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

SAR image classification method based on curve wave deep ladder network model

A network model and classification method technology, applied in the field of image processing, can solve the problems of reducing the classification accuracy rate, not considering the multi-resolution and multi-directional characteristics of the image, and the classification method is not robust, so as to improve the classification accuracy rate , improve the efficiency of classification, and the effect of fast training speed

Active Publication Date: 2019-10-08
XIDIAN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the disadvantage of this method is that the method directly sends the image block into the network model for classification, and does not take into account the multi-resolution and multi-directional characteristics of the image, which leads to the poor robustness of the classification method and reduces the classification accuracy

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 classification method based on curve wave deep ladder network model
  • SAR image classification method based on curve wave deep ladder network model
  • SAR image classification method based on curve wave deep ladder network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0033] Refer to attached figure 1 , the steps of the present invention are further described in detail.

[0034] Step 1. Build an initial sample set.

[0035] The high-resolution SAR image to be classified is input, and the input image is sliced ​​by a sliding window to obtain 225010 image blocks of 33×33 pixels as the initial sample set.

[0036] Step 2. Using curvelet transform to construct sample feature vector set.

[0037] Perform fast Fourier transform FFT on each sample in the initial sample set to obtain the Fourier transform coefficient of each sample;

[0038] Scale the Fourier transform coefficients of each sample to obtain 2 scale coefficients for each sample.

[0039] Perform inverse Fourier transform IFFT on the first scale coefficient of each sample, and pull it into a column vector to obtain the first group of 121-dimensional coefficients ...

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 classification method based on a curve wave depth ladder network model. The realization steps are as follows: input the SAR image to be classified; perform curve wave transformation on the input data to obtain sample features; normalize the sample features; construct The training data set and the test data set; construct the classifier model of the deep ladder network; use the training data set to train the classifier model; use the trained classification model to classify the test data set to obtain the classification result. The present invention uses curve wave transformation to extract features from samples, fully utilizes the multi-scale and multi-directional characteristics of samples, reduces the sample dimension, improves the robustness of feature extraction, simplifies the network, and speeds up the training and classification of the network speed.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a high-resolution Synthetic Aperture Radar (SAR) image classification method based on a curve wave depth ladder network model in the technical field of image classification. The invention can be applied to target classification and recognition of SAR images. Background technique [0002] Synthetic Aperture Radar (SAR) is widely used in the field of earth science remote sensing, because it not only has all-day and all-weather characteristics, but also provides different information than infrared and visible light sensors. Synthetic Aperture Radar (SAR) image classification completes the work of converting the image from the two-dimensional gray space to the target pattern space. The result of the classification is to divide the image into multiple sub-regions of different categories according to different attributes, which is a synthetic An important research conte...

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): G06K9/62G06K9/00
CPCG06V20/188G06F18/241
Inventor 焦李成屈嵘李晰张丹杨淑媛侯彪马文萍刘芳唐旭马晶晶古晶陈璞花
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