SAR image segmentation method based on semantic information classification

Abstract

The invention discloses an SAR image segmentation method based on semantic information classification. The SAR image segmentation method based on the semantic information classification mainly solves the problem that ground object zones, formed by uniformly connective ground object target gathering, of a forest, a building group and the like can not be obtained through non-supervision segmentation by an existing segmentation method. The method comprises the following steps: (1) an initial sketch model is used on an input SAR image so that an initial sketch image expressing image structure information is obtained; (2) semantic information analysis is performed on the initial sketch image so that semantic information classification results of all line segments are obtained; (3) the ground object zones formed by the ground object target gathering are classified based on the semantic information analysis; and (4) the rest zones are divided into zones to be determined and non-line-segment zones and SAR image segmentation is respectively performed to the zones to be determined and the non-line-segment zones so that the SAR image segmentation is finally achieved. Compared with the prior art, the SAR image segmentation method based on the semantic information classification is strong in generality and capable of achieving segmentation of SAR images with a large amount of ground object zones formed by the ground object target gathering. Uniform connectivity of a segmentation result is good, edge location is accurate, and the independent ground object target can be segmented.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to a method for segmenting SAR images, and can be used for processing and interpreting SAR images. Background technique [0002] Image segmentation is the technology and process of dividing an image into multiple regions with similar characteristics, and it is an important issue in image processing. Image understanding in computer vision, including object detection, object feature extraction, and object recognition, all depend on the quality of image segmentation. The two main criteria for image segmentation are: the accuracy of the edge location of the segmented area and the consistency of the internal features of the segmented area. According to the segmentation strategy, image segmentation methods can be roughly divided into three categories: segmentation based on discontinuity of features, segmentation based on similarity of features, and segmentation based on the combinatio...

AI Technical Summary

Problems solved by technology

[0004] (1) Segmentation methods based on gray levels, using pixels or superpixels as processing units, unsupervised segmentation of SAR images, but this type of method has serious problems in areas such as forests and building groups in SAR images. The phenomenon of over-segmentation can not get connected regions with good consistency, which is not conducive to subsequent image processing, such as image classification and target recognition;

[0005] (2) The texture-based segmentation method extracts the texture features of SAR image objects through the texture analysis method to describe the characteristics of the objects, and then performs SAR image segmentation. Although it can be obtained that consistent connectivity is obtained in forests, buildings and other object areas However, it is required to provide a model for describing the texture and provide sample data for learning model parameters. It belongs to supervised SAR image segmentation and cannot automatically process SAR image data, which limits this type of segmentation algorithm. Application in SAR Image Automatic Interpretation System

Images