Wavelet scatternet-based SAR image segmentation method

An image segmentation and image technology, applied in the field of image processing, can solve the problems of low algorithm efficiency and achieve the effect of improving efficiency, improving segmentation accuracy, and improving segmentation efficiency

Active Publication Date: 2015-11-18
XIDIAN UNIV
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The smaller the distance between two pixels, the more overlapping pixels between the corresponding two image b

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
  • Wavelet scatternet-based SAR image segmentation method
  • Wavelet scatternet-based SAR image segmentation method
  • Wavelet scatternet-based SAR image segmentation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] The SAR image segmentation method based on the wavelet scattering network of the present invention is based on the fast feature extraction of the SAR image texture. see figure 1 , including the following steps:

[0037] 1) Select the original SAR image that needs to be segmented, the size is [256,256], see figure 2 ; Select the Lee filter window size 5*5 to perform Lee filter denoising, and divide the SAR image data by 255 as a data normalization operation.

[0038] 2) Set the maximum scale of scattering transformation J=2, when segmenting the SAR image, the feature of each pixel is determined by an image block with a size of [8,8]; when processing the pixels on the boundary of the SAR image, It is necessary to symmetrically expand the boundary of the SAR image to obtain the expanded SAR image f with a size of [264,264].

[0039] 3) Morlet wavelet function in selected scattering transformation in is the two-dimensional mother wavelet function, x is the above-men...

Embodiment 2

[0050] The SAR image segmentation method based on the wavelet scattering network is the same as that in Embodiment 1, wherein step 3) generates the two-dimensional scattering propagation operator U(p)f, and the specific steps are as follows:

[0051] 3a) Select the Morlet two-dimensional mother wavelet function Then the wavelet function group in the scattering transform is ψ λ (x)=2 -2j ψ(2 -j r -1 x) ， Where r is the rotation parameter, select four rotation directions 0°, 45°, 90° and 135° respectively, j is the scale parameter, take an integer between 0 and J, ψ λ The frequency center of λ=2 -j r.

[0052] 3b) Set the scattering transformation path p={λ 0 ,λ 1 ,...,λ L-1}={r,2 -1 r,2 -2 r}, and then use the Morlet wavelet function in step 3a) to generate a set of two-dimensional filters where λ 0 =r,λ 1 = 2 -1 r,λ 2 = 2 -2 r.

[0053] 3c) First use the first filter from step 3b) Filter the image f to get the corresponding wavelet coefficients Then do t...

Embodiment 3

[0056] The SAR image segmentation method based on the wavelet scattering network is the same as embodiment 1-2, wherein step 4) produces the two-dimensional scattering operator S described in J (p)f, the specific steps are as follows:

[0057] 4a) Take a fixed window function in is a two-dimensional Gaussian function, that is,

[0058] 4b) Follow the path p={r,2 -1 r,2 -2 r} and the scattering propagation operator U(p)f in step 3), generate the frame structure scat of scattering transformation, that is, add a window function after the propagation parameters of each layer Filtering to preserve the spatial invariance of the texture within the window.

[0059] 4c) The two-dimensional scattering operator for scattering transformation of SAR image is Wherein the path length is L=3. In other words, the output of each layer of scattering transformation is produced by three operations of wavelet filtering, modulo value and window function filtering.

[0060] The two-dime...

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 present invention discloses a wavelet scatternet-based SAR image segmentation method, which resolves a technical problem that conventional texture-based SAR image segmentation is inefficient and time-consuming. Implementation steps are that: performing pre-processing of denoising and uniformization on an SAR image; setting a scattering transform path, selecting a wavelet function and a window function, and generating a scattering propagation operator and a scattering operator; performing scattering transform on the SAR image, to obtain a scattering coefficient of an SAR image pixel point; performing K-Means cluster on a scattering texture feature after dimension reduction, to obtain a preliminary segmentation result; searching for affine space in which pixels of different categories are located, to form an affine classifier; and performing sliding window correction on the preliminary segmentation result by using the affine classifier, to implement SAR image segmentation. According to the present invention, it is unnecessary to perform a partitioning operation on the SAR image, and the scattering texture feature that can reduce a difference between same texture and increase a difference between different texture is extracted, and precise and fast segmentation can be performed on the SAR image. The method is used for fast segmentation on a single SAR image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a SAR image segmentation, in particular to a SAR image segmentation method based on a wavelet scattering network. It can be applied to the segmentation of a single SAR image. Background technique [0002] Synthetic Aperture Radar (SAR) is an active microwave earth observation equipment, which obtains ground information by transmitting and receiving radar waves. . SAR images have been widely used in military and national economic fields, including aircraft target detection, land monitoring, navigation, natural disaster monitoring, etc. The research on SAR images mainly includes SAR image denoising, fusion, segmentation, target detection, change detection, etc. SAR image segmentation is a basic but important information extraction technology. Traditional SAR image segmentation algorithms include pixel-based and texture-based segmentation methods, among which the pixel-bas...

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
IPC IPC(8): G06T7/00
CPCG06T2207/10032
Inventor 焦李成刘芳马文萍刘红英屈嵘王爽侯彪杨淑媛
Owner XIDIAN UNIV
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