High-precision moving target imaging and recognition method based on multi-target tracking

Abstract

The invention discloses a high-precision moving target imaging and recognition method based on target tracking. The method comprises the following steps: acquiring a SAR video by an SAR platform working in a bunching mode; using the Probability Hypothesis Density multi-target tracking method to perform tracking, and estimating motion parameters of moving targets; using the acquired motion parameters of the moving targets to correct a Doppler imaging coefficient, and acquiring SAR images that are accurately imaged after defocusing and displacement; and detecting and recognizing the moving targets in the acquired accurate SAR images. The technical effects of the method are that the motion parameters of the moving targets in the SAR video can be acquired through the multi-target tracking method in the video, the Doppler imaging coefficient and the problems of defocusing and offsetting in the images are corrected according to the acquired motion parameters of the moving targets so as to obtain high-precision images; and a support is provided for high-precision recognition.

Description

technical field [0001] The invention belongs to the field of synthetic aperture radar target recognition, in particular to a high-precision moving target imaging and recognition method based on multi-target tracking. Background technique [0002] At present, SAR (Synthetic Aperture Radar; Synthetic Aperture Radar) target recognition technology mainly relies on two technologies: the imaging quality of SAR images and the target recognition algorithm in SAR images. With the rapid development of machine learning including deep learning algorithms, SAR target recognition algorithms are becoming more and more mature, such as target recognition methods based on traditional machine learning, through the extraction of SAR target features, training classifiers such as SVM, so that different features of the target Target recognition; in recent years, with the gradual improvement of computing power, it has become possible to use deep learning methods to detect and recognize targets. Com...

AI Technical Summary

Problems solved by technology

The traditional method of obtaining motion parameters of a moving target includes using a multi-channel SAR platform to image the same target area separately, and estimating the target motion parameters through the results of multiple imaging. Meet the needs of the system to obtain the motion parameters of moving targets

Can not meet the needs of accurate identification

Images