Performance evaluation of image fusion techniques and implementation of new fusion technique for remote sensing satellite data

Author:

Lawrance N.A.1,Shiny Angel T.S.2

Affiliation:

1. Research scholar, Computer Science Engineering, SRM Institute of Science and Technology, Tamilnadu, India

2. Computer Science Engineering, SRM Institute of Science and Technology, Tamilnadu, India

Abstract

The technique of integrating images from two or more sensors that were taken from the same place or the same object is known as image fusion. The goal is to get more spectral and spatial information from the combined image as a whole than from the individual images. It is required to fuse the images in order to improve the spatial and spectral quality of both panchromatic and multispectral images. This study introduces a novel method for fusing remote sensing images that combines L0 smoothing, NSCT (Non-subsampled Contourlet Transform), SR (Sparse Representation), and MAR (Max absolute rule). The multispectral and panchromatic images are initially divided into lower and higher frequency components using the L0 smoothing filter as the method of fusion. The fusion process is then carried out, utilising a technique that combines NSCT and SR to fuse low-frequency components. Similar to this, the Max-absolute fusion rule is used to fuse high-frequency components. In conclusion, the disintegration of fused low-frequency and high-frequency data yields the final image. Our method yields an enhanced outcome in terms of the correlation coefficient, Entropy, spatial frequency, and fusion of mutual information for both the term of picture quality enhancement and visual evaluation. This suggested approach produces superior outcomes after execution. This study makes use of the Landsat-7ETM+, IKONOS, and Quick Bird datasets. Different satellites are used to take each image. There have been two examples of each image used. In comparison to previous Traditional Methods, the proposed image fusion techniques’ output has a quality that is more than 20% higher.

Publisher

IOS Press

Subject

Artificial Intelligence,General Engineering,Statistics and Probability

Reference25 articles.

1. A new multi-spectral feature level image fusion method for human interpretation;Leviner;Infrared Physics & Technology,2009

2. Joseph D. and Jemima T. , Jebaseeli, A Survey Of Fusion Of Remote Sensing Images To Avoid Spectral Distortion, International Journal of Engineering Research & Technology (IJERT) 1(8) (2012), October –2012 ISSN: 2278-0181..

3. Edge detection in multispectral images;Cumani;CVGIP: Graphical Models and Image Processing,1991

4. A note on the gradient of a multi-image;Di Zenzo;Comput Vision Graphics Image Processing,1986

5. Anisotropic diffusion of multivalued images with applications to color filtering;Sapiro;IEEE Trans Image Processing,1996

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Landscape Planning and Design Based on E Cognition High-resolution Remote Sensing Image;2023 International Conference on Intelligent Sensing and Industrial Automation;2023-12-09

2. CS n Net: A Remote Sensing Detection Network Breaking the Second-Order Limitation of Transformers With Recursive Convolutions;IEEE Transactions on Geoscience and Remote Sensing;2023

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3