Statistical dictionary learning-based radar high range resolution profile target identification method

Abstract

The invention discloses a statistical dictionary learning-based radar high range resolution profile (HRRP) target identification method. The method comprises the steps of obtaining continuous HRRP original signals of T targets, and preprocessing the signals; dividing a main frame into two sub-frames according to a maximum probability difference algorithm, and obtaining an initialized statistical dictionary; configuring related parameters before training of the statistical dictionary; performing training to obtain an optimal dictionary and a transposed matrix; and performing test identificationclassification on the to-be-tested HRRP original signals by utilizing the transposed matrix. The method is especially applied to HRRP target identification under a low-signal-noise-ratio condition; and compared with a single statistical modeling and dictionary learning method, the method provided by the invention has better identification performance.

Description

Technical field [0001] The invention relates to radar technology, in particular to a radar high-resolution range image target recognition method based on statistical dictionary learning. Background technique [0002] Radar automatic target recognition technology is one of the important research directions of radar signal processing. The high resolution range profile (HRRP) is the amplitude waveform of the vector sum projected on the radar ray of the target scattered point echo obtained by the radar signal. Because HRRP can accurately reflect the physical structure information of the target itself, it is widely used in the fields of meteorology, aviation and target recognition. [0003] Target recognition based on radar high-resolution range profile belongs to the research category of pattern recognition theory and radar field. Therefore, radar HRRP target recognition involves many technical difficulties. Current domestic and foreign studies point out that azimuth sensitivity, tra...

AI Technical Summary

Problems solved by technology

(2) Translational sensitivity: Since most of the targets to be measured are in motion, the relative position of the radar target echo in the range window cannot be guaranteed, so translational sensitivity will appear in the process of intercepting the signal

Later, it was found that the uniform framing method could not describe the statistical characteristics of HRRP very well, so some related studies adopted the method of adaptively dividing the angle domain to improve the target recognition rate, but how to reasonably divide the target angle domain and extract robust features has not yet been solved. come up with effective solutions

Images