Radar Target Range Profile Recognition Method Based on Kernel Discriminant Local Tangent Space Arrangement

Abstract

The invention discloses a radar target range image recognition method based on nuclear identification of local tangent space arrangement, which comprises the following steps: acquiring a number of training range images whose target category is known and a test range image of the target category to be identified; preprocessing Obtained training range images and test range images; based on the local tangent space reconstruction error minimization and inter-class scattering maximization criteria, the mapping matrix V from the high-dimensional range image space to the low-dimensional feature space is obtained; the training range image and the test range image are extracted The feature of the distance image: y=VTk, wherein, VT is the transposition of the mapping matrix V, and k is the kernel vector of any training distance image or test distance image; adopt the nearest neighbor method to compare the features of the test distance image and the training distance image, Classify each test range image to be recognized into the target category to which the nearest training range image belongs.

Description

technical field [0001] The invention relates to the field of radar target recognition, in particular to a radar target range profile recognition method based on kernel discrimination local tangent space arrangement. Background technique [0002] At present, many methods related to manifold learning theory have been successfully applied in the field of radar target recognition. Local Tangent Space Arrangement (LTSA) is one of the classic manifold learning methods, which directly obtains the low-dimensional projection of high-dimensional data sets. Coordinates, when a new sample arrives, only the new sample is added to the old sample set, and then the new low-dimensional projection coordinates are recalculated, which greatly limits its application in the field of target recognition. [0003] In response to the shortcomings of LTSA, a linear local tangent space arrangement (LLTSA) method was proposed, which still has common defects with LTSA. They only focus on retaining the lo...

AI Technical Summary

Problems solved by technology

[0002] At present, many methods related to manifold learning theory have been successfully applied in the field of radar target recognition. Local Tangent Space Arrangement (LTSA) is one of the classic manifold learning methods, which directly obtains the low-dimensional projection of high-dimensional data sets. Coordinates, when a new sample arrives, only the new sample is added to the old sample set, and then the new low-dimensional projection coordinates are recalculated, which greatly limits its application in the field of target recognition

[0003] In response to the shortcomings of LTSA, a linear local tangent space arrangement (LLTSA) method was proposed, which still has common defects with LTSA. They only focus on retaining the local manifold structure between samples, while ignoring the category information of samples. This will affect the recognition performance to a certain extent

Furthermore, LLTSA is a linear method and has very limited learning capabilities for data with typically nonlinear characteristics such as radar target high-resolution distances

[0004] For nonlinear problems, the kernel method is undoubtedly a good solution. Classic kernel methods such as KPCA and GDA have been successfully applied to radar target high-resolution range image recognition, but both GDA and KPCA use global learning methods. The local structural features between samples are ignored, and their ability to solve the problem of pose sensitivity of high-resolution range images is very limited

Images