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

A Sparse Manifold Classification Method for Multi-scale Description Primitives of Polarized SAR Images

A classification method, multi-scale technology, applied in the field of image processing, which can solve problems such as poor model performance

Active Publication Date: 2019-06-11
WUHAN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional sparse coding models approximate the input signal by combining basis atoms in an overcomplete dictionary, but these models do not perform well in nonlinear situations, especially when the classification situation is complex

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
  • A Sparse Manifold Classification Method for Multi-scale Description Primitives of Polarized SAR Images
  • A Sparse Manifold Classification Method for Multi-scale Description Primitives of Polarized SAR Images
  • A Sparse Manifold Classification Method for Multi-scale Description Primitives of Polarized SAR Images

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In order to facilitate those of ordinary skill in the art to understand and implement the present invention, the present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the implementation examples described here are only used to illustrate and explain the present invention, and are not intended to limit this invention.

[0017] The fusion of incoherent features and coherent features of traditional time-series polarimetric SAR images cannot fully combine features at the early stage of feature formation. The multi-scale description primitive provided by the present invention uses multiple polarization coherent decompositions to extract polarization information at the polarization scale. On the time scale, the random walk method is used to extract relevant information with similarity as the weight, and combined to form a multi-scale cube, which can integrate features well and lay...

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 sparse manifold classification method for multi-scale description primitives of polarimetric SAR images, in order to solve the problems of extraction and fusion of non-coherent information and coherent information of time-series polarimetric SAR Multiplicative model non-coherent problem, through an essential feature fusion and manifold sparse expression, can effectively classify time series polarimetric SAR images. The invention discloses a method for constructing a multi-scale description primitive that combines two scale information of polarization incoherent features and time series coherent features, and utilizes a multi-level nonlinear production model expressed by compressed sensing and sparse manifolds to The method of feature extraction and information dimension reduction can effectively classify time series polarimetric SAR images, and multi-scale description primitives can also become a general basic technology for time series polarimetric SAR image processing.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a sparse manifold classification method based on multi-scale description primitives of time series polarization SAR images. Background technique [0002] Synthetic Aperture Radar (SAR) is a radar system used for imaging ground targets. With its high-resolution, all-time and all-weather characteristics, SAR has become an important tool for ground observation. SAR image classification is an important part of remote sensing image interpretation, and it is widely used in agricultural and forestry planning, disaster monitoring, environmental protection, military reconnaissance and other fields. [0003] For a single SAR image, statistical distribution is an important classification method; for polarimetric SAR images, polarization decomposition is a common classification method; for multiple time series images, coherent information can be obtained by unwrapping interference ...

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): G06K9/62G06K9/46
CPCG06V10/40G06F18/2411
Inventor 何楚涂明霞李壮韩功
Owner WUHAN 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