Abstract

We present a new algorithm for the discrimination of remote objects by their surface structure. Starting from a range-azimuth profile function, we formulate a range-azimuth matrix whose largest eigenvalues are used as discriminating features to separate object classes. A simpler, competing algorithm uses the number of sign changes in the range-azimuth profile function to discriminate among classes. Whereas both algorithms work well on noiseless data, an experiment involving real data shows that the eigenvalue method is far more robust with respect to noise than is the sign-change method. Two well-known methods based on surface structure, variance, and fractal dimension were also tested on real data. Neither method furnished the aspect invariance and the discriminability of the eigenvalue method.

© 1995 Optical Society of America

Multiscale fractal theory and object characterization

T. Peli
J. Opt. Soc. Am. A 7(6) 1101-1112 (1990)

Bispectral analysis of the wavelength dependence of speckle: remote sensing of object shape

Lyle G. Shirley and Peter A. Lo
J. Opt. Soc. Am. A 11(3) 1025-1046 (1994)

Efficient implementation of rigorous coupled-wave analysis for surface-relief gratings

Song Peng and G. Michael Morris
J. Opt. Soc. Am. A 12(5) 1087-1096 (1995)

Illumination-invariant recognition of texture in color images

Glenn Healey and Lizhi Wang
J. Opt. Soc. Am. A 12(9) 1877-1883 (1995)

Multi-class remote sensing object recognition based on discriminative sparse representation

Xin Wang, Siqiu Shen, Chen Ning, Fengchen Huang, and Hongmin Gao
Appl. Opt. 55(6) 1381-1394 (2016)