Improvement of the Example-Regression-Based Super-Resolution Land Cover Mapping Algorithm

Abstract

Super-resolution mapping (SRM) is a method for generating a fine-resolution land cover map from coarse-resolution fraction images. Example-regression-based SRM algorithms can estimate a fine-resolution land cover map with detailed spatial information by learning land cover spatial patterns from available land cover maps. Existing example-regression-based SRM algorithms are sensitive to fraction errors, and the results often include many linear artifacts and speckles. To overcome these shortcomings, this study proposes an improved example-regression-based SRM algorithm. The objective function of the proposed SRM algorithm comprises three terms. The first term is used to minimize the difference between the fraction values of the estimated fineresolution land cover map and the input fraction values. The second term is used to maximize the class membership possibility values of the fine pixels in the result. The final term is used to make the result locally smooth. The proposed SRM algorithm is compared with several popular SRM algorithms using both synthetic and real fraction images. Experimental results indicate that the proposed SRM algorithm can produce results with less speckles and linear artifacts, more spatial details, smoother boundaries, and higher accuracies than the SRM results used for comparison.Index Terms-Example based, subpixel mapping (SPM), superresolution mapping (SRM), support vector regression (SVR).

Research on super-resolution reconstruction of remote sensing images: a comprehensive review

“…It has more detailed spatial information and higher accuracy on different spatial scales. Subsequently, Zhang et al 47 improved the method, which produced results with fewer spots and linear artifacts, more spatial details, smoother boundaries, and higher accuracy.…”

Süper Çözünürlük Yönteminin Uydu İmgelerinin Sınıflandırma Performansına Etkisi

“…In recent years, many new algorithms based on HR image reconstruction [2][3][4][5], instance-based [6][7][8], regression-based [9][10][11] and deep learning [12][13][14][15] have been proposed. One of the main approaches for single frame SR of the image is the interpolation of the image, in which the high frequency information is extracted from the low frequency image and the estimation is made for the detailed information in the first image [16].…”