SAR target recognition method based on sparse least squares support vector machine

Abstract

The invention discloses a SAR target recognition method based on a sparse least squares support vector machine, which belongs to the technical field of image processing and mainly solves the problem that the existing method need a long time for SAR target recognition. The realization process comprises the following steps of: firstly respectively implementing feature extraction to the selected target images with known classification information and images to be recognized to obtain training samples and test samples; and then applying iterative training to the training samples by using the combination of incremental learning method and reversal learning method to select a sparse support vector set and obtain a Lagrange multiplier and deflection corresponding to the support vectors in the set; and finally using a classification decision function to recognize the test samples according to the obtained support vector set, the Lagrange multiplier and deflection corresponding to the support vectors. The invention has the advantage of shortening recognition time under the condition of equivalent recognition precision and can be used for detection and recognition of SAR target.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to target identification, and can be applied to the identification of Synthetic Aperture Radar (SAR) targets. Background technique [0002] Compared with ordinary optical images, SAR images not only have all-weather and all-weather working capabilities, but also have rich characteristic signals, containing various information such as amplitude, phase and polarization. Due to its unique advantages in earth observation in the field of earth science remote sensing, as well as its broad application prospects in military and civilian fields, target recognition technology based on high-resolution two-dimensional SAR images has attracted more and more attention. Generally, the SAR image interpretation system with the ultimate goal of target recognition mainly includes a preprocessing module with coherent speckle suppression, edge extraction, and region segmentation as the main content, ...

AI Technical Summary

Problems solved by technology

However, due to the addition of the quadratic loss function, the Lagrange multiplier obtained by the Karush-Kuhn-Tucker and KKT conditions is proportional to the error, so that almost all samples will be saved as support vectors, resulting in The lack of sparsity leads to an increase in the recognition time of SAR target recognition

Images