Share Email Print
cover

Proceedings Paper

Automatic target recognition algorithm based on statistical dispersion of infrared multispectral image
Author(s): Wei Zhang; Qing-yu Hou
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A novel automatic target recognition algorithm based on statistical dispersion of infrared multispectral images(SDOIMI) is proposed. Firstly, infrared multispectral characteristic matrix of the scenario is constructed based on infrared multispectral characteristic information (such as radiation intensity and spectral distribution etc.) of targets, background and decoys. Then the infrared multispectral characteristic matrix of targets is reconstructed after segmenting image by maximum distance method and fusing spatial and spectral information. Finally, an statistical dispersion of infrared multispectral images(SDOIMI) recognition criteria is formulated in terms of spectral radiation difference of interesting targets. In simulation, nine sub-bands multispectral images of real ship target and shipborne aerosol infrared decoy modulated by laser simulating ship geometry appearance are obtained via using spectral radiation curves. Digital simulation experiment result verifies that the algorithm is effective and feasible.

Paper Details

Date Published: 6 August 2009
PDF: 7 pages
Proc. SPIE 7383, International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications, 73833S (6 August 2009); doi: 10.1117/12.836105
Show Author Affiliations
Wei Zhang, Harbin Institute of Technology (China)
Qing-yu Hou, Harbin Institute of Technology (China)


Published in SPIE Proceedings Vol. 7383:
International Symposium on Photoelectronic Detection and Imaging 2009: Advances in Infrared Imaging and Applications

© SPIE. Terms of Use
Back to Top