SAR image super-pixel segmentation method based on variation level set

A superpixel segmentation and superpixel technology, applied in the field of image processing, can solve the problems of SAR image coherent speckle noise, low segmentation accuracy, lack of image texture information, etc., to solve the effect of coherent speckle noise and improve segmentation accuracy.
CN110533669AActive Publication Date: 2019-12-03XIDIAN UNIV
4 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
XIDIAN UNIV
Publication Date
2019-12-03

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses an SAR image super-pixel segmentation method based on a variation level set, and mainly solves the problems of low SAR image super-pixel segmentation precision and low super-pixel block region boundary fitting degree caused by SAR image speckle noise influence and texture information loss in the prior art. The method comprises the following steps: inputting an SAR image, and roughly segmenting the SAR image into K superpixel block areas; respectively designing energy functional based on SAR image speckle noise and image texture information; respectively inserting the designed energy functional into an edge evolution iterative equation to obtain a new iterative equation; carrying out edge evolution on the boundary of each super-pixel block region by utilizing a new iterative equation; and finishing super-pixel segmentation after edge evolution of the super-pixel block region is stopped. The SAR image super-pixel segmentation method effectively improves the precision of SAR image super-pixel segmentation, solves the problem that the super-pixel block region boundary fitting degree is not high, and can be used for image processing of airfield runways, farmlanddistribution and geological exploration.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of image processing, and in particular relates to an image segmentation method, which can be used for segmentation and extraction of SAR image targets in the field of computer vision. Background technique

[0002] The variational method is an effective method for studying integral functionals. The main idea is to solve the solution of the minimum functional. The level set method is an important means to solve the curve evolution method. It can perform numerical calculations on the evolution curves on the network, avoiding direct calculations. Changing curve normal vector and curve curvature.

[0003] Synthetic Aperture Radar (SAR) is an active microwave sensor. The SAR image segmentation technology is to divide the complete SAR image into interesting targets with different characteristics, so as to carry out the research and analysis of SAR image.

[0004] A superpixel is a collection of pixels composed of ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More