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

Indoor Human Pose Recognition Method Based on Weighted Joint Distance Time-Frequency Transformation

A technology of combined distance and time-frequency transformation, applied in the field of radar, can solve the problems of invasion of privacy, expansion of sensor network traffic, and great impact on the video image environment, achieving high range resolution, strong anti-interference ability, and high classification accuracy. Effect

Active Publication Date: 2020-04-10
NANJING UNIV OF SCI & TECH
View PDF6 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, video image information will cause the expansion of sensor network traffic, and video image detection is greatly affected by the environment, and privacy is violated to a certain extent.
Wearable human gesture recognition devices also have two major disadvantages: data memory and applicability
Existing research mainly uses radar to extract Doppler information of some periodic human body postures, such as arm swing walking, continuous jumping, squatting and other actions, which have very large limitations

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
  • Indoor Human Pose Recognition Method Based on Weighted Joint Distance Time-Frequency Transformation
  • Indoor Human Pose Recognition Method Based on Weighted Joint Distance Time-Frequency Transformation
  • Indoor Human Pose Recognition Method Based on Weighted Joint Distance Time-Frequency Transformation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0115] An indoor human gesture recognition method based on weighted joint distance-time-frequency transformation, comprising the following steps:

[0116] Step 1. In image 3 In the scene diagram of the experiment, there are 6 actions measured in the experiment, (1) turning around, (2) bending over, (3) sitting, (4) squatting, (5) jumping and (6) falling. There are 4 subjects in the experiment, each action is performed 10 times, and finally 240 packets of data are obtained.

[0117] Step 2: Intercepting the data including the human posture after filtering for 4 seconds, and selecting effective range gates, the energy contained in these range gates accounts for 95% of the total energy of the signal.

[0118] Step 3. Obtain the weighting coefficient according to the energy size of each effective range gate, use the short-time Fourier transform STFT to obtain the time-frequency distribution diagram of each effective range gate, and then use the time-frequency distribution diagra...

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 indoor human body posture recognition method based on weighted joint distance-time-frequency transformation. In the method, firstly, the indoor human body posture data collected by ultra-wideband radar is filtered by MTI, the data including human body posture is intercepted, and an effective distance gate is selected; The weighted joint distance time-frequency transformation is used to obtain the joint distance time-frequency distribution map, and the characteristic parameters of the body envelope in the figure are extracted; then the machine learning algorithm is used to determine the mapping relationship between different postures and characteristic parameters; finally, according to the obtained mapping relationship, Determine the type of human gesture. The method of the invention is effective and feasible, has reliable performance, and can accurately identify different human body postures in the room.

Description

technical field [0001] The invention belongs to the technical field of radar, in particular to an indoor human body posture and recognition method based on ultra-wideband radar. Background technique [0002] Human pose recognition is one of the challenging research hotspots in recent years. It has broad application prospects in the fields of security monitoring, human-computer interaction and medical care. In addition, as my country's population aging phenomenon is becoming more and more serious, the proportion of the elderly in the entire population is gradually increasing, and the social pressure faced by children is also increasing. How to effectively carry out early warning and effective monitoring of the safety problems faced by the elderly indoors at home is a major problem facing the whole society. With the development of computer technology, the monitoring system based on human body posture recognition can provide effective early warning and notify family members b...

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 Patents(China)
IPC IPC(8): G01S13/08G01C21/20G06K9/62
CPCG01C21/206G01S13/08G06F18/2411
Inventor 顾陈廖志成洪弘李彧晟孙理朱晓华丁传威邹宇
Owner NANJING UNIV OF SCI & TECH