LANDSAT satellite image fusion metric assessment

DOIResolve DOI:
AuthorSearch for: ; Search for:
Proceedings titleNational Aerospace and Electronics Conference, Proceedings of the IEEE
Conference2011 IEEE National Aerospace and Electronics Conference, NAECON 2011, 20 July 2011 through 22 July 2011, Fairborn, OH
Article number6183109
Pages237244; # of pages: 8
SubjectBiomedical images; Electro-optical; Entropy-based; Evaluation; Fused images; Image fusion methods; Image fusion metrics; Infrared imagery; Land cover; LANDSAT; Landsat imagery; LANDSAT satellite images; Metrics; Multi-spectral; Night vision; Structural similarity; Diagnosis; Image fusion; Vision; Satellite imagery
AbstractImage fusion is an important component of many applications such as inspection, night vision, medical diagnosis, and electro-optical (multispectral) targeting. In this paper, we build upon our previous results for image fusion metrics by applying the methods to satellite imagery versus night vision (visual and infrared imagery) and single-metric biomedical image fusion analysis. Multispectral examples include satellite imagery for land-cover analysis. In this paper, we explore a variety of metrics that have been used to quantify the performance of the fused image products. The exhaustive conclusive analysis over all possibilities is not realizable, so in this paper we group the various metrics into categories and demonstrate an application of the metrics to satellite LANDSAT imagery using an entropy-based image fusion method. From the many metrics analyzed, we found the Image Structural Similarity Based (ISSB) metrics are most useful. © 2011 IEEE.
Publication date
AffiliationNational Research Council Canada (NRC-CNRC)
Peer reviewedYes
NPARC number21271645
Export citationExport as RIS
Report a correctionReport a correction
Record identifier32697f21-6785-4305-bb45-17ec04ae8687
Record created2014-03-24
Record modified2016-05-09
Bookmark and share
  • Share this page with Facebook (Opens in a new window)
  • Share this page with Twitter (Opens in a new window)
  • Share this page with Google+ (Opens in a new window)
  • Share this page with Delicious (Opens in a new window)