CN111631723A - Indoor passive dynamic human body detection method based on channel state information - Google Patents
Indoor passive dynamic human body detection method based on channel state information Download PDFInfo
- Publication number
- CN111631723A CN111631723A CN202010438361.XA CN202010438361A CN111631723A CN 111631723 A CN111631723 A CN 111631723A CN 202010438361 A CN202010438361 A CN 202010438361A CN 111631723 A CN111631723 A CN 111631723A
- Authority
- CN
- China
- Prior art keywords
- human body
- channel state
- state information
- frequency
- receiver
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1118—Determining activity level
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The invention belongs to the technical field of indoor dynamic human body detection based on channel state information, and particularly relates to an indoor passive dynamic human body detection method based on channel state information. The invention mainly aims at the detection accuracy rate of dynamic human body in indoor environment and the detection accuracy rate when the human body moves at different speeds and postures. And extracting characteristics of the acquired data according to the influence of the human body movement on the signal frequency in the channel state information. The carrier frequency offset caused by the asynchronous clocks between the transmitting end and the receiving end can influence the phase information in the experimental data and correct the phase information. Secondly, the conversion of the frequency information amplifies the small change, so that the influence of the small moving speed on the channel state information can be adapted. The method can improve the detection accuracy of the method for the moving human bodies with different speeds and postures in the indoor environment through the conversion and processing of the frequency in the channel state information of the receiving end.
Description
Technical Field
The invention belongs to the technical field of indoor dynamic human body detection based on channel state information, and particularly relates to an indoor passive dynamic human body detection method based on channel state information.
Background
The indoor passive dynamic human body detection method based on the channel state information can well cope with the detection of the moving human body under various conditions. Indoor dynamic human bodies have certain speed and limb swing, and compared with static human bodies, the dynamic human bodies can generate larger CSI fluctuation and richer information. For the detection of indoor dynamic human body, when the movement speed and posture of the human body change, the propagation of wireless signals in the room will be affected. The research is carried out by utilizing the frequency information change of the channel state information subcarrier, and the orthogonal frequency division multiplexing technology converts the channel state information into a richer subcarrier form with higher dimensionality, so that richer information about human body movement can be extracted from the channel state information. In the description of the motion state of the human body, when the human body moves at different postures and speeds, the generated channel state information fluctuates differently, but the result can reflect whether the human body moves or not. By depicting the movement of the human body, neglecting the influence of the local action on the channel state information, extracting the result of the movement of the human body on the Doppler frequency shift, and converting the speed information of the human body into Doppler frequency shift information for judgment. Compared with the method that all subcarrier information is used for judgment, the irrelevant data amount is reduced more greatly by extracting the main information. Finally, the detection of indoor dynamic human body is realized.
Disclosure of Invention
The invention aims to provide an indoor passive dynamic human body detection method based on channel state information, which is used for detecting a moving human body existing indoors.
The purpose of the invention is realized by the following technical scheme: the method comprises the following steps:
step 1: arranging a transmitter and a receiver, wherein the receiver acquires channel state information in a period of time;
step 2: preprocessing the acquired channel state information, extracting phase amplitude to correct, and acquiring real phase amplitude information;
and step 3: calculating a minute frequency change due to the movement of the human body through fast Fourier transform; screening out a frequency change interval which accords with a range in the channel state information according to a frequency threshold determined by the Doppler frequency shift; extracting the maximum value, the minimum value and the median of the frequency change as characteristic values to form a characteristic vector;
when the human body approaches the receiver at a certain speed, the frequency of the signal received by the receiver will increase; when the human body moves away from the receiver at a certain speed, the frequency of the signal received by the receiver will decrease; the doppler shift versus the velocity and signal of the moving source can be formulated as:
wherein f is the signal frequency; c is the propagation velocity of the electromagnetic wave; v is the speed of the human body movement; theta is an included angle between the human body and the receiver and the transmitter;
and 4, step 4: dividing the extracted feature vectors into a training set and a test set; training a Gaussian mixture model by using a training set to obtain a classifier; and inputting the test set into a classifier to obtain a classification result.
The invention has the beneficial effects that:
the invention mainly aims at the detection accuracy rate of dynamic human body in indoor environment and the detection accuracy rate when the human body moves at different speeds and postures. And extracting characteristics of the acquired data according to the influence of the human body movement on the signal frequency in the channel state information. The carrier frequency offset caused by the asynchronous clocks between the transmitting end and the receiving end can influence the phase information in the experimental data and correct the phase information. Secondly, the conversion of the frequency information amplifies the small change, so that the influence of the small moving speed on the channel state information can be adapted. The method can improve the detection accuracy of the method for the moving human bodies with different speeds and postures in the indoor environment through the conversion and processing of the frequency in the channel state information of the receiving end.
Drawings
FIG. 1 is a general flow diagram of the present invention.
Fig. 2 is a schematic diagram of the position of an indoor human body relative to a receiver and a transmitter in an embodiment of the invention.
Fig. 3 is a schematic diagram of indoor human body movement according to an embodiment of the present invention.
FIG. 4 is a graph comparing experimental detection accuracy of the present invention with other existing methods.
Fig. 5 is a comparison graph of human body detection accuracy for different movement postures in the invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The invention provides an indoor passive dynamic human body detection method based on channel state information, which analyzes the defects of the existing indoor dynamic human body detection method.
The existing method only provides a processing scheme for judging whether the human body moves or not when detecting the dynamic human body, only considers the limb movement of the human body when identifying the human body movement, and ignores the research on whether the human body moves or not. The detection of dynamic human body proposed in the present invention needs to be studied from two aspects: the speed of movement and the posture of the motion.
The invention mainly aims at the detection accuracy rate of dynamic human body in indoor environment and the detection accuracy rate when the human body moves at different speeds and postures. And extracting characteristics of the acquired data according to the influence of the human body movement on the signal frequency in the channel state information. The carrier frequency offset caused by the asynchronous clocks between the transmitting end and the receiving end can influence the phase information in the experimental data and correct the phase information. Secondly, the conversion of the frequency information amplifies the small change, so that the influence of the small moving speed on the channel state information can be adapted. The method can improve the detection accuracy of the method for the moving human bodies with different speeds and postures in the indoor environment through the conversion and processing of the frequency in the channel state information of the receiving end.
Example 1:
as shown in fig. 1, the present invention is realized by:
(1) and (5) acquiring experimental data. The receiver and the transmitter are arranged indoors, and an experimenter moves in a path between the transmitter and the receiver and is used for collecting channel state information.
(2) Preprocessing the collected sample, eliminating environmental noise and electromagnetic fluctuation existing in the experimental number, correcting the phase and amplitude in the sample data, and acquiring the phase information of a real rule.
(3) And (5) extracting features. And acquiring the tiny frequency change generated by the movement of the human body according to the fast Fourier transform, and extracting the characteristics.
(4) And classifying the classification result by using a classifier. The feature values are classified using an efficient gaussian mixture model.
The detection scheme of the indoor moving human body is as follows:
(1) first, data is acquired. The transmitter and receiver were placed indoors at a distance of 3 meters and the experimenter acted on the line-of-sight path between the receiver and the transmitter. In the experiment, a router with two gain antennas is used as a transmitter, and a notebook computer with 3 external antennas is used as a receiver. And acquiring channel state information of the network card of the notebook computer through the CSI tool. The sampling frequency in the experiment was 1000 Hz.
(2) In the data preprocessing stage, after the collected data is decoded by the equalization decoder, the slight channel state change generated by the human body movement is removed. It is necessary to first process the phase and amplitude information and obtain the amplitude and phase information. Firstly, the channel state information in the window is subjected to phase correction to obtain real phase amplitude information. When a human body approaches a receiver at a certain speed, the frequency of a signal received by the receiver increases. Conversely, when the experimenter moves away from the receiver at a certain speed, the frequency of the signal received by the receiver will decrease. The doppler shift versus the velocity and signal of the moving source can be formulated as:
wherein f is the signal frequency; c is the propagation velocity of the electromagnetic wave; v is the speed of the human body movement; theta is an included angle between the human body and the receiver and the transmitter; when the human body moves on the sight distance path, the Doppler frequency shift generated by the movement of the human body is calculated to be 16 Hz according to a formula. Wherein the moving speed of human body is 1m/s, and the propagation speed of radio wave is light speed. The frequency of the radio signal used in the experiment was 2.4 GHZ. The range of frequency variation produced by human body movement in the experiment is therefore: 3.2HZ-32 HZ. In the detection of the experimental result, the frequency shift in the range is analyzed, and the data processing amount is reduced.
(3) The minute frequency variation produced due to the movement of the human body is calculated by fast fourier transform. And screening out a frequency change interval which accords with the range according to a frequency threshold value determined by the Doppler frequency shift in a time window of the experimental time. And extracting the characteristic values of the frequency change in the time window to form a characteristic vector. Selecting a characteristic value: maximum, minimum, median.
Maximum value (max): max ═ max (X) X is the total data, XiThe maximum value of the ith data;
minimum (min): min-min (x) minimum in data;
median (Median): intermediate data values in the mean (x) data
And combining the maximum value, the minimum value and the median in the window into a feature vector as an input of the classifier. Characteristic value characteristics: the frequency variation after transformation is within a certain range. And a frequency shift threshold is set, and the frequency shift is screened, so that the workload can be reduced, and the processing efficiency of the system can be improved.
(4) And (5) detecting a classifier. And detecting the indoor moving human body by using a Gaussian mixture model for classifier. The classifier has the advantages that: the characteristic matrix is classified efficiently and quickly. Compared with a static human body, the influence of a dynamic human body on signals changes continuously along with time, the system needs to be efficient, and the fast generated result comprises the human body moving at different moving speeds and states by classifying and detecting the feature vectors.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. An indoor passive dynamic human body detection method based on channel state information is characterized by comprising the following steps:
step 1: arranging a transmitter and a receiver, wherein the receiver acquires channel state information in a period of time;
step 2: preprocessing the acquired channel state information, extracting phase amplitude to correct, and acquiring real phase amplitude information;
and step 3: calculating a minute frequency change due to the movement of the human body through fast Fourier transform; screening out a frequency change interval which accords with a range in the channel state information according to a frequency threshold determined by the Doppler frequency shift; extracting the maximum value, the minimum value and the median of the frequency change as characteristic values to form a characteristic vector;
when the human body approaches the receiver at a certain speed, the frequency of the signal received by the receiver will increase; when the human body moves away from the receiver at a certain speed, the frequency of the signal received by the receiver will decrease; the doppler shift versus the velocity and signal of the moving source can be formulated as:
wherein f is the signal frequency; c is the propagation velocity of the electromagnetic wave; v is the speed of the human body movement; theta is an included angle between the human body and the receiver and the transmitter;
and 4, step 4: dividing the extracted feature vectors into a training set and a test set; training a Gaussian mixture model by using a training set to obtain a classifier; and inputting the test set into a classifier to obtain a classification result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010438361.XA CN111631723A (en) | 2020-05-22 | 2020-05-22 | Indoor passive dynamic human body detection method based on channel state information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010438361.XA CN111631723A (en) | 2020-05-22 | 2020-05-22 | Indoor passive dynamic human body detection method based on channel state information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111631723A true CN111631723A (en) | 2020-09-08 |
Family
ID=72323695
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010438361.XA Pending CN111631723A (en) | 2020-05-22 | 2020-05-22 | Indoor passive dynamic human body detection method based on channel state information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111631723A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113408691A (en) * | 2021-06-22 | 2021-09-17 | 哈尔滨工程大学 | Method for predicting through-wall passive population based on channel state information |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4016568A (en) * | 1974-01-18 | 1977-04-05 | Matsushita Electric Industrial Co., Ltd. | Method and system for measuring doppler frequency shift of an echo |
CN104502982A (en) * | 2014-12-11 | 2015-04-08 | 哈尔滨工程大学 | Indoor passive human-body detection method with free checking of fine granularity |
CN107171749A (en) * | 2017-07-17 | 2017-09-15 | 北京大学 | The method for determining the Doppler frequency shift for the wireless signal that moving object is directly reflected |
CN109379707A (en) * | 2018-08-31 | 2019-02-22 | 北京大学(天津滨海)新代信息技术研究院 | A kind of recognition methods of indoor objects zone of action and system based on wireless signal |
-
2020
- 2020-05-22 CN CN202010438361.XA patent/CN111631723A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4016568A (en) * | 1974-01-18 | 1977-04-05 | Matsushita Electric Industrial Co., Ltd. | Method and system for measuring doppler frequency shift of an echo |
CN104502982A (en) * | 2014-12-11 | 2015-04-08 | 哈尔滨工程大学 | Indoor passive human-body detection method with free checking of fine granularity |
CN107171749A (en) * | 2017-07-17 | 2017-09-15 | 北京大学 | The method for determining the Doppler frequency shift for the wireless signal that moving object is directly reflected |
CN109379707A (en) * | 2018-08-31 | 2019-02-22 | 北京大学(天津滨海)新代信息技术研究院 | A kind of recognition methods of indoor objects zone of action and system based on wireless signal |
Non-Patent Citations (3)
Title |
---|
FAHEEM ZAFARI等: "A survery of Indoor Localization Systems and Technology", 《IEEE COMMUNICATIONS SURVEYS & TUTORIALS》 * |
吕继光: "基于信道状态信息的室内设备无关被动入侵检测研究", 《中国博士学位论文全文数据库 (信息科技辑)》 * |
吕继光等: "Robust WLAN-Based Indoor Intrusion Detection Using PHY Layer Information", 《IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC》 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113408691A (en) * | 2021-06-22 | 2021-09-17 | 哈尔滨工程大学 | Method for predicting through-wall passive population based on channel state information |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105844216B (en) | Detection and matching mechanism for recognizing handwritten letters by WiFi signals | |
Zhang et al. | WiGrus: A WiFi-based gesture recognition system using software-defined radio | |
CN106483514B (en) | Airplane motion mode identification method based on EEMD and support vector machine | |
Zhang et al. | A spectrum sensing method based on signal feature and clustering algorithm in cognitive wireless multimedia sensor networks | |
CN112733609B (en) | Domain-adaptive Wi-Fi gesture recognition method based on discrete wavelet transform | |
CN104217218B (en) | A kind of lip reading recognition methods and system | |
Zhang et al. | CSI-based human activity recognition with graph few-shot learning | |
CN108197581B (en) | Unmanned aerial vehicle signal identification detection method based on improved AC-WGANs | |
CN111832462A (en) | Frequency hopping signal detection and parameter estimation method based on deep neural network | |
CN111901028B (en) | Human body behavior identification method based on CSI (channel State information) on multiple antennas | |
CN111631723A (en) | Indoor passive dynamic human body detection method based on channel state information | |
Chen et al. | Dynamic gesture recognition using wireless signals with less disturbance | |
CN116343261A (en) | Gesture recognition method and system based on multi-modal feature fusion and small sample learning | |
Pan et al. | Dynamic hand gesture detection and recognition with WiFi signal based on 1d-CNN | |
CN112751633B (en) | Broadband spectrum detection method based on multi-scale window sliding | |
CN105743756A (en) | Frame detection method based on Adaboost algorithm in Wi-Fi system | |
JP2020088529A (en) | Indoor state estimation method and indoor state estimation system | |
Fan et al. | Single-site indoor fingerprint localization based on MIMO-CSI | |
Dang et al. | Air gesture recognition using WLAN physical layer information | |
CN114639169B (en) | Human motion recognition system based on attention mechanism feature fusion and irrelevant to position | |
Liu et al. | Adversary helps: Gradient-based device-free domain-independent gesture recognition | |
KR101232365B1 (en) | Apparatus and method for multiple moving source positioning in wireless sensor network | |
Yang et al. | Recognition for human gestures based on convolutional neural network using the off-the-shelf Wi-Fi routers | |
CN111505581B (en) | Passive target detection method based on distributed sensor nodes | |
Yee et al. | Approximate conditional mean particle filtering for linear/nonlinear dynamic state space models |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200908 |