Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

SAR Image Segmentation Method Based on Submodel Dictionary Learning

An image segmentation and dictionary learning technology, applied in the field of image processing, can solve the problems of poor detail information integrity and low segmentation accuracy, and achieve the effect of improving classification performance and expanding application fields

Active Publication Date: 2019-10-25
XIDIAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to address the above-mentioned deficiencies in the prior art, to propose a SAR image segmentation method based on sub-model dictionary learning, to solve the problems of low segmentation accuracy and poor detail information integrity of the above method, and to improve the quality of SAR image segmentation

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
  • SAR Image Segmentation Method Based on Submodel Dictionary Learning
  • SAR Image Segmentation Method Based on Submodel Dictionary Learning
  • SAR Image Segmentation Method Based on Submodel Dictionary Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] Embodiments of the present invention are as follows: calculate SIFT feature in the pixel block with pixel as the center and supplemented by neighborhood, then perform sparse coding to SIFT feature to obtain spatial pyramid feature; randomly select training samples to construct graph model; by maximizing a sub-model The objective function is to cluster the graph model and construct a dictionary; finally, perform sparse coding and classification on all data, and the present invention will be further described in detail below in conjunction with specific examples.

[0035] refer to figure 1 , the implementation steps of the present invention are as follows:

[0036] Step 1: Calculate the scale-invariant feature transformation SIFT feature.

[0037] In the pixel block centered on the pixel and supplemented by the neighborhood, calculate the scale-invariant feature transformation SIFT feature {I 1 , I 2 ,...,I θ ,...,I N}, where I θ ∈R 128×m Represents the SIFT featur...

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 SAR image segmentation method based on sub-model dictionary learning, which mainly solves the problems of low SAR image segmentation accuracy and poor detail integrity in the current mainstream sub-model dictionary learning method. The segmentation process is as follows: 1. Calculate the spatial pyramid feature in the neighborhood centered on the pixel; 2. Select 10% of the training data from the spatial pyramid feature to construct the graph model G(V,E); 3. Maximize a sub Modular objective function, clustering the graph model; 4. Calculate the dictionary D according to the clustering results; 5. Fix the dictionary D, calculate the sparse coding features of the training data, the classification parameter matrix and the sparse coding features of all data; 6. According to the classification The parameter matrix W calculates the class label vector; 7. Convert the class label vector into a class label to obtain the final segmentation result. Compared with the existing sub-model dictionary learning method, the invention maintains the integrity of image detail information, improves segmentation precision, and can be used for SAR image target recognition.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a method for SAR image segmentation, which can be applied to target recognition. Background technique [0002] Synthetic Aperture Radar (SAR) is a high-resolution radar system. SAR imaging is basically not affected by factors such as light and climate, and can monitor targets all day and all day long. It is widely used in military, agricultural, geological detection and other fields. As the first step in SAR image interpretation, SAR image segmentation can provide overall structural information and highlight regions of interest, which plays an important role in subsequent image interpretation. The information on the SAR image is the reflection of the ground object on the radar beam, mainly the image information formed by the backscattering of the ground object, which reflects the electromagnetic scattering characteristics and structural characteristics of the target, and its imag...

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 Patents(China)
IPC IPC(8): G06T7/10G06K9/62
CPCG06T7/10G06T2207/10044G06F18/2321G06F18/2136G06F18/241
Inventor 侯彪焦李成唐欢马晶晶马文萍王爽白静
Owner XIDIAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com