SAR (synthetic aperture radar) target identification method based on nuclear sparse representation

Abstract

The invention discloses an SAR (synthetic aperture radar) target identification method based on nuclear sparse representation, mainly solving the problem of low error tolerance in the prior art. The method comprises the following realization steps: (1) respectively mapping a training sample matrix and a test sample to a nuclear space, randomly reducing the dimension of the mapped sample to the required dimension, and normalizing the dimension; (2) solving a reconstructed coefficient vector between the normalized test sample and the training sample matrix; and (3) solving the energy of the reconstructed coefficient of the test sample in each class, and substituting the energy into a class judging formula to obtain a final identification result. Compared with the prior art, the SAR target identification method is characterized by improving the error tolerance of the algorithm, so that the SAR target identification method has higher identification precision and high arithmetic speed in the SAR target identification application; and meanwhile, an application range is popularized to a low-dimensional sample, thus having better universality.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to SAR target recognition, and can be widely used in military and civilian applications. Background technique [0002] The research on SAR image processing is a comprehensive discipline that has only emerged in the past ten years. SAR is widely used in civil and military applications because of its all-weather and all-weather detection capabilities, and rich characteristic signals, which contain various information such as amplitude, phase and polarization. At present, the moving and stationary target acquisition and recognition plan proposed by the US Defense Advanced Research Projects Agency aims to develop the next generation of SAR target recognition system based on model vision. Uncertainty is modeled to provide a robust solution for object recognition in highly unconstrained scenarios. Therefore, the research on the processing method of the acquired SAR image is par...

AI Technical Summary

Problems solved by technology

However, since this method is a linear method and cannot achieve nonlinear feature representation, Zhang et al. proposed a kernel sparse representation method, which maps samples from the original space to the kernel space to solve the problem of nonlinear feature representation

However, in this method, since the reconstruction error criterion is used for classification, it is not fault-tolerant to noise, resulting in a decrease in classification accuracy.

Images