SAR (Synthesized Aperture Radar) image target detection method based on zone markers and grey statistics

Abstract

The invention discloses an SAR (Synthesized Aperture Radar) image target detection method based on zone markers and grey statistics. An artificial target potential zone thoroughly including all the artificial targets in the original SAR image is detected when independent of prior information such as target shapes, target characteristics and background characteristics and the like by using the structural information of the original SAR image extracted from a Primal Sketch model, the grey information of the original SAR image and the characteristic that the pixels of the SAR artificial target zone are distributed in an alternately dark and bright way are made the best of, a false alarm target zone is effectively removed in combination with an OTSU (maximum between-class variance) image thresholding algorithm, and the false alarm rate of an artificial target detection result is reduced; and the artificial targets are accurately positioned in the target zone, the technical problems of the SAR image target detection with high false alarm rate and low possibility of accurate positioning of the artificial targets in the target zone are solved, and the processing speed is quick. The SAR image target detection method can be applied to the target detection in the field of SAR image processing and computer vision.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a SAR image target detection method, in particular to a SAR image target detection method based on area marking and grayscale statistics, which can be used for target detection in the fields of SAR image processing and computer vision. Background technique [0002] The main task of target detection is to determine the position of the target of interest and realize the separation of the target from the background. The methods of target detection can be divided into two categories: single-frame image target detection and multi-frame sequence image target detection. The current target detection methods are generally limited to a certain application environment, and the effectiveness of the target detection method depends on the prior knowledge of the target characteristics, background characteristics and application environment, and the quality of the detection results depend...

AI Technical Summary

Problems solved by technology

[0005] Although the above method can get rid of the dependence on the prior information of the image, and only use the structural information of the SAR image to detect the suspected artificial target area in the image more thoroughly and quickly, but because the image features used by the detection method are relatively single, the detection The detected target area set contains more false alarm targets, and when the false alarm targets are eliminated in the post-processing, the detection method still only uses means and methods to reflect image structure information such as regularity and regularity ratio, which cannot be effective. Eliminate the false alarm target area; and when locating the potential area of ​​artificial targets, this method simply determines the final area range through the coordinates of the line segments in the obtained regular line segment set, resulting in more natural targets in the extracted target area information, which mainly has the following defects:

[0006] 1) The false alarm rate of the target detection result is high, and the detected artificial target potential area set contains more natural target areas such as forests and fields, which is not conducive to the subsequent processing of the image, such as accurate artificial target recognition;

[0007] 2) There is no artificial target positioning in the target area, and the detected target area contains a large proportion of natural target information such as forests, fields, and waters; the artificial target positioning is not accurate, which is not conducive to practical applications, such as precise search of targets and other applications

Images