Fine-grained human body posture estimation method based on wireless radio frequency signal
A human body posture, radio frequency technology, applied in the signal transmission system, computing, computer parts and other directions, can solve the problems of difficulty in large-scale use, power consumption, expensive laser radar, etc., to achieve easy deployment, high security, convenient deployment Effect
Inactive Publication Date: 2019-09-17
XI AN JIAOTONG UNIV
View PDF4 Cites 9 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, lidar is very expensive and power-hungry, making it difficult to use on a large scale in daily life and home environments
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0048] The present invention will be further described in detail below in conjunction with the accompanying drawings, which are explanations rather than limitations of the present invention.
[0049] refer to figure 1 , a fine-grained human body pose estimation method based on radio frequency signals, the specific steps are as follows:
[0050] Step 1, see figure 2 , the wireless transmitter uses a wifi transmitter with three antennas, and the wireless transmitter uses a wifi receiver with three antennas to establish a wifi field with a stable waveform.
[0051] Step 2, see image 3 , Deploy a time-stamp synchronization camera aligned with the wifi antenna next to the wireless transmitter to capture each frame of the video of the person, Figure 4 Shown is the time synchronization between the camera video frame and the WiFi signal.
[0052] Step 3. A person stands in the wifi field established between the wireless transmitter and the wireless transmitter to perform human bo...
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
Login to View More Abstract
The invention discloses a fine-grained human body posture estimation method based on a wireless radio frequency signal. The method is characterized in that aAwifi field is established by using the wireless transmitting ends of three antennas; when a user walks or makes a certain action in the wifi coverage area, the specific influence is generated on a wifi channel, the wireless receiving end receives the wifi signal and calculates the CSI value of the human body posture; a time stamp synchronous camera aligned with the WiFi antenna is used for capturing a figure video; a deep learning network is trained according to the CSI value and the video, and the human body posture is estimated by using the trained deep learning network, so that the single-person posture estimation is realized by using the wifi equipment, the convenience, usability and safety can be met while the higher identification accuracy is realized, the user does not need to carry any special equipment, the privacy life of the user cannot be recorded, and the method has the characteristics of convenience, easiness in deployment and high safety.
Description
technical field [0001] The invention relates to the technical field of human body posture perception, in particular to a fine-grained human body posture estimation method based on wireless radio frequency signals. Background technique [0002] At present, with the development of science and technology and the improvement of people's living standards, the concept of smart home and virtual reality technology have developed rapidly. In many applications in the field of computer vision, such as video surveillance, human-computer interaction, motion analysis, and virtual reality, the human body is the main object to be processed, and the recognition of human actions and behaviors is an indispensable link, which has an urgent It has become a very popular research direction in the field of computer vision. Human pose estimation is the process of obtaining the position of human bone points and the interconnection between bone points from a single RGB image or video, and finally out...
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
Login to View More IPC IPC(8): G06K9/00G06K9/62G08C17/02
CPCG08C17/02G06V40/20G06F18/214
Inventor 丁菡戴梓怡何旭王飞韩劲松黄东
Owner XI AN JIAOTONG UNIV