Title :
On classification of multispectral infrared image data
Author :
Cheung, Julian ; Ferris, David ; Kurz, Ludwik
Author_Institution :
Dept. of Electr. Eng., New York Inst. of Technol., NY, USA
fDate :
10/1/1997 12:00:00 AM
Abstract :
A detector is proposed that is based on a model in which the signal components consist of radiant thermal energy from either the small target or the intense, highly structured background. The resulting statistic is effective in enhancing the target and suppressing cluttered background. Estimation of the system parameters based on stochastic approximation techniques is presented. Simulation results demonstrate the practicality of the proposed detector
Keywords :
Gaussian distribution; approximation theory; clutter; image classification; infrared imaging; infrared spectra; iterative methods; parameter estimation; spectral analysis; stochastic processes; Gaussian distribution; IR detector; cluttered background suppression; iterative stochastic techniques; multispectral infrared image data classification; optimal likelihood ratio detector; radiance statistics; radiant energy; radiant thermal energy; sensor nois; signal components; simulation results; small target; statistic; stochastic approximation techniques; structured background; system parameter estimation; Infrared detectors; Infrared image sensors; Infrared imaging; Optical imaging; Remote monitoring; Sensor phenomena and characterization; Spatial resolution; Statistics; Stochastic systems; Temperature sensors;
Journal_Title :
Image Processing, IEEE Transactions on
