Sar classification method based on dense sar-sift and sparse coding

Abstract

The present invention disclosed a SAR classification method based on dense SAR‑Sift and sparse encoding. It mainly solves the problem that the existing feature extraction algorithm cannot effectively extract features from SAR images with similar spotted noise.The realization steps are: (1) Use the dense SAR‑sift to extract the local characteristics of the image; (2) Set the dictionary atomic number with the K‑Means cluster algorithm for the local characteristics of the cluster constructor; (3) the local characteristics of the local characteristicsThe sparse space encoding is characterized by the characteristic code; (4) the characteristic coding of the image performed the maximum pool of the airspace to obtain the characteristic vector of the image;Compared with the existing method, the invention can inhibit the effects of related spots noise, improve the category accuracy, and use a sparse space encoding method to accelerate the classification speed.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a synthetic aperture radar image target classification method based on dense synthetic aperture radar scale-invariant feature transformation SAR-SIFT (Synthetic ApertureRadar-Scale Invariant Feature Transform) and sparse coding synthesis Aperture radar SAR (Synthetic Aperture Radar) classification method, the invention can be used in the classification and identification of ground targets in SAR images. Background technique [0002] Synthetic aperture radar is a high-resolution imaging radar. Because of its all-weather and all-weather acquisition of battlefield intelligence and certain ground and vegetation penetration capabilities, it has become an important means of military reconnaissance and strike effect evaluation. How to integrate complex SAR Transforming image data into usable and effective information is a key issue in the current SAR image processing and ...

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that in the classification process of test data, the training data needs to be used as a dictionary to calculate the encoding of the test data. Usually, the number of training data is large, resulting in a very low encoding speed of the method.

The disadvantage of this method is that the scale-invariant feature conversion SIFT feature is affected by the coherent speckle noise in the SAR image, and cannot effectively extract the local features in the SAR image, resulting in a low classification accuracy of the method.

Images