic Mapper Plus and Landsat-8 Operational Land Imager sensors were used to evaluate the proposed method. Experimental results demonstrate the superiority of the proposed method to the related CCA-based methods in terms of computational performance and PIF quality.

show abstract

Pseudoinvariant feature selection for cross-sensor optical satellite images

Cited by 5 publications

References 24 publications

Hybrid Canonical Correlation Analysis and Regression for Radiometric Normalization of Cross-Sensor Satellite Images

Hybrid Canonical Correlation Analysis and Regression for Radiometric Normalization of Cross-Sensor Satellite Images

WaterNet: A Convolutional Neural Network for Chlorophyll-a Concentration Retrieval

Hybrid Canonical Correlation Analysis and Regression for Radiometric Normalization of Cross-Sensor Satellite Imagery

Contact Info

Product

Resources

About