Method for identifying SAR target under shielding conditions

Abstract

The invention discloses a method for identifying an SAR target under shielding conditions. The method mainly solves the problem that the identification performance of an existing identification technology is lowered under shielding conditions. The method is achieved through the steps that logarithmic transformation and median filtering are performed on a training image sequentially, image column vectorization is performed, premultiplication random matrix dimensionality reduction and energy normalization are performed on the training image as pre-processing, and pre-processed data are used for constructing a data dictionary D; logarithmic transformation, median filtering and image column vectorization are performed on the image to be tested sequentially, the premultiplication random matrix dimensionality reduction and energy normalization are performed on the image to be tested as pre-processing, and a non-negative sparse representation is constructed through test data after the pre-processing and the data dictionary D; a non-negative sparse decomposition coefficient is acquired after optimization, and various reconstruction errors are calculated through the non-negative sparse decomposition coefficient; a target identification result is acquired according to the minimum reconstruction error criterion. The method has the advantages of being high in identification rate and stable in performance even when the target to be tested is shielded, and is applicable to SAR target identification when the target may be shielded.

Description

technical field [0001] The invention belongs to the technical field of radar automatic target recognition, and in particular relates to a SAR target recognition method in the case of occlusion. The method is suitable for SAR target recognition in the case that the target to be recognized may be occluded. Background technique [0002] Synthetic aperture radar (SAR) has the characteristics of all-weather, all-time, high resolution and strong penetrating power, and has become an important means of earth observation and military reconnaissance. Since the development of radar imaging technology in the 1950s, the technology has been continuously matured and the imaging resolution has been continuously improved, which makes the automatic target recognition (ATR) through SAR images receive more and more attention. [0003] The existing SAR image automatic target recognition methods usually adopt the three-level processing flow proposed by the Lincoln Laboratory of the United States....

AI Technical Summary

Problems solved by technology

Existing recognition methods that use segmentation or feature extraction are greatly affected by this occlusion, resulting in a lower recognition rate

Images