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

Individual target recognition method of civil aviation passenger plane

A target recognition and airliner technology, applied in the field of target recognition, can solve the problems of unreachable efficiency, channel influence on signal, high time complexity, etc., and achieve the effect of improving detection accuracy, reducing time complexity, and high detection accuracy

Active Publication Date: 2018-12-11
10TH RES INST OF CETC
View PDF8 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when detecting in an image, it is necessary to perform sliding window detection on different scales of the image, and using a deep learning structure for sliding window detection cannot achieve ideal efficiency.
There are two main problems in traditional target detection: one is that the region selection strategy based on the sliding window is not targeted, the time complexity is high, and the window is redundant; the other is that the manually designed features are not very robust to changes in diversity. sex
[0006] With the rapid development of modern science and technology, the space electromagnetic environment is becoming increasingly complex, noise interference, and the influence of channels on signals make it difficult for conventional identification methods and theories to adapt to actual needs, and cannot effectively identify communication signals accurately

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
  • Individual target recognition method of civil aviation passenger plane
  • Individual target recognition method of civil aviation passenger plane
  • Individual target recognition method of civil aviation passenger plane

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] refer to figure 1 . According to the present invention, the recognition system is composed of a module for capturing aircraft communication signals, a module for preparing data sets, a module for constructing a neural network, a module for training a neural network, and a module for identifying the aircraft to which communication signals belong. The capture aircraft communication signal module starts from the original pulse waveform of the ADS_B signal emitted by the aircraft itself, captures the aircraft communication signal through the antenna, and receives and saves the broadcast communication signal ADS_B sent by the aircraft through high-speed acquisition card sampling; the preparation data set module prepares data Set, cut the received ADS_B signal composed of pulse trains into packets, save each pulse in the form of an image, convert the identification features of the signal into the spatial structure features of the image, and interpret the ADS_B data at the sam...

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 an individual target recognition method of a civil aviation passenger plane, aiming at providing a deep learning method with a high recognition rate. The invention is realized by the following technical scheme: a convolutional neural network identification system is formed by capturing an aircraft communication signal module, preparing a dataset module, constructing a neuralnetwork module, training the neural network module, identifying a communication signal and identifying an aircraft to which the communication signal belongs, wherein capturing the aircraft communication signal module starts from the aircraft original pulse waveform itself and samples the ADS_B original intermediate frequency signal through a high-speed acquisition card to save the ADS_B originalintermediate frequency signal to the local area; preparing the data set module slices the collected communication signals into images, and converts the recognition features of ADS_B communication signals into the spatial structure features of images; constructing the neural network module is to evaluate the number of layers of depth convolution through the network according to the number of targets; training the neural network module generates image samples based on a convolutional neural network algorithm for training. Therefore, an identified signal is obtained.

Description

technical field [0001] The invention relates to a target recognition method that applies deep learning to the field of communication signal recognition, in particular to a method for individual target recognition of civil aviation passenger aircraft based on a deep convolutional neural network. Background technique [0002] Aircraft detection based on optical remote sensing images has always been a research hotspot in the field of target recognition. Airport and aircraft target recognition is a typical application in remote sensing data analysis. Target recognition is one of the core issues in the field of computer vision, and aircraft target recognition is an important application in the civilian field. Scholars at home and abroad have done a lot of research on target recognition. Each target recognition method has its own advantages and disadvantages, and has a certain scope of application. Image Preprocessing and Segmentation Image preprocessing is an essential link in ...

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): G06N3/08G06N3/063G06N3/04G06K9/00
CPCG06N3/063G06N3/084G06N3/045G06F2218/08
Inventor 徐雄张希会王成刚贺文娇李思奇
Owner 10TH RES INST OF CETC
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