Human body recognition method based on multi-base radar micro-Doppler and convolutional neural network

A convolutional neural network and human body recognition technology, applied in the field of radar target recognition, can solve the problems of difficult to meet complex and diverse target recognition tasks, difficult to make full use of correlation, etc., so as to alleviate the difference of echo signals and improve the recognition accuracy. , good flexibility

Active Publication Date: 2018-11-23
TSINGHUA UNIV
View PDF1 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the classic target recognition method has many shortcomings mentioned above, and it is difficult to meet complex and diverse target recognition tasks; the simple majority vote fusion is difficult to make full use of the correlation between the data of each node, and the fusion effect still has room for improvement

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
  • Human body recognition method based on multi-base radar micro-Doppler and convolutional neural network
  • Human body recognition method based on multi-base radar micro-Doppler and convolutional neural network
  • Human body recognition method based on multi-base radar micro-Doppler and convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] The human body recognition method based on multistatic radar micro-Doppler and convolutional neural network proposed by the present invention, its flow chart is as follows figure 1 shown, including the following steps:

[0038] (1) Acquisition of known types of human body time domain echo signals:

[0039] A multistatic radar is used to collect time-domain echo signals of a known type of human body. The multistatic radar includes three receiving nodes with different positions, and the three receiving nodes simultaneously collect three-way time-domain echo signals s of the human body. 1 (t),s 2 (t),s 3 (t), where t is the acquisition time; in one embodiment of the present invention, the multistatic radar used is a chirp radar with a carrier frequency of 2.4GHz, a bandwidth of 45MHz, and a pulse repetition frequency of 5kHz, such as figure 2 As shown, it includes three nodes N1, N2, N3 arranged in a straight line at equal distances, among which N1, N2, N3 are all rec...

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 relates to a human body recognition method based on multi-base radar micro-Doppler and a convolutional neural network, and belongs to the technical field of radar target recognition. According to the method, the multi-base radar is used so that the echo signal difference caused by the change of view can be alleviated, the recognition robustness can be enhanced and the recognition accuracy can be enhanced. The convolutional neural network is applied to perform data processing without manual feature design so as to have certain universality and excellent recognition accuracy performance. According to the method, the transfer learning technology is used, the RGB optical image is utilized in the convolutional neural network to pre-train the weight and the three-channel multi-resolution time-frequency graph having the similar RGB optical image is used as the input of the convolutional neural network so that the pre-training weight dimension is matched, more information is provided in comparison with that of the single-resolution time-frequency graph. Great recognition accuracy can be obtained in multiple human body recognition tasks by the method.

Description

technical field [0001] The invention relates to a human body recognition method based on multistatic radar micro-Doppler and convolutional neural network, and belongs to the technical field of radar target recognition. Background technique [0002] Using radar to observe targets has the advantages of long-distance and all-weather all-weather. The radar micro-Doppler effect refers to the additional Doppler effect caused by the vibration and rotation of the target relative to the center of mass on the basis of the Doppler effect caused by the movement of the center of mass of the target. The micro-Doppler frequency shift of the target changes with time The law of change, that is, the micro-Doppler time-frequency map, can reflect the target's motion attitude and structural information, so it can be used as a feature of target recognition for application scenarios such as aircraft recognition, human posture recognition, and gesture recognition. Based on micro-Doppler features 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
Patent Type & Authority Applications(China)
IPC IPC(8): G01S13/90G01S7/41
CPCG01S7/417G01S13/90G01S13/9017G01S13/9047
Inventor 李刚陈兆希
Owner TSINGHUA UNIV
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