K distribution and texture feature-based SAR (Synthetic Aperture Radar) image segmentation method

Abstract

The invention discloses a K distribution and texture feature-based SAR (Synthetic Aperture Radar) image segmentation method, which belongs to the technical field of image processing. The segmentation method comprises the following steps: intercepting category C training samples on an SAR image to be segmented; intercepting 100 training samples of 9*9 at a feature region; extracting feature parameters of the training samples by using a K distribution statistical model and a gray scale co-occurrence matrix; arranging each category of feature coefficients into a matrix, i.e., a dictionary of cth category targets; calculating the dictionary of each category of targets and arranging the dictionaries to form a global big dictionary in sequence according to the method; inputting the SAR image to be segmented, substituting each pixel point by 9*9 pixel points of a neighbor of the pixel point, and solving a feature coefficient inverse solution matrix operation of the pixel point to obtain weight a; making delta i (a), i=1, ellipsis, wherein C is a vector which only remains the coefficient corresponding to the cth category in a and enable zero setting of the rest coefficients; and calculating a residual error function and repeating the steps to obtain a segmentation result of each pixel point of the SAR image to be processed according to the fact that the minimum error function is a category label of the feature coefficients.

Description

Technical field [0001] The invention belongs to the field of image processing and relates to a method for SAR image feature extraction and SAR image segmentation. It is a SAR image segmentation method based on K distribution and texture features and can be applied to SAR image target recognition. Background technique [0002] Synthetic Aperture Radar SAR is a high-resolution radar system, also known as synthetic aperture radar, used in military, navigation, agriculture, geological prospecting, image matching guidance and many other fields. Compared with other remote sensing imaging systems and optical imaging systems, there are many differences. In terms of military target recognition, SAR images are widely used in the field of target detection, and SAR image segmentation is an important step from image processing to image interpretation, and is the basis for target classification and recognition. Essentially, the SAR image reflects the electromagnetic scattering characteristics...

AI Technical Summary

Problems solved by technology

Non-causal Markov random field parameter estimation is difficult and requires iteration; causal Markov random field is prone to directional block effects

This kind of method considers the physical statistical characteristics and prior probability distribution knowledge of SAR image, so the segmentation effect is improved compared with the segmentation method based on speckle suppression, but it does not fully exploit the global features and local texture features of SAR images.

The segmentation result has information loss on the details of the SAR image, and the direction information such as boundaries and edges is incomplete

Images