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

Fast learning SAR automatic target recognition method

An automatic target recognition and fast technology, applied in neural learning methods, scene recognition, character and pattern recognition, etc., can solve the problems of long training time and low recognition accuracy, and achieve short training time, high recognition rate, and fast learning. Effect

Active Publication Date: 2018-11-30
ZHEJIANG UNIV
View PDF5 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the deficiencies of the current SAR automatic target recognition technology, the purpose of the present invention is to provide a fast learning SAR automatic target recognition method, which mainly solves the problems of long training time and low recognition accuracy in the prior art

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
  • Fast learning SAR automatic target recognition method
  • Fast learning SAR automatic target recognition method
  • Fast learning SAR automatic target recognition method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The present invention will be described in detail below according to the accompanying drawings.

[0041] refer to figure 1 , the specific implementation steps of the present invention are as follows:

[0042] 1) Obtain the SAR target image data and mark it according to the target category to form a training set.

[0043] For the multiple types of targets involved in the target recognition task, several SAR images are collected for each type as training samples.

[0044] 2) Perform data enhancement and preprocessing on the images in the training set.

[0045] 2.1) Data enhancement: Random translation, flipping, rotation and scaling operations are performed on each SAR image in the training set, and the generated derivative training samples are labeled with the same label as the original training samples to obtain an enhanced training sample set;

[0046] 2.2) Preprocessing: Carry out image preprocessing according to formula (1):

[0047]

[0048] Where x represent...

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 fast learning SAR automatic target recognition method. The method includes: acquiring SAR target image data and labeling the SAR target image data according to a target category to form a training set; performing data enhancement and preprocessing on the training set image data; constructing a dense connection convolutional neural network, and inputting training samples into the network for training; and finally, preprocessing the samples to be classified and inputting the pre-processed the samples to be classified into the network to perform recognition. The SAR automatic target recognition training time of the method is short, the recognition rate is high, and the automation degree is high.

Description

technical field [0001] The invention belongs to the technical field of radar data processing, and in particular relates to a SAR automatic target recognition method, which mainly solves the problems of low recognition accuracy and long training time of the existing SAR automatic target recognition technology. Background technique [0002] Synthetic Aperture Radar (SAR) is an active high-resolution imaging radar, which can obtain images similar to visible light images under the weather conditions of cloud cover and low visibility. SAR has strong penetrating power, high resolution, and large-scale monitoring capabilities. These advantages make it have significant advantages in applications such as environmental monitoring, ocean monitoring, map mapping, and military reconnaissance. Therefore, the research on SAR radar-related technologies has attracted more and more attention from all over the world, and SAR image automatic target recognition is one of the most important techn...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/13G06V2201/07G06N3/048G06N3/045G06F18/24G06F18/214
Inventor 万子宁刘兴高
Owner ZHEJIANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com