The Statistical methods of Pixel-Based Image Fusion Techniques

TL;DR

This paper compares various statistical image fusion techniques for remote sensing, evaluating their effectiveness in producing high-quality, high-resolution multispectral images from satellite data.

Contribution

It introduces a comparative analysis of multiple statistical image fusion methods and evaluates their performance using various quantitative quality metrics.

Findings

Local Mean and Variance Matching (LMVM) performs best among the tested methods.

Regression Variable Substitution (RVS) shows significant improvement in image quality.

Evaluation metrics effectively quantify the degree of information enhancement in fused images.

Abstract

There are many image fusion methods that can be used to produce high-resolution mutlispectral images from a high-resolution panchromatic (PAN) image and low-resolution multispectral (MS) of remote sensed images. This paper attempts to undertake the study of image fusion techniques with different Statistical techniques for image fusion as Local Mean Matching (LMM), Local Mean and Variance Matching (LMVM), Regression variable substitution (RVS), Local Correlation Modeling (LCM) and they are compared with one another so as to choose the best technique, that can be applied on multi-resolution satellite images. This paper also devotes to concentrate on the analytical techniques for evaluating the quality of image fusion (F) by using various methods including Standard Deviation (SD), Entropy(En), Correlation Coefficient (CC), Signal-to Noise Ratio (SNR), Normalization Root Mean Square Error (NRMSE) and Deviation Index (DI) to estimate the quality and degree of information improvement of a fused image quantitatively.