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

Training method of convolutional neural network used for SAR image ship classification, classification method of the convolutional neural network and ship classification model

A technology of convolutional neural network and training method, applied in biological neural network model, neural architecture, character and pattern recognition, etc., which can solve the problems of a large amount of training data, time-consuming labeling data, difficulty in obtaining, etc.

Active Publication Date: 2018-10-16
AEROSPACE INFORMATION RES INST CAS
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the bottleneck of using a deep learning model is that it requires a large amount of training data, and obtaining a large amount of labeled data is time-consuming and difficult to obtain

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
  • Training method of convolutional neural network used for SAR image ship classification, classification method of the convolutional neural network and ship classification model
  • Training method of convolutional neural network used for SAR image ship classification, classification method of the convolutional neural network and ship classification model
  • Training method of convolutional neural network used for SAR image ship classification, classification method of the convolutional neural network and ship classification model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In the following, specific embodiments of the present invention will be described in detail with reference to the accompanying drawings, but it is not a limitation of the present invention.

[0041] It should be understood that various modifications can be made to the embodiments disclosed herein. Therefore, the above description should not be regarded as a limitation, but merely as an example of an embodiment. Those skilled in the art will think of other modifications within the scope and spirit of this disclosure.

[0042] The drawings included in the specification and constituting a part of the specification illustrate the embodiments of the present disclosure, and are used to explain the present disclosure together with the general description of the present disclosure given above and the detailed description of the embodiments given below principle.

[0043] These and other characteristics of the present invention will become apparent from the following description of p...

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 provides a training method of a convolutional neural network used for SAR image ship classification and a classification method of the convolutional neural network. The training method includes the steps that slices, with ship types, in an SAR image are obtained; based on the slices with the ship types, the convolutional neural network used for SAR image ship classification is trained so as to reach preset training precision, wherein on the basis of a first model, a first full-connection layer of the first model is removed, and a second full-connection layer is added according tothe number of the ship types of the slices with the ship types to construct the convolutional neural network used for SAR image ship classification. According to the training method, the convolutional neural network used for SAR image ship classification can be trained under the condition that a small quantity of training data exist so as to reach the preset training precision. The convolutionalneural network which reaches the preset training precision is used for SAR image ship classification, and the ship classification precision of the convolutional neural network can reach 97.54%.

Description

Technical field [0001] This application relates to the field of remote sensing, in particular to a training method and a classification method of a convolutional neural network for SAR image ship classification. Background technique [0002] Since 2007, many high-resolution SAR satellites have been successfully launched, such as Cosmo-SkyMed, TerraSAR-X, ALOS-2PALSAR-2, Gaofen-3, etc., based on the resolution of high-resolution satellite SAR images obtained by the satellites More than 3 meters, it contains a wealth of information on ground features, such as the geometric characteristics of ships, which makes it possible to distinguish different types of ships. [0003] Deep learning models (for example, convolutional neural networks) can automatically learn the information representing features in SAR images, and provide corresponding end-to-end processing without manual intervention, thereby saving feature extraction and selection and optimal classification Time of the device. T...

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): G06K9/00G06K9/62G06N3/04
CPCG06V20/13G06N3/045G06F18/24G06F18/214
Inventor 王超王原原张红
Owner AEROSPACE INFORMATION RES INST CAS