CN109325399A - A kind of stranger's gesture identification method and system based on channel state information - Google Patents
A kind of stranger's gesture identification method and system based on channel state information Download PDFInfo
- Publication number
- CN109325399A CN109325399A CN201810771509.4A CN201810771509A CN109325399A CN 109325399 A CN109325399 A CN 109325399A CN 201810771509 A CN201810771509 A CN 201810771509A CN 109325399 A CN109325399 A CN 109325399A
- Authority
- CN
- China
- Prior art keywords
- data
- stranger
- module
- gesture
- channel state
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
- H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
- H04B7/0619—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
- H04B7/0621—Feedback content
- H04B7/0626—Channel coefficients, e.g. channel state information [CSI]
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to artificial intelligence fields, and in particular to a kind of towards stranger's gesture identification method and system based on the channel state information in wireless network.The system includes the acquisition and preprocessing module, valid data denoising module, four gesture abnormal data extraction module, characteristics extraction and classifier categorization module modules of initial data.The present invention using among the crest value in temporal signatures maximum value and wavelet variance as characteristic value, the classification for completing stranger and non-stranger is gone by random forest grader.This method recognition accuracy with higher can be used it and classify to the personnel in practical service environment.Of the invention is a kind of the method based on channel state information to be used under commercial wireless network environment, the gesture of stranger is identified from the technicality of the same gesture motion of different people itself, can also ensure that the safety of smart home user of service is protected by the identification of the gesture motion to stranger.
Description
Technical field
The invention belongs to artificial intelligence fields, and in particular to a kind of towards based on the channel state information in wireless network
Stranger's gesture identification method and system.
Background technique
With the continuous maturation of Internet technology, the cost of network hardware equipment and network software equipment is gradually reduced, hand
The yield of the intelligent mobile terminal equipments such as machine, mini-notebook computer rises year by year, to largely drive wireless
The rapid development of WiFi.Either in business places such as dining room, mass merchandiser, hotel chains, still at the train station, it is comprehensive
The figure of the public places such as hospital, school, wireless WiFi is seen everywhere.It universal either in work, or living
On all bring great convenience for us.
Channel state information in the field of wireless communication refers to the characteristic of channel of known communication link.Channel status letter
Breath can not only be used to communication process of the description signal between transmitting terminal and receiving end, can be utilized to indicate signal
Scattering, the decline of signal and the complex effect with the signals such as decaying of power caused by the increase of distance, so channel shape
State information is also referred to as channel estimation.Since channel state information can make the transmission of signal adapt to current channel status, from
And it enables signals to achieve the purpose that the reliable transmission in the multiaerial system of High Data Rate.
Although current some existing methods can identify the stranger in reality, the foundation that they are distinguished
It is mostly significantly human motion based on different people and the different gesture motions defined for different people, not from the of the same race of different people
Gesture motion itself goes to solve the problems, such as this, it is often more important that definition can not be gone for each identified person not in real life
Same gesture motion requires identified person to carry out a large amount of human motion.So finding the gesture motion sheet of the same race of different people
Difference possessed by body, and stranger is further identified just and becomes a kind of completely new stranger identification side by these difference
Method.
Summary of the invention
The purpose of the present invention is to provide a kind of stranger's gesture identification method based on channel state information.
The purpose of the present invention is to provide a kind of stranger's gesture recognition system based on channel state information.
The object of the present invention is achieved like this, method includes the following steps:
(1) a tool run on commercial 802.11n network interface card issued first using University of Washington, tool fortune
Row, equipped under the (SuSE) Linux OS of 3 antennas, collects the nothing based on 802.11 standards on 5300 wireless network card of Intel
Line channel state information.
(2) information being collected into is extracted to the information of corresponding 90 subcarriers after pretreatment operation, and is extracted
Phase information therein out；
(3) linear transformation is done to the phase data in the subcarrier extracted, isolates wherein effective phase data；
(4) gaussian filtering denoising is done to the phase data after linear transformation；
(5) data of some subcarrier after denoising operation are extracted using improved sliding interquartile-range IQR method
Exceptional value out；
(6) value of the maximum wave crest in every group of abnormal data is calculated to the abnormal Value Data extracted, and is calculated every
The value of wavelet variance in group abnormal data, using them as the characteristic value in time domain；
(7) characteristics extraction in remaining data is come out according to the method in step (6), forms the characteristic value of test set
Data matrix；
(8) data of each of characteristic value data matrix as training set gesture motion are respectively put into random gloomy
It is trained in woods classifier, it is ensured that there is no intersection between the characteristic value of the different gestures in training set；
(9) test set and training set eigenmatrix are brought into random forest grader and is classified, by stranger
The data line chart of recognition accuracy, shows the result of experiment.
Above-mentioned steps (5) wherein based on innovatory algorithm sliding interquartile-range IQR exceptional value extraction algorithm calculation process such as
Under:
(5.1) size of sliding window is set as N；
(5.2) signal data after arranging from small to large is subjected to the quartering, extracts the number of wherein the 3/4th position
Value；
(5.3) in four segment datas of equal part, each section of average value is calculated separately out, and by this average value and the section
The median of data compares, and selects the greater in the two as numerical value to be used in next step；
(5.4) data of each section of numerical value obtained in the previous step and the 3/4th location point of this section are summed, is thus obtained
The upper bound curve of sliding interquartile-range IQR in this section；
(5.5) test coefficient of the numerical value less than 1 is chosen, and the data in it and upper bound curve are subjected to multiplication operation, is obtained
To improved upper bound curve；
(5.6) point more than improved upper bound curve is considered as outlier and all extracts them.
A kind of stranger's gesture recognition system based on channel state information includes: acquisition and the pretreatment mould of initial data
Block, valid data denoising module, gesture abnormal data extraction module, characteristics extraction and classifier categorization module；
The CSI Tools tool that the acquisition module of initial data is mainly developed by University of Washington is somebody's turn to do come what is completed
Tool can form the matrix of a m × n according to the number of transmitting antenna m and receiving antenna n, original for indicating to be collected into
Data wherein contain amplitude and phase information in initial data；By the preprocessing module of initial data to the original being collected into
Beginning phase data carries out linear transformation to eliminate the significant noise that signal Central Plains originally has, to obtain effective phase letter
Breath；These information are stored in the ephemeral data file in matlab software with corresponding data structure；
It is to be mixed by handling effective phase data that previous step is extracted in removal that valid data, which denoise module,
While noise wherein, other people feature is different from possessed by the sender that remains different gestures；
Gesture abnormal data extraction module mainly by using by improved sliding quartile moments method, is denoised from passing through
It is isolated in data after processing and is mingled in gesture motion data therein；
Characteristics extraction and classifier categorization module include characteristics extraction module and classifier categorization module two parts, spy
Value indicative extraction module extracts from gesture motion data module obtained in the previous step and can distinguish different people and make gesture of the same race
One or more of characteristic values on time domain, frequency domain or time-frequency domain of movement；The selection of classifier categorization module can be to different people
The classifier that distinguishes of characteristic value data, and using the classifier the proprietary data extracted are passed through trained
Training set characteristic value out is classified.
The acquisition of the initial data and preprocessing module realize the step (1), step (2) and step (3), described
Valid data denoising module realizes the step (4), and the gesture anomaly extracting module realizes the step (5), described
Characteristics extraction and classifier categorization module realize the step (6)~step (9), and wherein characteristics extraction module realizes
Step (6), classifier categorization module realize step (7)~step (9)
The beneficial effects of the present invention are the present invention provides a kind of subtle differences by the gesture motion of different people itself
It is different go identification stranger and non-stranger method, using among the crest value in temporal signatures maximum value and wavelet variance as
Characteristic value goes the classification for completing stranger and non-stranger by random forest grader.This method identification with higher is quasi-
True rate can be used it and classify to the personnel in practical service environment.
Detailed description of the invention
Fig. 1 is the flow chart of stranger's gesture recognition system of the invention.
Fig. 2 (a) is the classification results figure under los path of the invention.
Fig. 2 (b) is the classification results figure under obstructed path of the invention.
Fig. 3 is the work flow diagram of stranger's gesture identification method of the invention.
Specific embodiment
The present invention is described in detail with reference to the accompanying drawing:
A gesture recognition system ring indispensable as artificial intelligence field, target seek to accomplish through everyone institute
The difference in identical gesture made achievees the purpose that identify different people, is finally reached and ensures gesture identification system
The purpose of system safety.Traditional stranger's identifying system based on channel state information is more by determining for different people
The different gesture of justice, or the difference between different testers is increased by the Large Amplitude Motion of individual, it can not be from difference
The gesture of the same race of people itself goes to distinguish stranger and non-stranger.
It can be used under commercial wireless network environment based on channel state information the purpose of the present invention is to provide a kind of
Method carries out knowledge method for distinguishing to the gesture of stranger from the technicality of the same gesture motion of different people itself, and
A kind of assessment device designed in the method on the basis of the method.The present invention also aims to by stranger's
The identification of gesture motion ensures that the safety of smart home user of service is protected.
The present invention is a kind of gesture recognition system for stranger of channel state information based in wireless network；Institute
State the acquisition and preprocessing module, valid data denoise module, gesture abnormal data proposes that gesture recognition system includes initial data
Modulus block, characteristics extraction and classifier categorization module；
The acquisition module of the acquisition and preprocessing module of initial data, initial data is mainly developed by University of Washington
CSITools tool complete, which can form a m*n's according to the number of transmitting antenna m and receiving antenna n
Matrix, the initial data for indicating to be collected into, wherein contains amplitude and phase information in initial data.Due to what is be collected into
Initial data cannot detect in real time with error information present in synchronous correction wireless device and commercial wireless network card, so
It needs to carry out linear transformation to the original phase data being collected by the preprocessing module of initial data to eliminate signal Central Plains
The significant noise originally having, to obtain effective phase information.These information are stored in corresponding data structure
In ephemeral data file in matlab software, prepare for the denoising work of next step initial data；
Valid data denoise module, and valid data denoising module is mainly effective number of phases by extracting to previous step
According to being handled, while as much as possible removal is mingled in noise therein, the sending of different gestures is preferably remained
It is clearly distinguishable from other people feature possessed by person, prepares for the extraction work of next step gesture abnormal data；
Gesture abnormal data extraction module, gesture abnormal data extraction module is mainly by using passing through improved sliding
Quartile moments method is isolated from by the data after denoising and is mingled in gesture motion data therein, in next step
The extraction work of characteristic value is prepared；
Characteristics extraction and classifier categorization module, characteristics extraction and classifier categorization module include characteristics extraction mould
Block and classifier categorization module two parts, characteristics extraction module from gesture motion data module obtained in the previous step for mentioning
One or more of characteristic values on time domain, frequency domain or time-frequency domain that different people makes gesture motion of the same race can be distinguished by taking out；
Classifier categorization module is used for the classifier for selecting that the characteristic value data of different people can be distinguished, and uses the classifier
To the proprietary data extracted by trained come training set characteristic value classify.
A tool run on commercial 802.11n network interface card that step 1 is issued using University of Washington first, the tool
It operates on 5300 wireless network card of Intel equipped under the (SuSE) Linux OS of 3 antennas, collects based on 802.11 standards
Radio channel status information.
The information being collected into is extracted the information of corresponding 90 subcarriers by step 2 after pretreatment operation, is passed through
Program file phase.m extracts phase information therein；
Step 3 does linear transformation to the phase data in the subcarrier extracted, isolates wherein effective phase data；
Step 4 selects the preferable data of collecting effect in 3 gain antennas to do the phase data after linear transformation
Gaussian filtering denoising；
The data of some subcarrier of the step 5 pair after denoising operation are mentioned using improved sliding interquartile-range IQR method
Exceptional value is taken out, the window of sliding is dimensioned to 240 in the experiment of this paper；
Step 6 uses max the and findpeaks function carried in matlab to calculate the abnormal Value Data extracted respectively
The value of the maximum wave crest in every group of abnormal data, the wavevarlet.m file write using oneself calculate every group of exception number out
According to the value of middle wavelet variance, using them as the characteristic value in time domain；
The data of each of characteristic value data matrix as training set gesture motion are respectively put at random by step 7
It is trained in forest classified device, it is ensured that there is no intersection between the characteristic value of the different gestures in training set；
Step 8 comes out the characteristics extraction in remaining data according to the method in step 6, forms the characteristic value of test set
Data matrix；
Test set and training set eigenmatrix are brought into random forest grader and are classified by step 9, by strange
The data line chart of people's recognition accuracy, shows the result of experiment.
Step 10 is exported assessment report in output module and is shown the operation of all kinds of safety indexs in the form of motion graphics
State.Wherein the calculation process of the sliding interquartile-range IQR exceptional value extraction algorithm based on innovatory algorithm is as follows:
Step 1 sets the size of sliding window as N；
Signal data after arranging from small to large is carried out the quartering by step 2, extracts the number of wherein the 3/4th position
Value；
Step 3 calculates separately out each section of average value in four segment datas of equal part, and by this average value and the section
The median of data compares, and selects the greater in the two as numerical value to be used in next step；
Step 4 sums the data of each section of numerical value obtained in the previous step and the 3/4th location point of this section, thus obtains
The upper bound curve of sliding interquartile-range IQR in this section；
Step 5 chooses test coefficient of the numerical value less than 1, and the data in it and upper bound curve are carried out multiplication operation, obtains
To improved upper bound curve；
Point more than improved upper bound curve is considered as outlier and all extracts them by step 6.
Claims (8)
1. a kind of stranger's gesture identification method based on channel state information, which is characterized in that method includes the following steps:
(1) a tool run on commercial 802.11n network interface card issued first using University of Washington, the tool are operated in
Equipped under the (SuSE) Linux OS of 3 antennas on Intel5300 wireless network card, the wireless communication based on 802.11 standards is collected
Channel state information；
(2) information being collected into is extracted to the information of corresponding 90 subcarriers after pretreatment operation, and extracts it
In phase information；
(3) linear transformation is done to the phase data in the subcarrier extracted, isolates wherein effective phase data；
(4) gaussian filtering denoising is done to the phase data after linear transformation；
(5) data of some subcarrier after denoising operation are extracted using improved sliding interquartile-range IQR method different
Constant value；
(6) value of the maximum wave crest in every group of abnormal data is calculated to the abnormal Value Data extracted, and calculate every group it is different
The value of wavelet variance in regular data, using them as the characteristic value in time domain；
(7) characteristics extraction in remaining data is come out according to the method in step (6), forms the characteristic value data of test set
Matrix；
(8) data of each of characteristic value data matrix as training set gesture motion are respectively put into random forest point
It is trained in class device, it is ensured that there is no intersection between the characteristic value of the different gestures in training set；
(9) test set and training set eigenmatrix are brought into random forest grader and is classified, by being identified to stranger
The data line chart of accuracy rate, shows the result of experiment.
2. a kind of stranger's gesture identification method based on channel state information according to claim 1, which is characterized in that
Wherein the calculation process for sliding interquartile-range IQR exceptional value extraction algorithm based on innovatory algorithm is as follows for above-mentioned steps (5):
(5.1) size of sliding window is set as N；
(5.2) signal data after arranging from small to large is subjected to the quartering, extracts the numerical value of wherein the 3/4th position；
(5.3) in four segment datas of equal part, each section of average value is calculated separately out, and by this average value and the segment data
Median compare, select the greater in the two as numerical value to be used in next step；
(5.4) data of each section of numerical value obtained in the previous step and the 3/4th location point of this section are summed, thus obtains the section
The upper bound curve of interior sliding interquartile-range IQR；
(5.5) test coefficient of the numerical value less than 1 is chosen, and the data in it and upper bound curve are subjected to multiplication operation, is changed
Upper bound curve after；
(5.6) point more than improved upper bound curve is considered as outlier and all extracts them.
3. a kind of stranger's gesture recognition system based on channel state information characterized by comprising the acquisition of initial data
And preprocessing module, valid data denoising module, gesture abnormal data extraction module, characteristics extraction and classifier classification mould
Block.
4. a kind of stranger's gesture recognition system based on channel state information according to claim 3, it is characterised in that:
The acquisition module of initial data is that the CSITools tool developed by University of Washington is completed, according to transmitting antenna m and
The number of receiving antenna n forms the matrix of a m × n, indicates the initial data being collected into, wherein contains width in initial data
Value and phase information；Linear transformation is carried out to the original phase data being collected by the preprocessing module of initial data to eliminate
The significant noise that signal Central Plains originally has, obtains effective phase information；These information are deposited with corresponding data structure
Storage is in the ephemeral data file in matlab software.
5. a kind of stranger's gesture recognition system based on channel state information according to claim 4, it is characterised in that:
Valid data, which denoise module, to be mingled in removal therein by handling effective phase data that previous step is extracted
While noise, other people feature is different from possessed by the sender that retains different gestures.
6. a kind of stranger's gesture recognition system based on channel state information according to claim 5, it is characterised in that:
Gesture abnormal data extraction module is mainly by using by improved sliding quartile moments method, after process denoising
Data in isolate and be mingled in gesture motion data therein.
7. a kind of stranger's gesture recognition system based on channel state information according to claim 6, it is characterised in that:
Characteristics extraction and classifier categorization module include characteristics extraction module and classifier categorization module two parts, characteristics extraction
Module is extracted from gesture motion data module obtained in the previous step can distinguish different people makes gesture motion of the same race one
Kind or several characteristic values on time domain, frequency domain or time-frequency domain；The selection of classifier categorization module can be to the characteristic value of different people
The classifier that data distinguish, and using the classifier to the proprietary data extracted by trained come instruction
Practice collection characteristic value to classify.
8. a kind of according to claim 1, stranger's gesture identification method and system based on channel state information described in 3,
Be characterized in that: the acquisition of the initial data and preprocessing module realize the step (1), step (2) and step (3), institute
Stating valid data denoising module realizes the step (4), and the gesture anomaly extracting module realizes the step (5), institute
Stating characteristics extraction and classifier categorization module realizes the step (6)~step (9), and wherein characteristics extraction module is realized
Step (6), classifier categorization module realize step (7)~step (9).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810771509.4A CN109325399B (en) | 2018-07-13 | 2018-07-13 | Stranger gesture recognition method and system based on channel state information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810771509.4A CN109325399B (en) | 2018-07-13 | 2018-07-13 | Stranger gesture recognition method and system based on channel state information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109325399A true CN109325399A (en) | 2019-02-12 |
| CN109325399B CN109325399B (en) | 2021-11-19 |
Family
ID=65263929
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810771509.4A Active CN109325399B (en) | 2018-07-13 | 2018-07-13 | Stranger gesture recognition method and system based on channel state information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109325399B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059612A (en) * | 2019-04-15 | 2019-07-26 | 哈尔滨工程大学 | A kind of gesture identification method and system that the position based on channel state information is unrelated |
| CN110062379A (en) * | 2019-04-15 | 2019-07-26 | 哈尔滨工程大学 | Identity identifying method based on channel state information under a kind of human body behavior scene |
| CN110414468A (en) * | 2019-08-05 | 2019-11-05 | 合肥工业大学 | Based on the auth method of hand signal under WiFi environment |
| CN110502105A (en) * | 2019-07-08 | 2019-11-26 | 南京航空航天大学 | A kind of gesture recognition system and recognition methods based on CSI phase difference |
| CN111626174A (en) * | 2020-05-22 | 2020-09-04 | 哈尔滨工程大学 | Attitude robust motion recognition method based on channel state information |
| CN112163540A (en) * | 2020-10-09 | 2021-01-01 | 上海第二工业大学 | Gesture recognition method based on WiFi |
| CN112861893A (en) * | 2019-11-27 | 2021-05-28 | 四川大学 | Stranger identification algorithm based on CSI amplitude-subcarrier probability distribution |
| CN113359816A (en) * | 2021-05-21 | 2021-09-07 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle control method and system based on wireless gesture recognition |
| CN113609976A (en) * | 2021-08-04 | 2021-11-05 | 燕山大学 | Direction-sensitive multi-gesture recognition system and method based on WiFi (Wireless Fidelity) equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102289558A (en) * | 2011-05-23 | 2011-12-21 | 公安部第一研究所 | Baseline adjusting method based on random signal processing |
| CN202261388U (en) * | 2011-04-22 | 2012-05-30 | 喜讯无限(北京)科技有限责任公司 | Remote gesture recognition and transmission realization system for touch panel mobile device with communication module |
| CN103529976A (en) * | 2012-07-02 | 2014-01-22 | 英特尔公司 | Interference elimination in gesture recognition system |
| CN105046265A (en) * | 2015-03-03 | 2015-11-11 | 沈阳工业大学 | Iris image intestinal loop area detection method based on texture difference |
| CN106599864A (en) * | 2016-12-21 | 2017-04-26 | 中国科学院光电技术研究所 | Deep face recognition method based on extreme value theory |
| KR101731031B1 (en) * | 2016-02-12 | 2017-04-27 | 주식회사 엠씨넥스 | Car smart key for prohibitting use by a stranger |
| CN107272903A (en) * | 2017-06-26 | 2017-10-20 | 王田 | Social intercourse system based on image processing algorithm |
| CN107356979A (en) * | 2017-05-27 | 2017-11-17 | 淮海工学院 | A kind of method of ionized layer TEC exception detection |
-
2018
- 2018-07-13 CN CN201810771509.4A patent/CN109325399B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202261388U (en) * | 2011-04-22 | 2012-05-30 | 喜讯无限(北京)科技有限责任公司 | Remote gesture recognition and transmission realization system for touch panel mobile device with communication module |
| CN102289558A (en) * | 2011-05-23 | 2011-12-21 | 公安部第一研究所 | Baseline adjusting method based on random signal processing |
| CN103529976A (en) * | 2012-07-02 | 2014-01-22 | 英特尔公司 | Interference elimination in gesture recognition system |
| CN105046265A (en) * | 2015-03-03 | 2015-11-11 | 沈阳工业大学 | Iris image intestinal loop area detection method based on texture difference |
| KR101731031B1 (en) * | 2016-02-12 | 2017-04-27 | 주식회사 엠씨넥스 | Car smart key for prohibitting use by a stranger |
| CN106599864A (en) * | 2016-12-21 | 2017-04-26 | 中国科学院光电技术研究所 | Deep face recognition method based on extreme value theory |
| CN107356979A (en) * | 2017-05-27 | 2017-11-17 | 淮海工学院 | A kind of method of ionized layer TEC exception detection |
| CN107272903A (en) * | 2017-06-26 | 2017-10-20 | 王田 | Social intercourse system based on image processing algorithm |
Non-Patent Citations (1)
| Title |
|---|
| JIGUANG LV等: "Device-Free Passive Identity Identification via WiFi Signals", 《SENSOR》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059612A (en) * | 2019-04-15 | 2019-07-26 | 哈尔滨工程大学 | A kind of gesture identification method and system that the position based on channel state information is unrelated |
| CN110062379A (en) * | 2019-04-15 | 2019-07-26 | 哈尔滨工程大学 | Identity identifying method based on channel state information under a kind of human body behavior scene |
| CN110059612B (en) * | 2019-04-15 | 2022-11-18 | 哈尔滨工程大学 | Position-independent gesture recognition method and system based on channel state information |
| CN110062379B (en) * | 2019-04-15 | 2022-10-28 | 哈尔滨工程大学 | Identity authentication method based on channel state information under human behavior scene |
| CN110502105A (en) * | 2019-07-08 | 2019-11-26 | 南京航空航天大学 | A kind of gesture recognition system and recognition methods based on CSI phase difference |
| CN110414468A (en) * | 2019-08-05 | 2019-11-05 | 合肥工业大学 | Based on the auth method of hand signal under WiFi environment |
| CN112861893A (en) * | 2019-11-27 | 2021-05-28 | 四川大学 | Stranger identification algorithm based on CSI amplitude-subcarrier probability distribution |
| CN111626174A (en) * | 2020-05-22 | 2020-09-04 | 哈尔滨工程大学 | Attitude robust motion recognition method based on channel state information |
| CN111626174B (en) * | 2020-05-22 | 2023-03-24 | 哈尔滨工程大学 | Attitude robust motion recognition method based on channel state information |
| CN112163540A (en) * | 2020-10-09 | 2021-01-01 | 上海第二工业大学 | Gesture recognition method based on WiFi |
| CN112163540B (en) * | 2020-10-09 | 2024-01-19 | 上海第二工业大学 | Gesture recognition method based on WiFi |
| CN113359816A (en) * | 2021-05-21 | 2021-09-07 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle control method and system based on wireless gesture recognition |
| CN113359816B (en) * | 2021-05-21 | 2022-07-15 | 中国人民解放军陆军工程大学 | Unmanned aerial vehicle control method and system based on wireless gesture recognition |
| CN113609976A (en) * | 2021-08-04 | 2021-11-05 | 燕山大学 | Direction-sensitive multi-gesture recognition system and method based on WiFi (Wireless Fidelity) equipment |
| CN113609976B (en) * | 2021-08-04 | 2023-07-21 | 燕山大学 | Direction-sensitive multi-gesture recognition system and method based on WiFi equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109325399B (en) | 2021-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109325399A (en) | A kind of stranger's gesture identification method and system based on channel state information | |
| CN106909784B (en) | Epileptic electroencephalogram (eeg) identification device based on two-dimentional time-frequency image depth convolutional neural networks | |
| CN107749143B (en) | WiFi signal-based system and method for detecting falling of personnel in through-wall room | |
| CN108030494B (en) | Electrocardiosignal error flag training sample recognition methods based on cross validation | |
| CN105807935B (en) | A kind of gesture control man-machine interactive system based on WiFi | |
| CN110059612A (en) | A kind of gesture identification method and system that the position based on channel state information is unrelated | |
| CN107968689A (en) | Perception recognition methods and device based on wireless communication signals | |
| CN104135327A (en) | Spectrum sensing method based on support vector machine | |
| Shi et al. | Human activity recognition using deep learning networks with enhanced channel state information | |
| CN109587645A (en) | Personnel's recognition methods under indoor environment based on channel state information | |
| CN111597991A (en) | Rehabilitation detection method based on channel state information and BilSTM-Attention | |
| CN106491129B (en) | A kind of Human bodys' response system and method based on EOG | |
| KR102221839B1 (en) | Real-time cardiac rate detection apparatus in noisy environment and method thereof | |
| CN104268598A (en) | Human leg detection method based on two-dimensional scanning lasers | |
| CN111627555B (en) | Intelligent inspection diagnosis system based on deep learning | |
| CN109124620A (en) | A kind of atrial fibrillation detection method, device and equipment | |
| CN112861813A (en) | Method for identifying human behavior behind wall based on complex value convolution neural network | |
| Shi et al. | Deep learning networks for human activity recognition with CSI correlation feature extraction | |
| Zhu et al. | Wi-ATCN: Attentional temporal convolutional network for human action prediction using WiFi channel state information | |
| CN114707563A (en) | Human body action recognition method based on Wi-Fi channel state information | |
| CN111142668B (en) | Interaction method based on Wi-Fi fingerprint positioning and activity gesture joint recognition | |
| Bu et al. | Wi-fi based gesture recognition using deep transfer learning | |
| CN111652132B (en) | Non-line-of-sight identity recognition method and device based on deep learning and storage medium | |
| CN114041784B (en) | Double gait disorder judging device based on commercial Wi-Fi | |
| CN114581958A (en) | Static human body posture estimation method based on CSI signal arrival angle estimation |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |