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

UAV classification method and device

A classification method and unmanned aerial vehicle technology, applied in the field of pattern recognition, can solve the problems that the recognition system does not have all-weather and all-day working ability, limit the application range, etc., and achieve the effect of good recognition ability

Inactive Publication Date: 2017-11-17
TSINGHUA UNIV
View PDF2 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, the image-based recognition system does not have the ability to work around the clock, which limits its application range

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
  • UAV classification method and device
  • UAV classification method and device
  • UAV classification method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] An embodiment of the present invention provides a method for classifying drones, see figure 1 , the method includes:

[0044] S101: Acquiring time-domain data of the target UAV;

[0045] In this step, the radar is used to obtain the time domain data of the target UAV during flight. The radar is an electronic system that emits electromagnetic waves to irradiate the target and receives its echo, and performs target detection and target feature extraction. Compared with the image acquisition and processing system, the radar has the ability to work around the clock and all the time, with high detection accuracy, good real-time performance, less affected by environmental factors, and small discrimination errors.

[0046] S102: Transform the time-domain data into a time-frequency diagram;

[0047] In this step, a time-frequency analysis tool is used to analyze the time-domain data collected by the radar in step S101 to obtain a time-frequency diagram of the target UAV; Le ...

Embodiment 2

[0054] An embodiment of the present invention provides a method for classifying drones. On the basis of the first embodiment above, the method further includes:

[0055] The feature vectors in the training samples are sent to the support vector machine for classification learning.

[0056] In this step, the training samples are selected from the collected total samples, and a part of the total samples are used as training samples to train the support vector machine to improve the accuracy of the classification of the support vector machine; the rest of the samples are used as test samples. The support vector machine for test classification.

[0057] It can be known from the above description that the classification accuracy of the support vector machine can be improved by learning the support vector machine.

[0058] On the basis of the first and second embodiments above, the X-band continuous wave radar is used to acquire the time-domain data of the target UAV.

[0059] In th...

Embodiment 3

[0082] An embodiment of the present invention provides a drone classification device, see Figure 7 , the device consists of:

[0083] Acquisition unit 10, for obtaining the time-domain data of target UAV;

[0084] A conversion unit 20, configured to transform the time-domain data into a time-frequency diagram;

[0085] The extraction unit 30 is used to extract the feature vector representing the motion state of the target drone in the time-frequency diagram;

[0086] The classification unit 40 is configured to send the feature vector to the support vector machine to classify the target UAV.

[0087] The learning unit 50 is configured to send the feature vectors in the training samples to the support vector machine for classification learning.

[0088] It can be seen from the above description that the UAV classification device provided by the embodiment of the present invention can effectively identify the UAV category, improve the classification accuracy and reduce the in...

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 UAV classification method and device. The method comprises a step or unit of obtaining time domain data of a target UAV; a step or unit of converting the time domain data into a time-frequency map; a step or unit of extracting a feature vector representing the motion state of the target UAV motion from the time-frequency map; and a step or unit of sending the feature vector into a support vector machine to classify the target UAV. According to the invention, the classification is performed by acquisition of the time-domain data of the UAV in flight and extraction of the feature vector from the time-domain data as the basis for the classification of the UAV, the effective recognition of the UAV class is realized, the classification accuracy is improved and the influence of environmental factors and the error of judgment are reduced; and by the use of the support vector machine for classification, a good identification capability is gained for the type of samples with a small number.

Description

technical field [0001] The invention relates to the technical field of pattern recognition, in particular to a method and device for classifying unmanned aerial vehicles. Background technique [0002] In recent years, the UAV industry has developed rapidly, and its role in aerial photography, agriculture, monitoring, surveying and mapping has become increasingly apparent. However, with the explosive growth of the number of drones, the "black flying" incidents of drones occur frequently, which repeatedly threatens the safety of civil aviation. Additionally, small drones may form ideal platforms for swift and stealthy criminal or even terrorist attacks. Drones "flying black" in the city also have the risk of falling from high altitudes and injuring people and causing privacy leaks. The hidden dangers cannot be ignored. Therefore, the correct and rapid identification of UAVs is of great significance for judging the category status of UAVs, determining their threat level, and ...

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): G06K9/62
CPCG06F18/2411
Inventor 李刚章鹏飞
Owner TSINGHUA UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com