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

Polarization SAR image ship target detection method based on superpixel scattering mechanism

A scattering mechanism and target detection technology, which is applied to computer parts, instruments, character and pattern recognition, etc., to achieve the effect of improving detection performance

Active Publication Date: 2015-02-25
XIDIAN UNIV
View PDF2 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] To sum up, with the continuous improvement of the resolution of polarimetric SAR images, some existing polarimetric SAR ship target detection algorithms have great limitations in the detection of extended targets with regional feature distribution, which is urgent It is necessary to find a method for polarimetric SAR ship target detection based on regional distribution feature information

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 image ship target detection method based on superpixel scattering mechanism
  • Polarization SAR image ship target detection method based on superpixel scattering mechanism
  • Polarization SAR image ship target detection method based on superpixel scattering mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0089] The present invention is a polarization SAR image ship target detection method based on the distribution characteristics of the superpixel scattering mechanism, which mainly involves the detection of some important ship targets on the sea surface. Some existing detection algorithms are mainly based on the pixel-level scattering mechanism characteristics. For detection, with the improvement of radar resolution, some point targets show a trend of regional distribution. The traditional detection algorithm based on the single-pixel point scattering mechanism has poor robustness for the detection of these extended targets and cannot reach the actual detection rate. In view of the above shortcomings, the present invention uses the superpixel-based scattering mechanism distribution feature to detect sea surface ship targets, which can significantly improve the detection performance of regionally distributed targets.

[0090] see figure 1 , the polarized SAR image ship target d...

Embodiment 2

[0103] The ship target detection method in polarized SAR images based on the superpixel scattering mechanism is the same as in Embodiment 1, combined with specific implementation steps and figure 1 Let me explain in detail.

[0104] Concrete implementation steps of the present invention are as follows:

[0105] Step 1, multi-scale polarimetric SAR image superpixel generation.

[0106] Firstly, input the complex data of fully polarized SAR test image and clutter training image, which are recorded as:

[0107] G XY ={g x,y |1≤x≤M,1≤y≤N},

[0108] Among them, XY represents one of the four polarization channels HH, HV, VH, and VV in the polarization SAR test image and clutter training image, and H, V represent the two polarization modes of electromagnetic wave horizontal polarization and vertical polarization respectively , g x,y Represents the complex value of the pixel at the coordinate position (x, y), M, N are the number of rows and columns of the image respectively, cal...

Embodiment 3

[0171] The polarization SAR image ship target detection method based on superpixel scattering mechanism is the same as embodiment 1-2, wherein in step 1d), the updating of each superpixel clustering center is carried out as follows:

[0172] 1d1) For the ith superpixel SP i , labeling the category numbers in the graph L x,y The row position coordinates of all pixels whose value is i are taken out to form a row coordinate vector, which is denoted as R i , while L x,y The column position coordinates of all pixels whose value is i are taken out to form a column coordinate vector, which is denoted as C i , labeling the category numbers in the graph L x,y The total number of pixels whose value is i is recorded as N i , the attribute matrix T of each cluster center c ,P c , L c Initialize to zero matrix;

[0173] 1d2) According to the local iterative mechanism of SLIC, the cluster centers of the fully polarized SAR test image and the clutter training image are updated respec...

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 polarization SAR image ship target detection method based on the distribution characteristics of a superpixel scattering mechanism. The method comprises the implementation steps that superpixel segmentation results under different scales are obtained through an SLIC iteration clustering algorithm; the distribution characteristics of the superpixel scattering mechanism are defined; the scattering mechanism distribution characteristic vectors of all the superpixels in a clutter training image and a test image are extracted; clutter training image over-complete dictionaries are constructed; scattering characteristic sparse reconstruction of the test image under the corresponding dictionary is carried out, and a detection statistics image is obtained; by applying an appropriate detection threshold value on the detection statistics image, a binary image of a final detection result is obtained. The method achieves the purpose of detecting ship targets with the distribution characteristics, the ship targets are detected on the superpixel level, the regional distribution characteristics of the scattering mechanism are effectively utilized, and higher robustness is achieved under different signal-to-clutter ratios.

Description

technical field [0001] The invention belongs to the technical field of radar target detection, and mainly relates to a method for detecting a ship target in a polarized SAR image, in particular to a method for detecting a ship target in a polarized SAR image based on the distribution characteristics of a superpixel scattering mechanism, which is useful for subsequent ship target identification. , identification and classification provide important useful information. Background technique [0002] Synthetic Aperture Radar (SAR) uses microwave remote sensing technology, is not affected by climate and day and night, has all-weather and all-day working capabilities, and has the characteristics of multi-band, multi-polarization, variable viewing angle and penetrability . At present, SAR has been widely used in military reconnaissance, geological census, topographic mapping and mapping, disaster forecasting, marine applications, and scientific research, and has broad research and...

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
IPC IPC(8): G06K9/62G06K9/46
CPCG06V20/13G06V2201/07G06F18/2321G06F18/2136
Inventor 王英华何敬鲁刘宏伟纠博陈渤
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