A CSI-based method for counting human continuous movements
A counting method and technology of human body movements, applied in computing, computer components, instruments, etc., can solve problems such as counting continuous human body movements that have not been proposed, and achieve the effects of low cost, easy deployment, and strong scalability
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0036] Such as figure 1 As shown, the present invention provides a CSI-based human body continuous motion counting method for a human body continuous motion counting and recognition system including a transmitter and a receiver equipped with a wireless network card, wherein the transmitter is a router, and the transmitter is provided with N t An antenna on the transmitting end, a computer with a wireless network card equipped with a CSI tool kit inside the receiver, a CSI information reading interface on the receiver, and a N on the receiver r A receiving end antenna, the human body continuous motion counting method includes the following steps
[0037] Step 1. Signal collection: When the human body is in the above-mentioned human body continuous motion counting and recognition system, read the CSI information file generated by the human body motion file within T time through the CSI information reading interface of the receiver, and generate the human body motion file within T...
Embodiment 2
[0056] The difference from Example 1 is that, see figure 2 as shown,
[0057] Also includes step five, extracting action features:
[0058] Will Z t,r In the waveform file to be calculated after smoothing, record the time interval between two adjacent peaks, and then according to the recorded time interval, obtain the time series of multiple actions in the human body action file within T time, and then according to For this time series, intercept the HP t,r In (2), the output waveforms corresponding to the corresponding time series are subjected to wavelet transformation on the output waveforms corresponding to all the intercepted time series to obtain the action waveform of each movement of the human body within T time, and the action waveform is the action produced by the human body feature;
[0059] Step 6: Action Classification:
[0060] According to the multiple motion waveforms of the human body's motions within T time obtained in step 5, match with the preset moti...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


