CN106411433A - WLAN-based fine-grained indoor passive intrusion detection method - Google Patents
WLAN-based fine-grained indoor passive intrusion detection method Download PDFInfo
- Publication number
- CN106411433A CN106411433A CN201610810891.6A CN201610810891A CN106411433A CN 106411433 A CN106411433 A CN 106411433A CN 201610810891 A CN201610810891 A CN 201610810891A CN 106411433 A CN106411433 A CN 106411433A
- Authority
- CN
- China
- Prior art keywords
- intrusion detection
- data
- detection method
- wlan
- variance
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
Abstract
The invention relates to the technical field of wireless positioning, and in particular relates to a WLAN-based fine-grained indoor passive intrusion detection method. The WLAN-based fine-grained indoor passive intrusion detection method disclosed by the invention comprises the following steps: data is transmitted by a transmitter; a signal is propagated in a monitoring area; the data is received by a receiver; the receiver transfers the received data as training data to a central server in real time firstly; the server extracts channel state information in real time; the variance of a sub-carrier amplitude variance in a sliding window is calculated and used as the signal feature, etc. According to the WLAN-based fine-grained indoor passive intrusion detection method disclosed by the invention, field data acquisition is carried out; a detection threshold value is estimated by utilization of the calculated signal feature; then, the probability whether a person exists in different windows or not can be calculated according to a hidden Markov model; finally, whether a person exists in a monitoring range can be determined; by utilization of less early training, human motion still can be detected with relatively high accuracy rate when the human motion speed is very slow; and thus, the method is suitable for indoor intrusion detection.
Description
Technical field
The present invention relates to wireless location technology field, the indoor passively invasion inspection of more particularly, to a kind of fine granularity based on WLAN
Survey method.
Background technology
With scientific and technological progress, indoor security monitoring technology steps up, and the technology species of monitoring system is very many,
The such as technology such as video monitoring, infrared monitoring, RF identification, pressure perception, but these technology have very harsh use environment,
For example need los path, if centre has the performance that barrier can reduce monitoring system even to lose efficacy, and these systems
Early stage lower deployment cost is also higher, needs special infrastructure.In recent years with the development of radio network technique, wireless local
The popularity rate of net WLAN, just in rapid growth, has had very high in population is than the public place of comparatively dense and family at present
Coverage rate.WLAN is except carrying out network service conventionally it is also possible to be used for passively indoor intrusion detection.Because it has very
High universality, can be used in different environment based on the passively indoor intruding detection system of WLAN, a lot of scholars in recent years
Great effort has been paid in correlational study.
, as the signal characteristic of MAC layer, the feature being easily obtained due to it is so as to be initially used for indoor passive invasion for RSSI
Detection.Indoor passive intrusion detection refers to that detected personnel need not carry any equipment related to detection, and system passes through analysis
Signal intensity in monitored area carries out human detection.But RSSI is a kind of signal characteristic of coarseness, in order that detection is more
Plus accurately, common practice is all to increase multiple transmitter and receivers and constitutes multilink, but this way increased detection
The hardware spending of system is so that cost raises.And RSSI is affected so that under equivalent environment by multipath effect in environment
RSSI is unstable.This disadvantage limits the raising of indoor passive intruding detection system precision, therefore many scholars are being just both at home and abroad
Exploring the precision improving human detection using the channel condition information of fine-grained physical layer.
Compared with RSSI, the channel condition information CSI of physical layer precisely make use of the multipath transmisstion of wireless signal, wirelessly
Signal travels to receiver through paths such as reflection, scattering, diffractions from transmitter indoors.CSI for human body movement more
Sensitivity, and the signal characteristic under same environment is more stable, is that under orthogonal frequency division multiplexi, the other signal of sub-wave length is special
Levy tolerance.And, current CSI can extract from general commercial network interface card so that a large amount of indoor passive intrusion detection based on CSI
System is come out, and has good detection performance.
Meanwhile it would be desirable to it is noted that current is not all examined based on the indoor passive intruding detection system of CSI
Consider human body to walk about the very slow situation of speed.However, because CSI can be affected by human body speed of walking about, speed of walking about is slower,
Impact to CSI is less, and when therefore traditional method walks about especially slow for human body in monitored area, accuracy of detection has
Significantly decline.And burglar gets in and will necessarily very carefully walk about, the speed of travel may be very slow, this feelings
Under condition, the detection performance of traditional method can decline.For this reason, We conducted substantial amounts of related experiment, find that CSI carries
The variance of wave-amplitude variance is all very sensitive for the human body of translational speed, can be as feature so that indoor passively invade
Detecting system is more efficient.
Content of the invention
It is an object of the invention to provide a kind of can keep compared with high detection performance based on WLAN under various translational speeds
The indoor passive intrusion detection method of fine granularity.
Realize what the object of the invention was realized in:
A kind of indoor passive intrusion detection method of fine granularity based on WLAN it is characterised in that include on-line stage and from
In the line stage, have following step, on-line stage includes step 1-5, off-line phase include step 1,2,3,6:
Step 1:Data is launched by transmitter, signal is propagated in monitored area, and by receiver receiving data;
Step 2:Receiver first in real time using the data transfer receiving to central server as training data, server
Extract real-time channel condition information, the variance calculating sliding window sub-carriers amplitude variance is as signal characteristic;
Step 3:On-line stage estimates one group of threshold value according to signal characteristic, according to this group threshold value, signal characteristic is divided into difference
Rank, using this rank as final eigenvalue;Off-line phase directly organizes the final eigenvalue of threshold calculations by this;
Step 4:Count the number of each level characteristics under someone and no one's state respectively, divided by corresponding training data window
Sum, the probability obtaining is as Initial Interest Confusion probability, and random initializtion state transition probability;
Step 5:Calculate confusion matrix and state-transition matrix using the Baum-Welch algorithm in HMM;
Step 6:Calculate the probability of hidden state using the Viterbi algorithm in HMM in real time, thus estimating
In meter environment, whether someone invades.
In step 1, receiver and server can be same equipment, and this equipment is responsible for receiving data and process simultaneously
Data.
In step 2, training data includes the data gathering when someone in environment walks about with nobody, the number that someone walks about
According to the speed that includes walking about fast, slow with very slow three kinds of situations, and have corresponding mark.
In step 2, the variance of sliding window sub-carriers amplitude variance refer to first respectively to size in the sliding window of n
All subcarrier H=[Hk,Hk+1,...,Hk+n-1] calculate the variance of its amplitude, obtain variance vectors Vw=[v1,v2,...,v30
]T, then variance V=var (V is calculated to the variance vectors obtainingw).
In step 3, the number of this group threshold value and size are by repeatedly repeatedly testing, according to Detection results, selecting one group
The best threshold value of effect.
The beneficial effects of the present invention is:
The present invention proposes a kind of indoor passive intrusion detection method of fine granularity based on WLAN, and the method includes 6 steps.
By collection in worksite data, estimate detection threshold value using the signal characteristic calculating, calculate finally according to HMM
The probability of someone or no one in different windows, final determines monitoring range whether someone.The method can be using less early stage
Training, still can detect human motion with higher accuracy rate when human motion speed is very slow, be suitably applied in room
In interior intrusion detection.
The present invention is only suitable for one group of transmitter and receiver, can adapt to the indoor environment of different area.And the present invention
The bigger indoor environment of area can also be deployed in using multigroup transmitter and receiver and realize human detection, have good expanding
Malleability.
Brief description
Fig. 1 is the flow chart of the indoor passive intrusion detection method of the fine granularity based on WLAN of the present invention.
Fig. 2 is the schematic diagram of this method grader.
Specific embodiment
Below in conjunction with accompanying drawing, the present invention is described in further details.
The invention discloses a kind of indoor passively intrusion detection method of fine granularity based on WLAN.The present invention includes:(1) special
Levy extraction;(2) human detection.The present invention proposes the indoor passive intrusion detection method of a fine granularity, and the method can utilize particulate
The channel condition information of degree calculating Variance feature, by the method for probability by different features with whether someone is mapped,
Thus judging in environment whether someone.For equivalent environment, this method is more sensitive to the human body moving slowly at, Neng Gouyou
Effect detects with the human body of very slow speed movement in environment, thus improving the effectiveness of indoor intruding detection system and can use
Property.
The present invention proposes a kind of indoor passive intrusion detection method of fine granularity based on WLAN, by human motion test problems
Be converted to the problem of probability, can still have very high accuracy of detection in the case that human motion speed is especially slow, improve room
The availability of interior intruding detection system.
In order to achieve the above object, the present invention proposes a kind of indoor passive intrusion detection method of fine granularity based on WLAN,
Comprise the following steps:
At present, can be carried including 30 sons by being got using the firmware of modification on commercial wireless network card Intel 5300
The CFR of ripple, and User space can be submitted in the form of channel condition information and processed.
Method includes off-line phase and on-line stage, and off-line phase includes step 101-105, and on-line stage includes step
101st, 102,103 and 106.
In a step 101, dispose a pair of transmitter and receiver real-time data collection indoors, deployed position can be appointed
Meaning, and extract channel condition information.Can by the use of general commercial wireless router as transmitter, using one equipped with
The computer of Intel5300 wireless network card sends ICMP bag as receiver, receiver to transmitter, and launching opportunity is to receiver
Return corresponding packet, using the packet returning as the data gathering.
During radio signal propagation, in time domain, radio communication can simply be modeled as:
Wherein t is the time, and y is receipt signal, and x is sending signal, and h is channel response, and it is a plural number, representation signal
Amplitude and phase information, z is Gaussian white noise.
But can be affected by multipath effect due in wireless signal indoors environment, including the reflection etc. of signal, be connect
The signal that receiving end receives is to be formed by the superposition of different paths, lead to different spread lengths, path loss, different when
Prolong, amplitude is decayed and phase offset.Multi-path environment can pass through linearly filter h (τ) characterization, i.e. channel impulse response
(Channel Impulse Response, CIR):
Wherein, ai、θiAnd τiRepresent amplitude, phase place and the time delay in i-th path, i=1 respectively, 2 ..., N, N represent road
Footpath number.
In frequency domain, ofdm system provides the channel frequency response (Channel in OFDM subcarrier granularity
Frequency Response, CFR) be:
H=[H (f1),H(f2),...,H(f30)]
The CFR of wherein each subcarrier comprises amplitude information and phase information:
H(fk)=| | H (fk)||ejsin(∠H)
Wherein | | H (fk) | | for the amplitude of subcarrier, ∠ H is the phase place of subcarrier.
For a given bandwidth, CIR can be converted into CFR by fast Fourier transform:
H=FFT (h (τ))
In a step 102, calculate channel condition information data using the data of collection in 101, according to appropriately sized cunning
The variance of dynamic window calculation sub-carrier amplitude variance, as signal characteristic.Circular is as follows:
First, from HkThe size starting is that the CSI in the data window of n can be expressed as:
H=[Hk,Hk+1,...,Hk+n-1]
Wherein H is the matrix of a 30 × n, seeks variance to the amplitude of each subcarrier in window:
vi=var (| Hi,k|,|Hi,k+1|,...,|Hi,k+n-1|)
Wherein | Hi,k| it is from HkThe amplitude of the 1st CSI of i-th subcarrier, v in the window startingiFor i-th subcarrier
Variance in this window for the amplitude, the variance of all sub-carrier amplitude is expressed as:
Vw=[v1,v2,...,v30]T
The variance of all sub-carrier amplitude variances is expressed as:
V=var (Vw)
Using V as signal characteristic, when in monitored area, someone is mobile, V can be bigger during no one than in region.
In step 103, off-line phase needs to estimate one group of threshold value according to the signal characteristic calculating from training data, this
Organize threshold value by the size fractionation of signal characteristic, using this rank as final eigenvalue.On-line stage directly utilizes this to organize threshold
Signal characteristic is classified by value, obtains eigenvalue.
Typically between 4 to 7, the quantity that signal characteristic falls in different stage is uneven to the number of rank, environment
The signal characteristic of middle no one mainly falls in the first order, and minority falls in the second level, and in environment, the signal characteristic of someone is in each level
All can not be distributed.
At step 104, as shown in Fig. 2 HMM is used as grader, wherein in monitoring of environmental whether
As two hidden states in model, eigenvalue is the explicit state in model to someone.
Count the number of each level characteristics under someone and no one's state respectively, divided by corresponding training data window sum,
The probability obtaining is as Initial Interest Confusion probability, and random initializtion state transition probability.
Here confusion probabilities refer to that each eigenvalue corresponds to the probability of someone or no one, and confusion probabilities constitute and obscure square
Battle array, dimension is 2 × nf, and wherein nf is characterized the number of value, and state transition probability refers between someone and this two states of no one
The mutually probability of phase transfer, state transition probability constitutes state-transition matrix, and dimension is 2 × 2.
In step 105, the confusion probabilities in 104 and state transition probability are brought into and calculate HMM
Baum-Welch Algorithm Learning obtains corresponding HMM.
Baum-Welch algorithm is the learning algorithm in three basic problems of HMM, can be using initially estimating
The confusion matrix of meter and state-transition matrix and corresponding observation sequence calculate the HMM of local optimum.
In step 106, using calculating HMM in 105, the test data of Real-time Collection is inputted into hidden
In Viterbi algorithm in Markov model, calculate someone walk about and no one probability, the big state of probability as terminates most
Really.
Viterbi algorithm is the algorithm calculating hidden state probability in HMM, using Hidden Markov mould
State transition probability in type and confusion probabilities and observation sequence calculate the probability of hidden state, the big hidden state of probability
It is final result, thus judging whether someone invades for interior.
The deployment of system is divided into two stages:Off-line phase and on-line stage.In off-line phase, be well placed transmitter and
Receiver, common commercial wireless router as transmitter, equipped with Intel 5300 network interface card computer as receiver, connect
Receipts machine launches ICMP bag with certain frequency (such as 20Hz) to transmitter, and then receiver utilizes Linux CSI Tool to drive
Obtain CSI information from the response bag of signal transmitter, tester should be configured to systematic parameter first, including ICMP bag
The corresponding informations such as transmission rate, transmitter IP address argument.After the completion of deployed with devices, tester gathers indoor someone respectively
With data during no one, and carry out labelling someone or no one, the situation that someone walks about needs to gather the data of various speed of walking,
The collection 2-3 minute of every group of data.System will be calculated one using these data according to the step in off-line phase
Individual suitable hidden Markov model.
In on-line stage, transmitter and receiver position is constant, and system opens on-line checking function, and receiver is still pressed
Frequency according to off-line phase launches ICMP bag to transmitter, and obtains channel information from network interface card, and system is according to on-line stage
Step using the probability calculating someone and no one from the calculated hidden Markov model of off-line phase, when the probability of someone
It is judged as when bigger that someone invades, when the probability of no one is bigger, be judged as no one.
Claims (6)
1. a kind of indoor passive intrusion detection method of fine granularity based on WLAN it is characterised in that:Including on-line stage with offline
In the stage, on-line stage includes step 1-5, off-line phase include step 1,2,3,6:
Step 1:Data is launched by transmitter, signal is propagated in monitored area, and by receiver receiving data;
Step 2:Receiver first in real time using the data transfer receiving to central server as training data, server is real-time
Extract channel condition information, the variance calculating sliding window sub-carriers amplitude variance is as signal characteristic;
Step 3:One group of threshold value is estimated according to signal characteristic, according to this group threshold value, signal characteristic is divided into not at the same level in off-line phase
Not, using this rank as final eigenvalue;Directly eigenvalue is gone out using this group threshold calculations in on-line stage;
Step 4:Count the number of each level characteristics under someone and no one's state respectively, divided by training data window sum, obtain
The probability arriving is as Initial Interest Confusion probability, and random initializtion state transition probability;
Step 5:Calculate confusion matrix and state-transition matrix using the Baum-Welch algorithm in HMM;
Step 6:Calculate the probability of hidden state using the Viterbi algorithm in HMM in real time, thus estimating ring
In border, whether someone invades.
2. a kind of indoor passive intrusion detection method of fine granularity based on WLAN according to claim 1 it is characterised in that:
In step 1, receiver and server can be same equipment, and this equipment is responsible for receiving data and processing data simultaneously.
3. a kind of indoor passive intrusion detection method of fine granularity based on WLAN according to claim 1 it is characterised in that:
In step 2, training data includes the data gathering when someone in environment walks about with nobody, and the data that someone walks about includes walking
Dynamic speed is fast, slow with very slow three kinds of situations, and have corresponding mark.
4. a kind of indoor passive intrusion detection method of fine granularity based on WLAN according to claim 1 it is characterised in that:
In step 2, the variance of sliding window sub-carriers amplitude variance refers to first respectively size be carried for height every in the sliding window of n
Amplitude | H | of ripple=[| Hk|,|Hk+1|,...,|Hk+n-1|] calculate its variance Vw=[v1,v2,...,v30]T, then to the side obtaining
Difference vector calculates variance V=var (Vw).
5. a kind of indoor passive intrusion detection method of fine granularity based on WLAN according to claim 1 it is characterised in that:
In step 3, the number of this group threshold value and size are by repeatedly repeatedly testing, and according to Detection results, select one group of effect best
Threshold value, signal characteristic is classified by threshold value, rank number generally 4 to 7, and this rank is as final eigenvalue.
6. a kind of indoor passive intrusion detection method of fine granularity based on WLAN according to claim 1 it is characterised in that:
In step 4, in monitoring of environmental whether someone as the hidden state of HMM, eigenvalue is as the explicit shape of model
State.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610810891.6A CN106411433B (en) | 2016-09-08 | 2016-09-08 | Fine-grained indoor passive intrusion detection method based on WLAN |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610810891.6A CN106411433B (en) | 2016-09-08 | 2016-09-08 | Fine-grained indoor passive intrusion detection method based on WLAN |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106411433A true CN106411433A (en) | 2017-02-15 |
CN106411433B CN106411433B (en) | 2019-12-06 |
Family
ID=57999413
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610810891.6A Active CN106411433B (en) | 2016-09-08 | 2016-09-08 | Fine-grained indoor passive intrusion detection method based on WLAN |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106411433B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107025751A (en) * | 2017-03-10 | 2017-08-08 | 深圳大学 | The method and its system of indoor condition of a fire Detection And Warning based on transmission of wireless signals |
CN107154088A (en) * | 2017-03-29 | 2017-09-12 | 西安电子科技大学 | Activity personnel amount method of estimation based on channel condition information |
CN107818663A (en) * | 2017-09-18 | 2018-03-20 | 深圳大学 | A kind of indoor intelligent safety protection method, system and medium based on WiFi networkings |
CN109409216A (en) * | 2018-09-18 | 2019-03-01 | 哈尔滨工程大学 | Speed adaptive indoor human body detection method based on subcarrier dynamic select |
CN109658655A (en) * | 2019-01-15 | 2019-04-19 | 哈尔滨工程大学 | A kind of passive intrusion detection method in interior based on wireless signal |
CN112869734A (en) * | 2021-01-11 | 2021-06-01 | 乐鑫信息科技(上海)股份有限公司 | Wi-Fi human body detection method and intelligent device |
CN113723221A (en) * | 2021-08-11 | 2021-11-30 | 西安交通大学 | Indoor behavior real-time identification method and system based on WiFi channel state information |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8694274B2 (en) * | 2008-03-18 | 2014-04-08 | Koninklijke Philips N.V. | Distributed spectrum sensing |
CN104469942A (en) * | 2014-12-24 | 2015-03-25 | 福建师范大学 | Indoor positioning method based on hidden Markov model |
CN104883732A (en) * | 2015-04-14 | 2015-09-02 | 哈尔滨工程大学 | Enhanced indoor passive human body location method |
CN104951757A (en) * | 2015-06-10 | 2015-09-30 | 南京大学 | Action detecting and identifying method based on radio signals |
-
2016
- 2016-09-08 CN CN201610810891.6A patent/CN106411433B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8694274B2 (en) * | 2008-03-18 | 2014-04-08 | Koninklijke Philips N.V. | Distributed spectrum sensing |
CN104469942A (en) * | 2014-12-24 | 2015-03-25 | 福建师范大学 | Indoor positioning method based on hidden Markov model |
CN104883732A (en) * | 2015-04-14 | 2015-09-02 | 哈尔滨工程大学 | Enhanced indoor passive human body location method |
CN104951757A (en) * | 2015-06-10 | 2015-09-30 | 南京大学 | Action detecting and identifying method based on radio signals |
Non-Patent Citations (1)
Title |
---|
霍世敏: ""基于Wi-Fi的室内非法入侵检测识别算法研究"", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107025751A (en) * | 2017-03-10 | 2017-08-08 | 深圳大学 | The method and its system of indoor condition of a fire Detection And Warning based on transmission of wireless signals |
CN107025751B (en) * | 2017-03-10 | 2018-05-08 | 深圳大学 | The method and its system of indoor fire behavior Detection And Warning based on wireless signal transmission |
CN107154088A (en) * | 2017-03-29 | 2017-09-12 | 西安电子科技大学 | Activity personnel amount method of estimation based on channel condition information |
CN107818663A (en) * | 2017-09-18 | 2018-03-20 | 深圳大学 | A kind of indoor intelligent safety protection method, system and medium based on WiFi networkings |
CN107818663B (en) * | 2017-09-18 | 2020-02-18 | 深圳大学 | Indoor intelligent security method, system and medium based on WiFi networking |
CN109409216A (en) * | 2018-09-18 | 2019-03-01 | 哈尔滨工程大学 | Speed adaptive indoor human body detection method based on subcarrier dynamic select |
CN109409216B (en) * | 2018-09-18 | 2022-04-05 | 哈尔滨工程大学 | Speed self-adaptive indoor human body detection method based on subcarrier dynamic selection |
CN109658655A (en) * | 2019-01-15 | 2019-04-19 | 哈尔滨工程大学 | A kind of passive intrusion detection method in interior based on wireless signal |
CN112869734A (en) * | 2021-01-11 | 2021-06-01 | 乐鑫信息科技(上海)股份有限公司 | Wi-Fi human body detection method and intelligent device |
CN113723221A (en) * | 2021-08-11 | 2021-11-30 | 西安交通大学 | Indoor behavior real-time identification method and system based on WiFi channel state information |
CN113723221B (en) * | 2021-08-11 | 2023-09-08 | 西安交通大学 | Indoor behavior real-time identification method and system based on WiFi channel state information |
Also Published As
Publication number | Publication date |
---|---|
CN106411433B (en) | 2019-12-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106411433A (en) | WLAN-based fine-grained indoor passive intrusion detection method | |
CN104502982B (en) | Indoor passive human-body detection method with free checking of fine granularity | |
CN103596266B (en) | A kind of human testing and method, the apparatus and system of positioning | |
Choi et al. | Deep learning based NLOS identification with commodity WLAN devices | |
CN109672485B (en) | Indoor personnel real-time invasion and movement speed detection method based on channel state information | |
CN108038419B (en) | Wi-Fi-based indoor personnel passive detection method | |
CN104883732B (en) | A kind of enhanced indoor passive passive human body localization method | |
CN110475221B (en) | Personnel action identification and position estimation method based on channel state information | |
CN102883360B (en) | A kind of method and system of the passive user's detection of indoor wireless omnidirectional | |
WO2018133264A1 (en) | Indoor automatic human body positioning detection method and system | |
CN109151707B (en) | Sight distance/non-sight distance path identification method in moving state | |
Chabbar et al. | Indoor localization using Wi-Fi method based on Fingerprinting Technique | |
CN105158727A (en) | Enhanced indoor passive human body positioning method | |
CN109698724A (en) | Intrusion detection method, device, equipment and storage medium | |
CN105163382A (en) | Indoor region location optimization method and system | |
Cai et al. | Self-deployable indoor localization with acoustic-enabled IoT devices exploiting participatory sensing | |
CN109347579A (en) | A kind of Weak Signal Detection Method to decline under condition of uncertainty in wireless channel | |
CN104486833A (en) | Indoor radio tomography imaging enhancement method capable of deleting interfering link based on motion prediction | |
Li et al. | An indoor positioning algorithm based on RSSI real-time correction | |
CN105911520A (en) | Moving object-reflected wireless signal identifying method | |
CN104467991B (en) | A kind of passive personnel's detection method and system based on WiFi physical layer informations | |
CN107911863B (en) | A method of the position malice AP is determined based on simple gesture | |
CN109151724B (en) | Line-of-sight/non-line-of-sight path identification method based on channel impulse response energy distribution | |
CN102983956B (en) | Moving speed estimation method for terminal and base station | |
Pirzada et al. | WLAN location fingerprinting technique for device-free indoor localization system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |