Crosswind measurements through pattern recognition techniques

摘要

An optical device for measuring crosswinds by pattern recognition techniques is described. The device includes a minicomputer to process observed spectral profiles. In the training phase spectral features, which are weakly intercorrelated but strongly correlated with the crosswind, are selected and classified with known winds. This data is stored in the computer. During the execution phase, the observed spectral features are compared with the previously stored classifications to yield a best estimate of the crosswind.