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

SAR image ship target segmentation method

A target segmentation and ship technology, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as excessive side lobes and "smear", close distance between two ships, and unsatisfactory segmentation, and achieve running speed. quick effect

Active Publication Date: 2017-06-06
HARBIN INST OF TECH
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem of unsatisfactory segmentation caused by insufficient prior information, too strong side lobe and "smear", and too close distance between the two ships when the existing method detects and segments the ship target, and proposes a Segmentation method of ship target in SAR image

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 ship target segmentation method
  • SAR image ship target segmentation method
  • SAR image ship target segmentation method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0029] Specific embodiment one: the specific process of a kind of SAR image ship target segmentation method of the present embodiment is:

[0030] Step 1, performing water and land separation based on color and region on the original image;

[0031] Step 2, perform Otsu binary segmentation and region segmentation on the image after water and land separation to obtain the size of the ship;

[0032] Step 3. Set the background window based on the size of the ship, assuming that the clutter in the background window is K-distributed, estimate the K-distribution parameter, obtain a threshold, and segment the ship target based on the threshold;

[0033] Step 4, perform an open operation on the ship target to obtain the segmented image;

[0034] SAR is synthetic aperture radar and Otsu is the maximum between-class variance.

specific Embodiment approach 2

[0035] Embodiment 2: The difference between this embodiment and Embodiment 1 is that the original image is obtained in the step 1, and the original image is separated from water and land based on color and region; the specific process is:

[0036] Step 11, based on color detection, the land in the image is yellowish, and the water surface is blue, and the RGB value is detected for the original image, and the part with the B value greater than or equal to the R value in the RGB value is taken as the water surface; the B value (blue color) in the RGB value is taken as the water surface; Component) less than the R value (red component) as land;

[0037] Step 12. Keep the area with the largest water surface separated in step 11 and mark it as black (gray value 0), and other areas are regarded as land and marked as white (gray value 255) to get a binary value image;

[0038] Step 13, the binary image obtained in step 12 is subjected to opening operation and inverse color transform...

specific Embodiment approach 3

[0051] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is that in the step two, Otsu binary segmentation and region segmentation are performed on the image after water and land separation to obtain the size of the ship; the specific process is:

[0052]Since the CFAR to be used next involves determining the size of the background window, and the resolution of different SAR images is different, and the pixel values ​​occupied by the ship target are also different, the size of the window should naturally be different. If the size of the window is too large, the calculated background will not be Detect the background where the ship target is located. If it is too small, the ship target itself may be included in the background window, which will lead to inaccurate results. Therefore, sufficient prior information is needed to determine the size of the selection window, and the process of obtaining prior information should be rapid...

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 relates to an SAR image ship target segmentation method. The invention aims to solve the problems of insufficient prior information, too strong sidelobes and ''smearing'' and too small distance between two ships which occur when an existing method is utilized to detect and segment ship targets and cause unsatisfactory segmentation. The specific process includes the following steps: 1. performing water-land separation on an original image based on colors and regions; 2. Performing Otsu binary segmentation and region segmentation on the image after water-land separation to obtain the sizes of ships; 3. setting a background window based on the sizes of the ships, assuming that clutter in the background window is in K distribution, estimating a K-distribution parameter, obtaining a threshold value, and segmenting ship targets based on the threshold value; and 4. performing opening operation on the ship targets to obtain an image after segmentation. The SAR image ship target segmentation method provided by the invention is used for the field of ship target segmentation.

Description

technical field [0001] The invention relates to a method for segmenting a ship target in a SAR image. Background technique [0002] my country has a vast territory of oceans, rivers and other waters, so there are many ships coming and going, so it is very necessary to monitor the ships. Ordinary optical images are easily disturbed by external conditions, such as time, season, weather, clouds and so on. Synthetic Aperture Radar (SAR) has the advantages of all-weather and all-weather, and is not easily disturbed by external conditions. Surface penetration ability, so it is more widely used. [0003] Radar target recognition is of great practical significance in national defense, and it is a hot issue at present. Due to the imaging mechanism of SAR radar, there are a certain amount of noise, sea clutter, side lobes, strong reflection "smear" and a series of interference factors in the formed image, which we do not expect to obtain. How to reduce the interference factors of ...

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): G06K9/00G06K9/34G06T7/11G06T7/136
CPCG06T2207/10044G06T2207/10024G06T2207/30181G06V20/13G06V10/267
Inventor 王勇郭天骄谢俊好李绍滨李高鹏
Owner HARBIN INST OF TECH
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