Ground target classification method based on stochastic forest and data rejection

Abstract

The invention discloses a ground target classification method based on a random forest and data rejection, which comprises the following steps: (1) preprocessing a training sample set; (2) extractinga training feature matrix; (3) training a random forest classifier; (4) preprocessing the test sample; (5) extracting test feature vector; (6) calculating the output probability vector of the ground target; (7), judging whether that t sample is rejected or not; (8) if the judgment is rejected, taking the test sample as the echo signal without the fretting characteristic of the target; (9) if the judgment is not rejected, outputting the corresponding class of the maximum value in the probability vector as the ground target classification result of the test sample. The method rejects the judgment of clutter, deceptive interference and non-fretting target signal, improves the classification and recognition rate of ground moving target, and adopts a classifier with parallel processing abilityto improve the real-time performance of the method.

Description

technical field [0001] The invention belongs to the technical field of communication, and further relates to a ground target classification method based on random forest and data rejection in the technical field of radar signal processing. The invention can classify different vehicle targets and human targets moving on the ground in real time in the environment with clutter and deceptive interference. Background technique [0002] In radar ground target classification, radar returns may contain clutter, deceptive jamming, and non-jittering ground target signals. For clutter and deceptive interference, the classification method should refuse to classify; and for the target signal without micro-motion, because the effective micro-motion features required for classification cannot be extracted, the classification method cannot effectively and correctly classify. How to reasonably and effectively remove clutter, deceptive interference and target signals without micro-motion is ...

AI Technical Summary

Problems solved by technology

Although this method can process radar signals with high signal-to-noise ratio and identify tracked vehicles and wheeled vehicles, there are still shortcomings in this method: since this method only directly compares the observed Doppler spectrum with the wheeled vehicle Doppler spectrum template, tracked vehicle Doppler spectrum template distance, so in the environment with clutter and deceptive interference, clutter and deceptive interference will still be identified as vehicle targets; It is randomly classified, which causes misjudgment of the classification method and reduces the recognition rate

Although this method can process and classify radar signals of ground targets, there are still shortcomings in this method: since this method uses a support vector machine classifier, the support vector machine itself is a classifier with a serial structure, so it supports Vector machine classifiers require more processing time, which leads to poor real-time performance of the method

Images