Resolution Improvement of Infrared Images Using Visible Image Information

Cited 7 time in webofscience Cited 0 time in scopus
  • Hit : 289
  • Download : 0
This letter presents a new framework for improving the spatial resolution of infrared (IR) images based on the high-resolution visible image information. Edge regions in an IR image, which have a strong correlation with the aligned edges in the visible image, are sharpened by using their high frequency patches, which are locally estimated from the visible image. The estimation is performed on the basis of intensity correlations between two images. In addition, in order to improve the resolution in the uncorrelated edge regions and the texture regions where visible image information is not available, we adopt learning-based and reconstruction-based super resolution algorithms, respectively. Experimental results demonstrate that the proposed algorithm improves the spatial resolution compared with the existing upsampling algorithms.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2011-10
Language
English
Article Type
Article
Keywords

REGISTRATION

Citation

IEEE SIGNAL PROCESSING LETTERS, v.18, no.10, pp.611 - 614

ISSN
1070-9908
URI
http://hdl.handle.net/10203/96330
Appears in Collection
EE-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.
This item is cited by other documents in WoS
⊙ Detail Information in WoSⓡ Click to see webofscience_button
⊙ Cited 7 items in WoS Click to see citing articles in records_button

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0