Radar target-range image non-linear projection recognition method

Abstract

The present invention provides a method for distinguishing nonlinear projection of one-dimensional distance image which belongs to field of radar target recognition. Random two sorts targets in multiple targets are classified into one group, one-dimensional distance image of each group target is processed nonlinear transform and mapped to high-dimensional linear characteristic space, a nonlinear projection plane transform matrix is build in high-dimensional linear characteristic space, characteristic is obtained and classified by minimum-distance criterion, and the sorts input target belonged to is determined finally by voting mechanism. Steps: random two sorts of targets in training target are matched into one group; matrix WAlpha is determined by kernel function and radar target one-dimensional distance image training vector matrix Pi and (K)ij in the group; nonlinear projection vector of input target one-dimensional distance image xt is determined; Euclidean distance between nonlinear projection vector and library template vector is determined; sort number of input target one-dimensional distance image is determined; sort number with most stat votes is sort belonged to input target. The present method can improve target identification performance efficiently.

Description

Technical field [0001] The invention belongs to the field of radar target recognition, relates to a one-dimensional range image recognition method of multiple types of radar targets, in particular to a nonlinear projection recognition method of a radar target one-dimensional range image. Background technique [0002] Compared with the radar cross-sectional area of ​​the target obtained by the low-resolution radar, the high-resolution radar can obtain the one-dimensional range image information of the target, and the one-dimensional range image reflects the distribution of the target scattering points on the radar line of sight, which can provide more More information that is beneficial to target classification. [0003] The classification method based on subspace is a classic statistical pattern recognition method, which is widely used in face recognition, image recognition and other fields. In radar target recognition, the classification method based on subspace is also ve...

AI Technical Summary

Problems solved by technology

[0006] However, since these subspace methods use the one-dimensional range image sample set of the training target to only establish a common transformation matrix, when the number of target categories is large, the feature areas to which different targets belong also increase, and the classification of the target Boundaries can become very complex and blurred, resulting in poor object recognition performance

[0007] In addition, due to the obvious nonlinear features in the 1D range profile distribution of radar targets, there is still room for further improvement in the recognition performance of these linear subspace methods

Images