Multisensor fusion of satellite images for urban information extraction using pseudo-Wigner distribution

Abstract

A new algorithm has been proposed to fuse high-resolution panchromatic image with a low-resolution multispectral image of World View-2, based on pseudo-Wigner distribution (PWD). Spatial-frequency method, particularly PWD, provides pixel-wise analysis, shift invariant as well as characterization of local spectral properties of nonstationary image, which is indispensable for image fusion. The input images are re-sampled using nearest neighbor (NN), bicubic spline (BCS), and cubic convolution (CC). The comparison of performance of the proposed method and the discrete wavelet transform (DWT) has been evaluated using root mean square error, peak signal-to-noise ratio, correlation coefficient index. It has been found that PWD fusion technique outperforms DWT fusion technique using average as well as maximum selection rule, both quantitatively and qualitatively. All three resampling methods-the NN, the BCS, and the CC-do not have any significant effect on the final visual appearance of the fused images.Rajput, Ghosh, and Kumar: Multisensor fusion of satellite images for urban information extraction.

Permuted Spectral and Permuted Spectral-Spatial CNN Models for PolSAR-Multispectral Data based Land Cover Classification

“…Out of the 11 bands, 6 bands namely blue, green, red, near infrared, short wave infrared 1, and short wave infrared 2 are selected for the study. These selected bands are pan sharpened as explained in Gillespie, Kahle, and Walker (1987) and then resampled to the PALSAR-2 PolSAR data spatial resolution of 6 meters using the "bicubic spline" interpolation method (Rajput, Ghosh, and Kumar 2014). A false colour composite using the selected multispectral bands is displayed in Figure 2…”

Pan-sharpening Using Spatial-frequency Method

“…PWD is ideally suited for representing a nonstationary image in the spatial frequency domain and is carried out by adapting the fast Fourier transform (FFT) algorithm. The significant properties of PWD motivate its use in the field of image processing, especially for the fusion of satellite images [30,31]. These properties are as follows:…”

“…Thus, the goal of pan-sharpening is to produce pan-sharpened images with the highest spectral fidelity possible, as the importance of such images in various applications, ranging from land use/land cover classification to road extraction. Therefore, preserving the spectral information of the original MS images in the pansharpened images is of great importance [31][32][33]. Therefore, an attempt to utilize the concept of pseudo-Wigner distribution (PWD) for the pan-sharpening of highresolution PAN image with a low-resolution MS image has been introduced.…”