SAR (stop and reveres) image segmentation method based on dictionary migration clustering

Abstract

The invention discloses an SAR (stop and reveres) image segmentation method based on dictionary migration clustering, which mainly solves the problems that the existing artificial mark SAR image has high cost and the existing non-mark SAR image can not assist a target SAR image in segmenting. The method has the following realization processes: 1) extracting wavelet characteristics for the target SAR image and the non-mark assistant SAR image; 2) setting circulation ending times, and preliminarily dividing the target SAR image with a k-means method; 3) training a dictionary for each class of target SAR image data; 4) migrating a group of samples for each class of target SAR image data from the assistant SAR image data; 5) removing the assistant data sample with an unstable label by a spectral clustering integration method; 6) training an assistant dictionary by each bath of purified assistant samples; and 7) updating a sample label and outputting a clustering segmenting result according to a target dictionary, the assistant dictionary and a corresponding clustering center. The SAR image segmentation method has the advantage of good segmenting effect and can be used for further identifying the SAR image target.

Description

technical field [0001] The invention belongs to the technical field of image processing and can be used for SAR image segmentation as the basis for further SAR image understanding and interpretation. Background technique [0002] Synthetic Aperture Radar (SAR) imaging technology overcomes the passive imaging shortcomings of ordinary imaging technology that must be imaged under certain lighting conditions. It actively emits and receives electromagnetic waves, and images according to the reflection and scattering characteristics of objects. SAR uses the principle of synthetic aperture to improve the azimuth resolution, which has unique advantages in the field of remote sensing. Since SAR has all-weather and all-weather detection and reconnaissance capabilities, the interpretation of SAR images has received more and more attention from national defense and civilian applications. As a very important step of SAR image interpretation, SAR image segmentation becomes more and more ...

AI Technical Summary

Problems solved by technology

Due to the particularity and complexity of the imaging mechanism of SAR images, there is a large amount of coherent speckle noise in the resulting images, which leads to poor separability of SAR images, and the segmentation results obtained by traditional methods are not ideal.

The semi-supervised clustering algorithm can get better results than the traditional clustering algorithm, but the semi-supervised segmentation method requires a certain amount of labeled data. The SAR image source itself is relatively scarce, and the labeled data is less, and SAR covers a wide range. , it takes a lot of manpower and material resources to label new SAR image data, and the cost is too high

Images