Polarization SAR ship detection method based on low-rank dictionary learning and sparse representation

A technique of sparse representation and dictionary learning, which is applied in the field of ship target detection and polarization SAR ship detection, and can solve problems such as low-rank damage to the dictionary

Inactive Publication Date: 2014-07-30
CNGC INST NO 206 OF CHINA ARMS IND GRP
View PDF2 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the training samples are polluted by noise, the low-rank property of the dictionary may be destroyed

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
  • Polarization SAR ship detection method based on low-rank dictionary learning and sparse representation
  • Polarization SAR ship detection method based on low-rank dictionary learning and sparse representation
  • Polarization SAR ship detection method based on low-rank dictionary learning and sparse representation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0070] refer to figure 1 , specifically illustrate the polarized SAR ship detection method based on low-rank dictionary learning and sparse representation of the present invention, which specifically includes the following steps:

[0071] Step 1, extract the sea clutter samples as training clutter samples, and construct the training data matrix Z from the pixels of the clutter samples.

[0072] Its specific sub-steps are:

[0073] (1.1) extract the sea clutter sample as the training clutter sample, and form the training data matrix Z with the feature vectors of N pixels of the training clutter sample, its expression is: Z=[z 1 ... z i ... z N ];

[0074] Among them, N is the number of pixels selected in the training clutter samples, and N>9, the feature vector z i Representing the feature vector i=1, 2, . In the simulation experiment of the present invention, N=50 is set.

[0075] (1.2) For the i-th pixel of the training clutter sample, according to its polarization s...

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 field of radar automatic target detection, and discloses a polarization SAR ship detection method based on low-rank dictionary learning and sparse representation. The method is applied to ship target detection in a polarization SAR image and specially comprises the following steps of firstly extracting a sea clutter sample as a training clutter sample, constructing a training data matrix Z through pixels of the clutter sample, secondly, utilizing the training data matrix Z for performing training, obtaining a low-rank dictionary D through learning, thirdly, performing sparse representation on feature vectors of all the pixels of a test sample on the basis of the low-rank dictionary D obtained by learning, defining the detection statistic relying on a scattering mechanism according to a solved sparse representation coefficient, setting a threshold of the detection statistic, performing threshold detection on the detection statistic of all the pixels of the test sample, and obtaining a final binary image for displaying the detection result.

Description

technical field [0001] The invention belongs to the field of radar automatic target detection, and relates to a polarization SAR ship detection method based on low-rank dictionary learning and sparse representation. The method is suitable for ship target detection in polarimetric SAR images. Background technique [0002] Synthetic Aperture Radar (SAR) has the characteristics of all-day and all-weather working ability, and has become an important high-resolution telemetry method. A very important application of SAR images is ship detection. In recent years, ship detection based on fully polarimetric SAR data has attracted widespread attention, because polarimetric SAR data makes detection based on scattering mechanisms possible. [0003] Early object detection methods for polarimetric SAR usually relied on scattering intensity, for example, object detection methods based on polarimetric whitening filters (PWF). In the case of low signal-to-clutter ratio, the detection perfo...

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): G01S7/02
CPCG01S7/024G01S13/9029G01S13/9076
Inventor 王英华齐会娇刘宏伟文伟丁军
Owner CNGC INST NO 206 OF CHINA ARMS IND GRP
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