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

Satellite identification method of ISAR image

An image and satellite technology, which is applied in the field of satellite target recognition of ISAR two-dimensional images, can solve the problem that the accuracy rate cannot reach the ideal state, and achieve the effect of simplifying the target recognition process, good generalization ability, and good applicability

Inactive Publication Date: 2020-01-17
PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV
View PDF4 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The accuracy of the satellite target features extracted by the above methods in the satellite target recognition of ISAR images is not ideal.

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
  • Satellite identification method of ISAR image
  • Satellite identification method of ISAR image
  • Satellite identification method of ISAR image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] The embodiment of the present invention provides a DCNN-based satellite target recognition method for ten kinds of satellite target ISAR images, respectively named as Number-1, Number-2, Number-3, Number-4, Number-5, and Number-6 , Number-7, Number-8, Number-9, and Number-10. Among them, the image sample data of each satellite target is more than 1000 pieces after amplification, figure 1 A flow chart of a satellite target recognition method for ISAR images is given. Such as figure 1 As shown, Embodiment 1 of the present invention discloses a satellite target recognition method of an ISAR image, including:

[0058] Step 1: Take the modulo value of the original complex data of the ISAR image to obtain the magnitude image of the ISAR, and perform normalization processing on the magnitude image of the ISAR to obtain a normalized magnitude image of the ISAR.

[0059] Such as figure 2 As shown, the raw data (Raw Data) of the ISAR image is a data matrix with a style such ...

specific example

[0094] In this example, there are a total of 10,000 images after the ISAR images of ten satellite targets are amplified, of which the train data set contains 7,000 images, the val data set contains 1,000 images, and the test data set contains 2,000 images. Among them, the train data set and the val data set are used for the training of the DCNN network structure of the satellite target recognition of the ISAR image, and the DCNN network structure model of the satellite target recognition of the ISAR image is obtained; the test data set is used for the DCNN of the satellite target recognition of the ISAR image Testing of network structure models. Figure 9 The test results of the satellite recognition network structure model of the test set in ISAR images are given. From the recognition results of the ten satellite targets in the figure, it can be concluded that the final average recognition rate of the test set by the satellite recognition network model of the ISAR image Top-1...

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 satellite identification method for an ISAR image. The satellite identification method comprises the following steps: making two-dimensional real image sample data of an ISAR;amplifying the manufactured two-dimensional real image data of the ISAR, and randomly dividing the amplified image into a training set, a verification set and a test set; making satellite target tagsfor the training set, the verification set and the test set; constructing a deep convolutional neural network (DCNN) structure for satellite identification of an ISAR (Inverse Synthetic Aperture Radar) image; setting DCNN network training parameters suitable for the ISAR image; training the DCNN by using the training set and the verification set to obtain a satellite target recognition network model of the ISAR image; and testing the network model by using the test set, and verifying and identifying the performance of the network model. According to the method, manpower and time can be greatly saved, the uncertain influence and artificial subjective judgment errors caused by manual feature selection on the satellite target recognition result are reduced, and the satellite target recognition precision and recognition efficiency of the ISAR image are greatly improved.

Description

technical field [0001] The invention belongs to the technical field of radar target recognition, and relates to a satellite recognition method of an ISAR (Inverse Synthetic Aperture Radar, ISAR) image, in particular to a satellite target recognition method of an ISAR two-dimensional image. Background technique [0002] As countries all over the world attach great importance to spaceflight and the rapid development of civil spaceflight, more and more satellites are launched into space, and space becomes increasingly crowded, more competitive and confrontational. How to effectively perceive the space situation and then control the space has become a major problem faced by all aerospace powers. As an important means of effectively sensing the space situation, broadband radar has the characteristics of all-day, all-weather, and high resolution. It plays an important role in the space target recognition system and has been widely used. [0003] There are two main identification ...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V20/13G06V2201/07G06N3/045
Inventor 李智张刚李雪薇徐灿尹灿斌方宇强林财永程文华
Owner PLA PEOPLES LIBERATION ARMY OF CHINA STRATEGIC SUPPORT FORCE AEROSPACE ENG UNIV