Automatic target recognition algorithm based on statistical dispersion of infrared multispectral image

Wěi Zhāng, Le-lin Cao, Chun-Feng Wu, Qingyu HouProceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE 2009 · DOI

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.
BibTeX
@inproceedings{zhang2009automatic,
  author = {Wěi Zhāng and Le-lin Cao and Chun-Feng Wu and Qingyu Hou},
  title = {{Automatic target recognition algorithm based on statistical dispersion of infrared multispectral image}},
  booktitle = {Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE},
  year = {2009},
  doi = {10.1117/12.836105},
}

Loading related content...

Figure