Pseudoinvariant Feature Selection Using Multitemporal MAD for Optical Satellite Images

Lin, Bor-Luh; Wang, Zhijia; Syariz, Muhammad Aldila; Denaro, Lino Garda; Lin, Chao-Hung

doi:10.1109/lgrs.2019.2899969

Cited by 6 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Section 4.1, we discussed the influence of polygon size. Integrating the pseudo−invariant points with a suitable polygon size, as demonstrated by Kim, Pyeon [38], Zhou, Liu [24], and Lin, Wang [25], is a practical way to automatically select polygon features and will be included in future research and monitoring.…”

Section: Limitations Of Polygon Feature−based Normalization Algorithmsmentioning

confidence: 99%

See 1 more Smart Citation

Radiometric Normalization Using a Pseudo−Invariant Polygon Features−Based Algorithm with Contemporaneous Sentinel−2A and Landsat−8 OLI Imagery

Chen

Lian

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

As sensor parameters and atmospheric conditions create uncertainties for at−sensor radiation detection, radiometric consistency among satellite images is difficult to achieve. Relative radiometric normalization is a method that can improve multi−image consistency with accurate pseudo−invariant features (PIFs), especially over large areas or long time series satellite images. Although there are algorithms that manually or automatically select PIFs, the spatial mismatch of satellite images can affect PIF extraction, particularly with artificial pixels. To alleviate this problem, we proposed to use Landsat−8 OLI as the reference image and Sentinel−2A as the subject image, to apply pseudo−invariant features−based algorithms with polygon features through the single−band and multiple−band regression. Compared to pseudo−invariant point features, hyperspectral library, and histogram matching approaches, the results demonstrate the superiority of the proposed algorithms with correlation coefficients of 0.9948 and 0.9945, and an RMSE of 0.0097 and 0.0095 with multiple− and single−band regression, respectively. We also found more accurate linear fitting and better shape matching through band scattering and reflectance frequency analysis. The proposed algorithms are a significant improvement in radiometric normalization, within artificial pixels, achieving spectral signature consistency.

show abstract

Section: Limitations Of Polygon Feature−based Normalization Algorithmsmentioning

confidence: 99%

“…Automatically extracting PIFs makes the radiometric correction processing more efficient and has been proposed by several researchers [24][25][26][27][28]. In these studies, PIFs are extracted automatically and sorted into a radiometric control set, radiometric control points, no−change set, and unchanged pixels [29][30][31][32].…”

Section: Introductionmentioning

confidence: 99%

Radiometric Normalization Using a Pseudo−Invariant Polygon Features−Based Algorithm with Contemporaneous Sentinel−2A and Landsat−8 OLI Imagery

Chen

Lian

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The next step in the image-processing pipeline is the extraction of pseudo-invariant features (PIFs). These PIFs refer to stable features on the Earth's surface that remain relatively unchanged over time, and they can be used to normalize remote-sensing data [31]. Examples of PIFs include urban areas, roads, and bare soil, which tend to have consistent surface-reflectance values over time.…”

Section: Pif Extractionmentioning

confidence: 99%

Relaxation-Based Radiometric Normalization for Multitemporal Cross-Sensor Satellite Images

Ryadi

Syariz

Lin

2023

Sensors

Self Cite

View full text Add to dashboard Cite

Multitemporal cross-sensor imagery is fundamental for the monitoring of the Earth’s surface over time. However, these data often lack visual consistency because of variations in the atmospheric and surface conditions, making it challenging to compare and analyze images. Various image-normalization methods have been proposed to address this issue, such as histogram matching and linear regression using iteratively reweighted multivariate alteration detection (IR-MAD). However, these methods have limitations in their ability to maintain important features and their requirement of reference images, which may not be available or may not adequately represent the target images. To overcome these limitations, a relaxation-based algorithm for satellite-image normalization is proposed. The algorithm iteratively adjusts the radiometric values of images by updating the normalization parameters (slope (α) and intercept (β)) until a desired level of consistency is reached. This method was tested on multitemporal cross-sensor-image datasets and showed significant improvements in radiometric consistency compared to other methods. The proposed relaxation algorithm outperformed IR-MAD and the original images in reducing radiometric inconsistencies, maintaining important features, and improving the accuracy (MAE = 2.3; RMSE = 2.8) and consistency of the surface-reflectance values (R2 = 87.56%; Euclidean distance = 2.11; spectral angle mapper = 12.60).

show abstract

“…In addition to the normalized-KMAD, the spectral angle (SA) suggested by [22], which measures the difference between the spectral signatures of the corresponding pixels in the bitemporal images, is introduced as another weight. By integrating these two weights, the weighting scheme is formulated as follows:…”

Section: B Hybrid Ccamentioning

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 Using Multitemporal MAD for Optical Satellite Images

Cited by 6 publications

References 13 publications

Radiometric Normalization Using a Pseudo−Invariant Polygon Features−Based Algorithm with Contemporaneous Sentinel−2A and Landsat−8 OLI Imagery

Radiometric Normalization Using a Pseudo−Invariant Polygon Features−Based Algorithm with Contemporaneous Sentinel−2A and Landsat−8 OLI Imagery

Relaxation-Based Radiometric Normalization for Multitemporal Cross-Sensor Satellite Images

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

Contact Info

Product

Resources

About