Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Small-sample polarized SAR ground feature classification method based on deep convolutional twin network

A twin network and deep convolution technology, applied in the field of image processing, can solve the problems of reduced network classification accuracy, complex feature design, and high cost, and achieve the effect of improving classification performance and facilitating model classification.

Active Publication Date: 2018-08-10
XIDIAN UNIV
View PDF11 Cites 45 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although this method makes full use of the target decomposition and statistical distribution characteristics of polarimetric SAR data, it still has the disadvantages of complex feature design, strong expert knowledge and more labeled samples for model training.
Although this method makes full use of the supervision information of labeled samples of polarimetric SAR data and improves the classification accuracy, the method still has the disadvantage that the training process requires a large amount of labeled sample information, and the cost is high. In less cases, the classification accuracy of the network will be greatly reduced

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
  • Small-sample polarized SAR ground feature classification method based on deep convolutional twin network
  • Small-sample polarized SAR ground feature classification method based on deep convolutional twin network
  • Small-sample polarized SAR ground feature classification method based on deep convolutional twin network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be introduced and described in detail below in conjunction with the accompanying drawings.

[0032] Refer to attached figure 1 , the specific implementation steps of the present invention are as follows:

[0033] Step 1. Input a polarimetric SAR image with a size of 430*280 to be classified and the real object label information corresponding to the polarimetric SAR image.

[0034] Step 2. Use the refined Lee filtering method to perform filtering processing on the polarimetric SAR image to be classified, remove the coherent speckle noise interference, and obtain the filtered polarimetric SAR image to be classified.

[0035] Step 3. Extracting the polarimetric SAR input feature vector from the filtered polarimetric SAR image to be classified.

[0036] (3a) Express each pixel in the polarimetric SAR image data with a 3*3 polarimetric coherence matrix T:

[0037]

[0038] (3b) Extract the polarization eigenvector I of the corresponding pixel...

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 small-sample polarized SAR ground feature classification method based on a deep convolutional twin network, and mainly solves a problem that a conventional method is low in classification precision because the number of polarized SAR data mark samples is smaller. The method of the invention comprises the steps: 1), inputting a to-be-classified polarized SAR image and a real ground object mark of the to-be-classified polarized SAR image, and carrying out the Lee filtering; 2), extracting an input feature vector from the filtered to-be-classified polarized SAR data, andcarrying out the dividing of a training sample set and a test sample set; 3), carrying out the combination of each two samples in the training sample set, and obtaining a sample pair training set; 4), building the deep convolutional twin network, and carrying out the training of the deep convolutional twin network through the training sample set and the sample pair training set; 5), carrying outthe classification of the samples in the test set through the trained deep convolutional twin network, and obtaining the classes of ground features. According to the invention, the method expands thetraining set under the twin configuration, achieves the extraction of the difference features, enables the classification precision of a model to be higher, and can be used for the target classification, detection and recognition of a polarized SAR image.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for classifying polarimetric SAR ground features, which can be used for ground feature classification or target recognition of polarimetric SAR remote sensing images. Background technique [0002] Polarization SAR is a synthetic aperture radar capable of full-polarization measurement of the target. It performs full-polarization measurement and imaging of the target by simultaneously transmitting and alternately receiving combined echoes of different polarization states. Polarimetric SAR data contains richer target scattering information, can express and describe the target more comprehensively, and improve the ability to identify ground objects. At the same time, it has the advantages of all-weather, all-time, high resolution, etc. It has outstanding advantages in aspects such as recognition, object classification, and parameter inversion, so it is w...

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): G06K9/62G06K9/46G06T5/00G06N3/04
CPCG06T2207/20024G06T2207/10044G06V10/30G06V10/40G06N3/045G06F18/2155G06F18/2411G06F18/24G06T5/70
Inventor 杨淑媛刘振马文萍刘红英冯志玺孟丽珠马晶晶赵慧张凯侯彪徐光颖
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
Eureka Blog
Learn More
PatSnap group products