Polarized SAR image segmentation method based on superpixels and fractal network evolution algorithm

A fractal network evolution and image segmentation technology, applied in image analysis, image enhancement, image data processing, etc., can solve the problems of reducing the accuracy of parameter estimation, differences in boundaries, and jagged segmentation results, etc., to avoid jagged segmentation boundaries Phenomenon, smooth boundary, consistent effect of segmented objects

Active Publication Date: 2017-09-19
CHINA UNIV OF GEOSCIENCES (WUHAN)
View PDF3 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the one hand, the grid division method will cause the final segmentation result to be jagged. On the other hand, the grid division and the boundary of the ground object are different, which will reduce the accuracy of parameter estimation.

Method used

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
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Polarized SAR image segmentation method based on superpixels and fractal network evolution algorithm
  • Polarized SAR image segmentation method based on superpixels and fractal network evolution algorithm
  • Polarized SAR image segmentation method based on superpixels and fractal network evolution algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0063] Please refer to figure 1 and figure 2 , the embodiments of the present invention provide a polarization SAR image segmentation method based on superpixels and fractal network evolution algorithm, comprising the following steps:

[0064] Step 1: Perform Pauli decomposition on the polarimetric SAR image to be segmented to generate PauliRGB image, and use the improved simple linear iterative clustering algorithm to generate the initial object;

[0065] The Pauli decomposition is a coherent decomposition that, under the reciprocity condition, decomposes the scattering matrix of a deterministic target into single scattering from a flat surface, dihedral scattering from a corner reflector with a direction angle of 0° and a direction angle of 45° A linear combination of the dihedral scattering of the corner reflectors.

[0066] Since the calculation of the statistical feature similarity between an object and its adjacent objects requires sufficient samples to estimate the p...

Embodiment 2

[0084] Please refer to figure 1 and image 3 , the embodiments of the present invention provide a polarization SAR image segmentation method based on superpixels and fractal network evolution algorithm, comprising the following steps:

[0085] Step 1: For the polarimetric SAR image to be segmented, generate superpixels as the initial object;

[0086] Step 2: Replace the spectral similarity in the fractal network evolution algorithm with the similarity between objects derived based on the statistical model, establish a similarity criterion that combines shape features and statistical features, and calculate the distance between each object in the initial object and adjacent objects. Statistical similarity, constructing a similarity criterion of comprehensive statistical features and shape features between adjacent objects;

[0087] The specific method is:

[0088] Step 2.1: Model the polarimetric SAR data using a statistical model, preferably G 0 distribution model, and est...

Embodiment 3

[0117] Please refer to figure 1 and Figure 4 , the embodiments of the present invention provide a polarization SAR image segmentation method based on superpixels and fractal network evolution algorithm, comprising the following steps:

[0118] Step 1: Perform Pauli decomposition on the polarimetric SAR image to be segmented to generate PauliRGB image, and use the improved simple linear iterative clustering algorithm to generate the initial object;

[0119] The Pauli decomposition is a coherent decomposition that, under the reciprocity condition, decomposes the scattering matrix of a deterministic target into single scattering from a flat surface, dihedral scattering from a corner reflector with a direction angle of 0° and a direction angle of 45° A linear combination of the dihedral scattering of the corner reflectors.

[0120] Since the calculation of the statistical feature similarity between an object and its adjacent objects requires sufficient samples to estimate the p...

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

PUM

No PUM Login to view more

Abstract

The invention discloses a polarized synthetic aperture radar (SAR) image segmentation method based on superpixels and a fractal network evolution algorithm. The method includes the steps of generating superpixels as initial objects for a polarized SAR image to be segmented; calculating similarity criteria among the adjacent objects in the initial objects; conducting statistics on the minimum value of the similarity criterion between each object and the adjacent object, if the minimum value is less than or equal to a dimension parameter, merging the two adjacent objects to generate a new object, and if the minimum value is greater than the dimension parameter, then traversing all the objects instead of merging, to complete a first segmentation and generate a new object layer; and generating an object polygon to obtain a final segmentation result. According to the invention, the method provides sufficient pixels for the estimation of statistical model parameters, and avoids zigzag phenomena of a segmented boundary; and integrates statistical features and shape features based on the idea of the fractal network evolution algorithm to make the segmentation object more consistent and the boundary smooth, and the accuracy of the polarized SAR image segmentation is improved.

Description

technical field [0001] The invention relates to a polarization synthetic aperture radar (Synthetic Aperture Radar, SAR) image segmentation method, in particular to a polarization SAR image segmentation method based on superpixels and fractal network evolution algorithms. Background technique [0002] Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. It is a key step from image processing to image analysis. Due to the interference of coherent speckle noise in polarimetric SAR images, the boundaries of ground objects are blurred, and the interpretation of polarimetric SAR images is difficult. The object-based method can not only effectively suppress the influence of coherent speckle, but also introduce more available features, which is helpful to understand the ground objects and target information contained in the image, and the interpretation result is better. [000...

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

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/143G06T7/187G06T7/11
CPCG06T7/11G06T7/143G06T7/187G06T2207/10044
Inventor 陈启浩刘修国徐乔杨帅
Owner CHINA UNIV OF GEOSCIENCES (WUHAN)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap