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

Small sample SAR image target recognition method based on improved prototype network

A prototype network, target recognition technology, applied in the field of SAR automatic target recognition, can solve hundreds of problems, and achieve the effect of reducing sensitivity, improving recognition accuracy, and improving recognition performance

Pending Publication Date: 2021-06-18
XIDIAN UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems existing in the prior art, the object of the present invention is to provide a small-sample SAR image target recognition method based on an improved prototype network, which solves the problem that hundreds or even more training samples are required for each type of target to be recognized in the traditional recognition method. The problem of achieving effective classification and recognition goals with a small number of labeled samples in each class

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
  • Small sample SAR image target recognition method based on improved prototype network
  • Small sample SAR image target recognition method based on improved prototype network
  • Small sample SAR image target recognition method based on improved prototype network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] refer to figure 1 , a kind of small sample SAR image object recognition method based on improved prototype network provided by the present invention, comprises the following steps:

[0035] Step 1. Obtain the training sample set and the small sample SAR image set to be identified; select C×m SAR images by category from the training sample set as the training support set, and the remaining A SAR image to form a training query set; similarly, the small-sample SAR image set to be identified is divided into a labeled support set and a query set to be identified;

[0036] Among them, the target category in the small sample SAR image set to be identified is different from the target category in the training sample set; the number of target categories in the two is the same, C is the total number of target categories to be trained, and m is the SAR of each target category in the training support set number of images, is the total number of SAR images corresponding to the k...

Embodiment 2

[0070] refer to figure 2 , a deep convolution-bidirectional long-short-time prototype neural network, including sequentially connected deep convolution-bidirectional long-short-time neural network, a prototype module and a classifier based on Euclidean distance; the deep convolution-bidirectional long-short-time The neural network includes a deep convolutional neural network and a bidirectional long-short-time neural network; the deep convolutional neural network includes a plurality of convolutional modules connected in sequence and a fully connected layer; each convolutional module includes a convolutional layer connected in sequence, a ReLU Activation layers, batch normalization layers, and max pooling layers.

[0071] In this embodiment, a maximum pooling layer may also be set after multiple convolutional layers, ReLU activation layers, and batch normalization layers.

[0072] like figure 2Shown: In this example, the construction includes eight convolutional layers, ei...

Embodiment 3

[0075] refer to image 3 , a deep convolution-bidirectional long-short-time prototype neural network training method, comprising the following steps:

[0076] Step 1. Obtain training sample set and test sample set; select C×m SAR images by category from the training sample set as the training support set, and the remaining SAR images form a training query set; similarly, the test sample set is divided into a test support set and a test query set;

[0077] Among them, C is the total number of target categories to be trained, m is the number of SAR images of each target category in the training support set, is the total number of SAR images corresponding to the kth class target in the training sample set; the test support set is a labeled sample, and the test query set is an unlabeled sample;

[0078] Step 2, using the training support set and the training query set to train the deep convolution-bidirectional long-short-time prototype neural network to obtain the trained dee...

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 technical field of radar image processing, and particularly relates to a small sample SAR image target recognition method based on an improved prototype network, which can be used for SAR automatic target recognition under a small sample condition. The method comprises steps of acquiring a training sample set and a to-be-recognized small sample SAR image set, constructing a deep convolution-bidirectional long-short time prototype neural network, namely an improved prototype network, adopting a training support set and a training query set to train the deep convolution-bidirectional long-short time prototype neural network, and obtaining a target recognition result of the small sample SAR image. According to the method, a new network structure is constructed, so that the problem that each type of to-be-recognized target needs hundreds of or even more training samples in a traditional recognition method is solved, and the targets are effectively classified and recognized by using a small number of labeled samples in each type.

Description

technical field [0001] The invention relates to the technical field of radar image processing, in particular to a small sample SAR image target recognition method based on an improved prototype network, which is a SAR automatic target recognition method and can be used for SAR automatic target recognition under small sample conditions. Background technique [0002] Synthetic Aperture Radar (SAR) is an imaging radar with high resolution in both range and azimuth directions. Because of its all-day, all-weather, and long-distance working capabilities, it has been widely used in battlefield reconnaissance, disaster forecasting, and ocean observation. Automatic Target Recognition (ATR) is an algorithm based on a computer system that acquires data from sensors, extracts features, and automatically obtains target categories. Different from optical imaging, single-polarization SAR images use grayscale to represent the intensity of target scattering. At the same time, due to the inf...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/082G06N3/045G06F18/24133G06F18/214
Inventor 周峰郭欣仪王力田甜白雪茹石晓然
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