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

SAR Image Object Recognition Method Based on Non-negative Matrix Factorization Based on Sparse Constraint

A technology of non-negative matrix decomposition and sparse constraints, which is applied in the field of non-negative matrix decomposition SAR image target recognition, can solve the problem of not reflecting the sparsity of SAR images, and achieve the goal of improving the difference, improving the recognition rate, and improving the recognition accuracy Effect

Active Publication Date: 2017-12-12
XIDIAN UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in this method, the sparsity of the SAR image itself is not reflected, and the machine learning algorithm with high classification accuracy is not used

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 Object Recognition Method Based on Non-negative Matrix Factorization Based on Sparse Constraint
  • SAR Image Object Recognition Method Based on Non-negative Matrix Factorization Based on Sparse Constraint
  • SAR Image Object Recognition Method Based on Non-negative Matrix Factorization Based on Sparse Constraint

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] refer to figure 1 As shown, the specific implementation steps of the present invention are as follows:

[0033] Step 101: Input a training sample set and a test sample set, and the input samples are SAR target pictures in the MSTAR database, such as figure 2 As shown, a is the original image of the BMP2-SN_9563 armored vehicle, b is the original image of the BMP2-SN_9566 armored vehicle, c is the original image of the BTR70-SN_C71 armored vehicle, d is the original image of the T72-SN_132 main battle tank, e The original image of the T72-SN_812 main battle tank. The MSTAR database is provided by the DARPA / AFRL Motion and Stationary Target Acquisition and Recognition Project work, figure 2 The resolution of each image is 0.3m*0.3m and the size is 128*128. In the experiment, the training sample we selected is the image when the SAR pitch angle is 17°, and the selected test sample is the pitch angle of 15°. ° picture.

[0034] The input training sample set is Z={Z i...

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 belongs to the technical field of image processing, and specifically discloses a SAR image target recognition method based on non-negative matrix decomposition of sparse constraints, which mainly extracts more effective features by improving the non-negative matrix decomposition method to improve recognition accuracy and solve the problem of The features extracted by the existing technology are not typical, and the recognition accuracy is not high. The implementation plan is: perform the same preprocessing on the training sample image and the test sample image and perform logarithmic transformation, decompose the preprocessed training sample set with sparse-constrained non-negative matrix decomposition to obtain the base matrix and coefficient matrix, and test the sample set The set is projected into the subspace constructed by the basis matrix, and after the feature matrix is ​​obtained, SVM is used to classify to obtain the final classification accuracy. Compared with the prior art, the feature extracted by the invention is more effective and can effectively improve the recognition accuracy.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to an image feature extraction method, namely a non-negative matrix decomposition method, in particular to a SAR image target recognition method based on sparse constraint non-negative matrix decomposition, which can be widely used in military and in civil applications. Background technique [0002] Synthetic Aperture Radar (SAR) is one of the important means of earth observation and military detection due to its all-weather, all-weather and strong penetrating power. As one of the key technologies of SAR image analysis and interpretation, SAR image target recognition has strong commercial and military value, and has increasingly become a research hotspot at home and abroad. [0003] In SAR image target recognition research, it mainly includes image feature extraction research and machine learning machine research. The main purpose of image feature extraction research is to ...

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): G06K9/00G06K9/62
CPCG06F18/23213G06F18/2411
Inventor 慕彩红焦李成师萌熊涛刘若辰刘静杨淑媛王爽云智强王孝齐
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