SAR target recognition method based on non-negative least square sparse representation

Abstract

The invention provides an SAR target recognition method based on non-negative least square sparse representation. According to the method, a frequency spectrum characteristic based on an SAR image is taken as a recognition characteristic, a test sample is projected on a training set, non-negative constraint is added in a sparse projection process, influence of non-practical mathematic description on radar target recognition caused by positive and negative sparse coefficients in sparse representation can be avoided, moreover, a low dimension structure of a target in a high dimension space can be effectively reflected through a sparse solution, category of a test sample can be determined through a sparse reconstruction process, radar target recognition is realized, the recognition rate is improved, moreover, azimuth estimation on SAR image targets and influence of factors such as defocusing or a signal to noise ratio on target recognition can be avoided, excellent noise robustness is realized, radar target recognition accuracy can be effectively improved.

Description

technical field [0001] The invention relates to the technical field of radar target recognition, in particular to a SAR target recognition method based on non-negative least square sparse representation. Background technique [0002] Synthetic Aperture Radar (SAR) technology is a pulse radar technology that uses mobile radar mounted on satellites or aircraft to obtain radar target images in high-precision geographic areas. Synthetic Aperture Radar Auto Targets Recognition (SAR-ATR) has important application value in many geographic information analysis technology fields. [0003] The recognition performance of automatic radar target recognition is mainly determined by feature extraction and recognition algorithms. In terms of feature extraction, better feature extraction can not only reduce the dimensionality of data recognition, but also retain as much effective information as possible for recognition. Due to some unique characteristics of SAR images, such as specular ref...

AI Technical Summary

Problems solved by technology

[0005] In view of the above-mentioned problems existing in the prior art, in order to solve the problem that the SAR image target recognition in the prior art needs to estimate the target azimuth angle and the recognition accuracy is limited, the present invention provides a SAR based on non-negative least squares sparse representation Target recognition method, the radar target recognition method obtains sparse vectors by projecting test samples onto the training set, and then determines the category of test samples through the sparse reconstruction process to realize the recognition of radar targets, and in the process of sparse projection By adding non-negative constraints, the results of projection reconstruction are more in line with the actual situation, and the obtained sparse solution will be more accurate and sparse, so that the recognition of radar targets does not need to rely on the target azimuth estimation of SAR images At the same time, it can avoid the interference caused by factors such as defocus or signal-to-noise ratio on target recognition, and improve the accuracy of SAR target recognition

Images