Unlock instant, AI-driven research and patent intelligence for your innovation.

Method for enhancing ship target detection SAR image data

A target detection and image data technology, applied in image data processing, image enhancement, image analysis, etc., can solve the problems of low quality of generated data, poor practicability, and no labels, etc., to achieve improved feature resolution, stable training, Mode Robust Effects

Active Publication Date: 2022-01-21
10TH RES INST OF CETC
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a training stable , The mode is robust, has diversity and practicability, can improve the quality of generated SAR image data, and is a SAR image data enhancement method for ship target detection

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
  • Method for enhancing ship target detection SAR image data
  • Method for enhancing ship target detection SAR image data
  • Method for enhancing ship target detection SAR image data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] refer to figure 1 . First, centering on the ship position, the ship position in image form is used as the constraint condition c of SAR image enhancement, the constraint condition c and the hidden variable z are used as the input of the conditional generation confrontation network generator based on the ship position information, and the hidden variable After z passes through two fully connected layers, a high-dimensional feature vector is obtained, and it is reconstructed into a hidden variable feature map. The constraint c obtains a conditional feature map through a convolutional layer. The hidden variable feature map and the conditional feature map are cascaded and input to At least 4 layers of transposed convolutional layers are obtained to obtain a comprehensive feature map, and the feature resolution is increased by layer-by-layer upsampling to generate a new SAR ship image, and the target frame as the constraint c is correspondingly converted into the label of th...

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 method for enhancing ship target detection SAR image data disclosed by the invention is stable in training and steady in mode. According to the technical scheme, the method comprises the following steps: taking a ship position as a center, taking the ship position in an image form as a constraint condition of SAR image enhancement, reconstructing an obtained high-dimensional feature vector into a condition feature map through two full connection layers, cascading the condition feature map and a hidden variable feature map, inputting the cascaded feature map into a transposed convolution layer to obtain a comprehensive feature map, carrying out layer-by-layer up-sampling to improve the feature resolution, generating a new SAR ship image, correspondingly converting a target frame into a tag of the generated SAR image, and constructing a data-tag pair; extracting the characteristics of the data-label pair through a convolutional layer, discriminating the authenticity of the generated SAR image and the matching degree of the image and the label by the discriminator, and stimulating the generator to generate higher-quality SAR image new data through the confrontation of the generator and the discriminator; and finally, enhancing SAR image data through collaborative learning of the adversarial network and the target detection network.

Description

technical field [0001] The invention relates to data enhancement in the field of artificial intelligence, in particular to an image data intelligent enhancement technology based on a generative confrontation network, in particular to a SAR image data enhancement method for ship target detection. Background technique [0002] In the fields of marine monitoring and geological exploration, Synthetic Aperture Radar (SAR) has the characteristics of all-day, all-weather, high resolution, and wide surveying swath. Strong penetrating active microwave remote sensing technology is an indispensable and important means for ocean information acquisition and monitoring. Since the SAR image reflects the electromagnetic scattering characteristics of the target, the homogeneous clutter and artificial clutter contained in it reduce the accuracy of traditional target detection methods. In addition to common clutter false alarms, the azimuth ambiguity caused by the ship target itself is also a...

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): G06T5/00G06N3/08G06N3/04
CPCG06T5/00G06N3/08G06T2207/20081G06T2207/10044G06N3/045
Inventor 潘磊高翔廖泓舟
Owner 10TH RES INST OF CETC