Polarized SAR Image Classification Method Based on Sparse Deep Stack Network

A classification method and sparse technology, applied in the field of image processing, can solve the problems of low classification accuracy, achieve the effects of high classification accuracy, overcome high time complexity, and improve classification efficiency

Active Publication Date: 2018-04-17
XIDIAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The present invention extracts the depth features of polarimetric SAR images, avoiding the problem of low classification accuracy caused by the use of a single polarimetric scattering feature

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 Classification Method Based on Sparse Deep Stack Network
  • Polarized SAR Image Classification Method Based on Sparse Deep Stack Network
  • Polarized SAR Image Classification Method Based on Sparse Deep Stack Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0049] The present invention will be further described below in conjunction with the accompanying drawings.

[0050] refer to figure 1 , the specific implementation steps of the present invention are as follows:

[0051] Step 1. Input a polarimetric SAR image.

[0052] Input a coherence matrix of a polarization SAR image to be classified, its size is a matrix of 3×3×N, and N represents the number of pixels in the polarization SAR image.

[0053] Step 2. Select training samples and test samples.

[0054] The real and imaginary parts of the six upper triangular elements of the coherence matrix are used as the features of the polarimetric SAR image to form a 9×N sample set.

[0055] 10% of the samples are randomly selected from the sample set as training samples, and the remaining 90% of the samples are used as test samples.

[0056] Step 3. Construct a sparse deep stack network.

[0057] The three single-layer sparse deep networks, the positional relationship of the upper l...

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 polarimetric SAR image classification method based on a sparse deep stack network. The specific steps are: (1) inputting a polarimetric SAR image; (2) selecting training samples and test samples; (3) constructing a sparse deep stack network ; (4) Train the sparse deep stack network; (5) Input the test sample; (6) Obtain the classification result map. The present invention uses a sparse deep stack network to extract depth features from polarimetric SAR images, avoiding the problem that a single polarized scattering feature cannot fully characterize the characteristics of complex targets, and at the same time adds sparse constraints to the sparse deep stack network, taking into account the characteristics local correlations between them. The invention has the advantages of low time complexity, high classification accuracy and wide algorithm adaptability. It can be applied to the field of object classification and target recognition in radar images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a polarization synthetic aperture radar SAR image classification method based on a sparse deep stack network in the technical field of polarization synthetic aperture radar image classification. The invention can be applied to the object classification and target recognition of radar images. Background technique [0002] Synthetic Aperture Radar (SAR) is a coherent imaging radar operating in the microwave band and an active remote sensing sensor. Polarized SAR belongs to the category of SAR. Compared with traditional SAR, it can greatly improve the ability to obtain various information of targets by controlling and changing the polarization mode of radar transmitting and receiving electromagnetic waves, and provides a basis for more in-depth study of target scattering mechanism. Important reference. The understanding and interpretation of polarimetric SAR images ...

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): G06K9/62
CPCG06F18/2413G06F18/214
Inventor 侯彪焦李成刘小娟马晶晶张向荣马文萍
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