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

A Recognition Method of Ship Isar Image Based on Optical Image Aid

A technology of optical image and recognition method, which is applied in the field of ship ISAR image recognition, can solve the problem of low accuracy rate of ship ISAR image recognition, achieve good classification and recognition effect, improve accuracy, and improve the effect of recognition accuracy

Active Publication Date: 2021-04-27
HARBIN INST OF TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem of low accuracy of ship ISAR image recognition in the prior art, and propose a ship ISAR image recognition method based on optical image assistance

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
  • A Recognition Method of Ship Isar Image Based on Optical Image Aid
  • A Recognition Method of Ship Isar Image Based on Optical Image Aid
  • A Recognition Method of Ship Isar Image Based on Optical Image Aid

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0028] Specific implementation mode one: combine figure 1 Describe this embodiment, the concrete process of a kind of ship ISAR image recognition method based on optical image assistance in this embodiment is:

[0029] Step 1. Preprocessing the ship ISAR image of the known ship category (frigate, destroyer, etc.) in the database, the preprocessing includes denoising processing and image normalization processing;

[0030] Step 2. Use the derivative network Pix2pix of GAN to complete the mapping from the preprocessed ship ISAR image domain to the ship optical image (known in the database) domain in step 1, and obtain the trained derivative network Pix2pix;

[0031] Step 3. Use the derivative network Pix2pix trained in step 2 to generate a ship optical image from the preprocessed ship ISAR image, and combine the ship optical image with the ship ISAR image. The synthesized image contains both ship ISAR image information and Optical image information; use synthetic images to const...

specific Embodiment approach 2

[0035] Embodiment 2: The difference between this embodiment and Embodiment 1 is that the ISAR image is preprocessed in the step 1, and the preprocessing includes denoising processing and image normalization processing; the specific process is:

[0036] Step 11, using the global threshold to denoise the ISAR image to obtain the denoised ISAR image of the ship;

[0037] Step 12: Normalize the denoised ship ISAR image obtained in step 11.

[0038] Other steps and parameters are the same as those in Embodiment 1.

specific Embodiment approach 3

[0039] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is that, in the step one by one, the global threshold is used to analyze the ISAR image (such as Figure 6 ) for denoising processing to obtain the denoised ship ISAR image (such as Figure 7 ); the process is: see the flow chart figure 2 :

[0040] Step one by one, setting the difference threshold t for determining the global threshold;

[0041] Step 112, set the initial threshold threshold as T:

[0042]

[0043] In the formula, I(i,j) max Represents the pixel value of the brightest point in the ISAR image of the ship, I(i,j) min Represents the pixel value of the darkest point in the ISAR image of the ship; i represents the i-th row of the image matrix, and j represents the j-th column of the image matrix;

[0044] Step 113, compare the intensity (pixel value) of each pixel point in the ISAR image of the ship with the initial threshold threshold T, and return ...

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

A ship ISAR image recognition method based on optical image assistance, the invention relates to a ship ISAR image recognition method. The purpose of the invention is to solve the problem of low recognition accuracy of ship ISAR images in the prior art. The process is as follows: 1. Preprocessing the ship ISAR images of known ship types in the database; 2. Obtaining the trained derivative network Pix2pix; 3. Using the trained derivative network Pix2pix to generate ship ISAR images into ship optics image, combine the optical image of the ship with the ISAR image of the ship; obtain the trained convolutional neural network; 4. preprocess the ISAR image of the ship to be tested; 5. use the trained derivative network Pix2pix to obtain the The ship optical image is merged with the ship ISAR image; 6. Input the obtained synthetic image into the trained convolutional neural network to obtain the category. The invention is used in the field of radar target identification.

Description

technical field [0001] The invention belongs to the field of radar target recognition, in particular to a ship ISAR image recognition method. Background technique [0002] Inverse synthetic aperture radar (ISAR) completes target imaging by transmitting signals to detection targets and receiving target echoes. The most commonly used imaging algorithm is the range-Doppler imaging algorithm. The essence of this algorithm is to perform two-dimensional Fourier transform on the received echo in the azimuth direction and the range direction. The resolution of the range direction is determined by the carrier frequency. , the azimuth resolution depends on the angle the target turns during the coherent integration time. The classification and recognition of ISAR images starts with flying targets, in Botha E C.Classification of aerospace targets using superresolution ISAR images[C].Communications and Signal Processing,1994.COMSIG-94,Proceedings of the 1994IEEE South African Sympoisumo...

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
CPCG06V20/13G06F18/241
Inventor 李高鹏张云孙昭王洁
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