Remote object recognition by analysis of surface structure

摘要

We present a new algorithm for the discrimination of remote objects by their surface structure. Starting from a range-azimuth function (RAF), 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 RAF to discriminate between classes. While 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 the sign change method.