Unmanned aerial vehicle target recognition and classification method based on deep learning

A technology of target recognition and deep learning, which is applied in the field of UAV radio signal monitoring, can solve the problems of unstable target recognition and low signal-to-noise ratio, increase the monitoring range and detection efficiency, improve anti-noise performance, and improve The effect of target recognition accuracy

Active Publication Date: 2019-08-02
CHINA ELECTRONIC TECH GRP CORP NO 38 RES INST
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the electromagnetic environment in practice is very complex, various radio signals and noise are mixed together, and the signal-to-noise ratio is relatively low. In this case, it is difficult to correctly extract these characteristic parameters, which makes the target recognition effect unstable.

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
  • Unmanned aerial vehicle target recognition and classification method based on deep learning
  • Unmanned aerial vehicle target recognition and classification method based on deep learning
  • Unmanned aerial vehicle target recognition and classification method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0031] Such as figure 1 As shown, the overall workflow of UAV signal recognition classification is as follows:

[0032] After the radio signal sent by the drone is detected by the scout, the data is collected and sent to the data processing center. After signal preprocessing and deep learning algorithm analysis, the target recognition and classification results of the drone are obtained, and the analysis results are combined with the collected data. The data is stored together in the database.

[0033] Such as figure 2 As shown, a deep learning algorithm architecture diagram for UAV target recognition and classification is given. The deep neural network algorithm consists of an input layer, three hidden layers, and an output layer. The detected UAV signal Perform preprocessing such as resampling and Fourier transform to obtain time-domain waveform (data length is n) and spectral feature data (data length is N) respectively. n+N neurons. The time and frequency domain data ...

Embodiment 2

[0036] Such as image 3 As shown, this embodiment provides another deep learning algorithm architecture diagram for UAV target recognition and classification. The deep neural network algorithm is composed of an input layer, a stacked autoencoder, a fully connected layer, and an output layer. The stacked autoencoder consists of a two-layer autoencoder network. The detected UAV signal is subjected to preprocessing such as resampling and Fourier transform to obtain time-domain waveform (data length is n) and spectral characteristic data (data length is N). The time domain and spectrum data pass through two layers of stacked autoencoders respectively, and after information mining in the time domain or frequency domain, they are merged, input to the fully connected layer, and finally to the output layer. The output layer is the probability of each target category, and the category with the highest selection probability is the target recognition result of the UAV signal. Among the...

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 an unmanned aerial vehicle target recognition and classification method based on deep learning, and the method comprises the specific processing steps: (1), carrying out the collection through a radio monitoring means, and obtaining a link signal of a small civil unmanned aerial vehicle; (2) sending the link signal to a data processing center, and carrying out signal preprocessing to obtain a time domain characteristic and a frequency domain characteristic of the signal; (3) inputting the time domain characteristics and the frequency domain characteristics of the signalinto a deep learning network for calculation, and outputting to obtain a target identification classification result of the signal; and (4) storing the acquired signal data and the identification result in a database, and if the acquired signal data and the identification result are newly discovered target categories, adding the newly discovered target categories to a signal identification library after manual confirmation. According to the unmanned aerial vehicle target identification classification method provided by the invention, the deep learning algorithm is applied to the field of unmanned aerial vehicle radio signal monitoring, so that the application bottleneck of a traditional radio signal analysis method is broken through, and the unmanned aerial vehicle signal monitoring and identification problems in low-altitude safety protection are solved practically.

Description

technical field [0001] The invention relates to the technical field of UAV radio signal monitoring, in particular to a method for identifying and classifying civilian UAV signals. Background technique [0002] At present, drones have been widely used in various fields, such as agricultural plant protection, geographic surveying and mapping, forest fire prevention, power inspection, etc. In addition, drones are also used in some illegal activities, such as terrorist activities with explosives, airport "black flight" incidents, etc. It can be seen that small civilian drones have brought serious low-altitude security threats, and it is a problem that needs to be solved urgently all over the world. In order to realize the monitoring, identification and effective control of UAVs, many scientific research institutions and enterprises at home and abroad have been working hard to explore the realization of UAV signal monitoring, identification and management countermeasures, but no...

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): G06K9/00G06N3/04G01V3/12
CPCG01V3/12G06N3/045G06F2218/12
Inventor 徐钦李臻黄双双苏志杰单志林王颖潘玉静李朝英胡佳黄穗朱秋君鄢雯
Owner CHINA ELECTRONIC TECH GRP CORP NO 38 RES INST
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap