CN115190418A - High-precision positioning method for police wireless local area network - Google Patents
High-precision positioning method for police wireless local area network Download PDFInfo
- Publication number
- CN115190418A CN115190418A CN202210741437.5A CN202210741437A CN115190418A CN 115190418 A CN115190418 A CN 115190418A CN 202210741437 A CN202210741437 A CN 202210741437A CN 115190418 A CN115190418 A CN 115190418A
- Authority
- CN
- China
- Prior art keywords
- positioning
- sight
- line
- distance
- measurement
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000005259 measurement Methods 0.000 claims abstract description 61
- 238000004422 calculation algorithm Methods 0.000 claims description 28
- 230000004927 fusion Effects 0.000 claims description 26
- 238000001914 filtration Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000007635 classification algorithm Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims 2
- 238000012216 screening Methods 0.000 claims 1
- 238000012795 verification Methods 0.000 abstract description 7
- 238000002474 experimental method Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 8
- 238000011160 research Methods 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 238000007500 overflow downdraw method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 241000209094 Oryza Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 238000005562 fading Methods 0.000 description 2
- 238000013450 outlier detection Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/025—Services making use of location information using location based information parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a high-precision method of a police wireless local area network, which comprises the following steps: step 1: calculating a WLAN positioning error lower bound of the complex environment based on the channel state information; and 2, step: intelligently distinguishing line-of-sight propagation from non-line-of-sight propagation; and step 3: distance measurement and angle measurement errors are eliminated in a non-line-of-sight propagation scene; and 4, step 4: measuring a positioning data-fused WLAN positioning based on the channel state information; and 5: measuring a positioning data-fused WLAN positioning based on the channel state information; step 6: and establishing a WLAN positioning performance verification experiment system based on the wireless channel state information. The invention provides a new technical scheme for solving the problem of positioning the police wireless local area network nodes with high precision and low cost, and lays a good theoretical and technical foundation for the practicability of the wireless local area network positioning method based on the channel state information in the future.
Description
Technical Field
The invention relates to a high-precision method of a police wireless local area network, belonging to the technical field of wireless network safety.
Background
When the positioning target is a node of a wireless local area network, a wireless signal transmitted by a traditional satellite or a cellular base station is blocked by a building in the process of propagation, so that the positioning accuracy is greatly reduced, and even the positioning cannot be performed, and therefore, a wireless local area network scene becomes a 'blind area' of a satellite and cellular network positioning system. In order to solve the problem of the last kilometer positioning of the wireless local area network, domestic and foreign scholars research various positioning technologies and obtain certain results, such as ultrasonic positioning, radio frequency identification positioning, bluetooth positioning, zigBee positioning, ultra wideband positioning and the like. The positioning technologies can be applied to indoor and outdoor scenes and requirements which are respectively adapted to the indoor and outdoor scenes, but positioning networks and hardware equipment are required to be deployed in advance, and cost is high. Compared with the above positioning technologies, a Wireless Local Area Network (WLAN) based positioning technology can implement a low-cost positioning system without additional hardware devices.
Currently, the existing WLAN positioning method generally uses the received signal power strength to realize the target node positioning according to the path loss model of the wireless signal power strength (or according to the power strength fingerprint database established offline). Since the received signal strength is only a coarse-grained representation of the radio channel, the corresponding positioning accuracy is generally low. According to the IEEE 802.11 protocol standard, the wireless Channel response of the WiFi system can be more fully characterized in a finer-grained form through Channel State Information (CSI) on each frequency domain subcarrier. Therefore, compared with the traditional wireless positioning technology based on signal strength, the wireless positioning technology based on the channel state information can theoretically obtain more accurate positioning results without increasing the system cost. In order to realize high-precision and robust positioning, the wireless positioning method based on the channel state information needs to solve the technical challenges caused by the randomness and instability of radio propagation. In the process of propagation, wireless signals are easily reflected, scattered and even shielded by various indoor and outdoor objects such as the ground, walls, personnel and the like, so that not only is a strong multipath propagation effect caused, but also the signal propagation between a node to be positioned and an anchor node is changed from a line-of-sight distance to a non-line-of-sight distance, and a wireless channel generates obvious shadow fading. These significant shadowing and multipath effects can cause random variations in the wireless channel, thereby negatively impacting the performance of the wireless location technology based on channel state information. Therefore, the research on the WLAN node positioning method based on the channel state information has important research value and significance for realizing stable, accurate and quick WLAN positioning. However, in the police wireless lan, the radio propagation environment is complex, and the wireless signal is often shielded by obstacles such as the ground, walls, personnel, etc. during the propagation process, which not only causes shadow fading of the wireless channel, but also causes reflection and scattering of the signal, resulting in multipath effect.
Disclosure of Invention
The invention aims to provide a high-precision method for a police wireless local area network aiming at the defects of the prior art, which comprises the steps of firstly researching a wireless local area network positioning error theoretical lower bound based on channel state information, then establishing a distance measurement and angle measurement model suitable for a line-of-sight propagation scene and a non-line-of-sight propagation scene, eliminating distance measurement and angle measurement errors, then providing positioning based on fusion CSI measurement data, and finally carrying out a positioning performance verification experiment.
The technical scheme adopted by the invention for solving the technical problem is as follows: a high-precision method for police wireless local area network comprises the following steps:
step 1: and calculating the lower limit of the WLAN positioning error of the complex environment based on the channel state information.
The calculation of the lower bound of the positioning error theory has very important theoretical guidance function for the research of the positioning method, because the lower bound of the positioning error theory directly determines the optimal positioning accuracy theoretically obtained by the WLAN positioning method based on the channel state information
Step 1-1: establishing a wireless channel model under a line-of-sight multipath scene by modeling the direct path and the multipath related parameters as random variables;
step 1-2: on the basis of evaluating the deviation of a traditional distance measurement and angle measurement model in a sight distance scene, establishing a distance and angle unbiased estimation theoretical model based on channel state information in a sight distance multipath scene;
step 1-3, solving a measurement error model of distance and angle under a line-of-sight scene according to an unbiased estimation model;
step 1-4, establishing a channel model under a non-line-of-sight scene by modeling multipath parameters as random variables;
step 1-5, establishing a distance and angle unbiased estimation theoretical model under a non-line-of-sight scene;
step 1-6, combining a channel model and an unbiased estimation model, and solving a measurement error model in a non-line-of-sight scene;
and 1-7, deducing a Fisher information matrix of the WLAN positioning error in the complex environment, and further solving a lower boundary of the Clarithrome positioning error based on the channel state information.
And 2, step: the intelligence of line-of-sight propagation is distinguished from non-line-of-sight propagation.
Since the distance and angle measurement models in the two scenes of line-of-sight and non-line-of-sight have large differences, the two scenes need to be accurately distinguished before measurement errors are eliminated. The whole distinguishing process is divided into two stages, namely off-line establishment of a distinguishing model and on-line real-time distinguishing. The emphasis is to build the discriminative model off-line.
Step 2-1: and respectively acquiring CSI data in a line-of-sight scene and a non-line-of-sight scene, calculating CSI amplitude and phase, and preprocessing the amplitude and phase data. Candidate features are then computed, the features considered including, but not limited to, mean, standard deviation, coefficient of variance, skewness, kurtosis, rice K-factor, etc. of the amplitude and phase. These candidate features are then combined to form a plurality of candidate feature clusters. And for each feature cluster, the feature cluster and the distinguishing result are respectively used as input and output to train a distinguishing model. The adopted distinguishing model can be screened and improved from classification algorithms such as a support vector machine, bayes, a neural network and the like.
Step 2-1: taking the classification of the support vector machine with strong generalization capability as an example, the output of the differentiation model can be expressed as
Step 2-3: and training a plurality of distinguishing models according to different CSI feature clusters and different classification algorithms. And then testing, evaluating and contrastively analyzing the distinguishing models to select the optimal feature cluster and the optimal distinguishing model.
And step 3: positioning data fused WLAN positioning is measured based on channel state information.
The complex environment causes part of the wireless transmission link to change from line of sight to non-line of sight. The traditional positioning method generally eliminates the non-line-of-sight link positioning data with larger relative error, and then only adopts the line-of-sight link data with smaller relative error for positioning. But the non-line-of-sight link positioning data still contains valuable positioning auxiliary information, and the positioning accuracy can be effectively improved by correcting the non-line-of-sight link positioning data and fusing the corrected non-line-of-sight link positioning data and the line-of-sight link data.
Step 3-1: respectively calculating a line-of-sight link positioning result and a non-line-of-sight link positioning result by a distance and angle measurement algorithm according to respective distance and angle measurement data of the line-of-sight link and the non-line-of-sight link;
step 3-2: when the number of anchor nodes of the line-of-sight links is sufficient, a non-line-of-sight positioning autoregressive model is established by taking positioning results of a plurality of line-of-sight links as a reference due to the fact that line-of-sight positioning results have high accuracy;
step 3-3: when the number of the anchor nodes of the line-of-sight link is insufficient, the constructed non-line-of-sight autoregressive model can be adopted to predict and correct the positioning result of the non-line-of-sight link;
step 3-4: performing adaptive weighted fusion on the sight distance positioning result and the corrected non-sight distance positioning result to obtain a preliminary fusion positioning result of sight distance and non-sight distance;
step 3-5: more accurate positioning and tracking results are obtained through nonlinear filtering algorithms including, but not limited to, extended kalman filtering, volumetric kalman filtering, and the like.
And 4, step 4: and WLAN positioning based on the fusion of the fingerprint data and the measurement model.
The offline acquisition workload of fingerprint positioning is considered to be large, and under the condition that the number of fingerprints is limited, the positioning accuracy can be effectively improved by fusing fingerprint data and measurement positioning data.
Step 4-1: and acquiring CSI, and preprocessing CSI amplitude and phase data, including outlier detection, filtering and the like. And then, two initial positioning results are obtained according to the two types of positioning algorithms, namely, on one hand, the fingerprint positioning result is obtained through a CSI fingerprint positioning algorithm, and on the other hand, the measurement positioning result is obtained through the vision distance and non-vision distance measurement fusion positioning algorithm.
Step 4-2: and fusing the fingerprint positioning result and the measurement positioning result by adopting an intelligent fusion algorithm. A Bayesian fusion algorithm and a neural network fusion algorithm are mainly researched, because the Bayesian data fusion method can fully utilize data parameter prior information, and the neural network algorithm has strong self-learning and self-adaption capabilities and nonlinear processing capabilities. Taking an adaptive Bayesian data fusion method as an example, before fingerprint positioning and measurement positioning data are selected, reliability of the fingerprint positioning and measurement positioning data is estimated, and therefore, confidence distances among data need to be defined:
wherein x is i And x j Respectively a one-time fingerprint positioning data and a measurement positioning data, p i (x|x i ) And p j (x|x j ) The probability density distribution of the fingerprint positioning result and the measurement positioning result are respectively. A confidence distance matrix is further calculated. Then according to the stability of fingerprint positioning and measurement positioning, combining deviceAnd (5) grading the reliability of the positioning data by the distance, and calculating a self-adaptive relation matrix. Calculating the optimal fusion number and weight factor by the relationship matrix, and calculating the fusion result of fingerprint positioning and measurement positioning.
Has the advantages that:
1. the invention further deepens the research on the positioning theory and technology of the wireless local area network and well realizes the positioning of the wireless local area network node for police with high precision and low cost.
2. The invention adopts stable and reliable wireless network to provide convenient and rapid inquiry, management and scheduling functions on the premise of ensuring safety fully when positioning the police wireless local area network.
3. The invention designs the high-precision positioning method which can adapt to the complex working environment by fully utilizing the ubiquitous positioning information which is easily acquired in the wireless local area network equipment, thereby stably, quickly and accurately positioning the mobile policeman and the equipment at lower cost and playing an important service role in creating a public safety command system with high-utility police and sensitive response.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a general architecture of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples of the specification so that the advantages and features of the invention may be more readily understood by those skilled in the art, and the scope of the invention is more clearly and clearly defined.
As shown in fig. 1-2, the present invention provides a high-precision positioning method for police wireless local area network, which comprises the following steps:
step 1: and calculating the lower limit of the WLAN positioning error of the complex environment based on the channel state information.
The calculation of the lower bound of the positioning error theory has very important theoretical guidance function for the research of the positioning method, because the lower bound of the positioning error theory directly determines the optimal positioning accuracy theoretically obtained by the WLAN positioning method based on the channel state information
Step 1-1: establishing a wireless channel model under a line-of-sight multipath scene by modeling the direct path and the multipath related parameters as random variables;
step 1-2: on the basis of evaluating the deviation of a traditional distance measurement and angle measurement model in a sight distance scene, establishing a distance and angle unbiased estimation theoretical model based on channel state information in a sight distance multipath scene;
step 1-3, solving a distance and angle measurement error model under a line-of-sight scene according to an unbiased estimation model;
1-4, establishing a channel model in a non-line-of-sight scene by modeling multipath parameters as random variables;
step 1-5, establishing a distance and angle unbiased estimation theoretical model in a non-line-of-sight scene;
step 1-6, combining a channel model and an unbiased estimation model to solve a measurement error model in a non-line-of-sight scene;
and 1-7, deducing a Fisher information matrix of the WLAN positioning error in the complex environment, and further solving a lower boundary of the Clarithrome positioning error based on the channel state information.
And 2, step: an intelligent distinction between line-of-sight propagation and non-line-of-sight propagation is proposed.
Since the distance and angle measurement models in the two scenes of line-of-sight and non-line-of-sight have large differences, the two scenes need to be accurately distinguished before measurement errors are eliminated. The whole distinguishing process is divided into two stages, namely off-line establishment of a distinguishing model and on-line real-time distinguishing. With the emphasis on establishing the discriminative model off-line.
Step 2-1: and respectively acquiring CSI data in a line-of-sight scene and a non-line-of-sight scene, calculating CSI amplitude and phase, and preprocessing the amplitude and phase data. Candidate features are then computed, and the features considered include, but are not limited to, mean, standard deviation, coefficient of variance, skewness, kurtosis, rice K-factor, and the like. These candidate features are then combined to form a plurality of candidate feature clusters. And for each feature cluster, the feature cluster and the distinguishing result are respectively used as input and output to train a distinguishing model. The adopted distinguishing model can be screened and improved from classification algorithms such as a support vector machine, bayes, a neural network and the like.
Step 2-1: taking the classification of the SVM with strong generalization capability as an example, the output of the discriminant model can be expressed as
Step 2-3: and training a plurality of distinguishing models according to different CSI feature clusters and different classification algorithms. And then testing, evaluating and contrastively analyzing the distinguishing models to select the optimal feature cluster and the optimal distinguishing model.
And step 3: positioning data fused WLAN positioning is measured based on channel state information.
The complex environment causes part of the wireless transmission link to change from line-of-sight to non-line-of-sight. The traditional positioning method generally eliminates the non-line-of-sight link positioning data with larger relative error, and then only adopts the line-of-sight link data with smaller relative error for positioning. But the non-line-of-sight link positioning data still contains valuable positioning auxiliary information, and the positioning accuracy can be effectively improved by correcting the non-line-of-sight link positioning data and fusing the corrected non-line-of-sight link positioning data and the line-of-sight link data.
Step 3-1: respectively calculating a line-of-sight link positioning result and a non-line-of-sight link positioning result by a distance and angle measurement algorithm according to respective distance and angle measurement data of the line-of-sight link and the non-line-of-sight link;
step 3-2: when the number of the anchor nodes of the sight distance links is sufficient, because the sight distance positioning result has high accuracy, a non-sight distance positioning autoregressive model is established by taking the positioning results of a plurality of sight distance links as a reference;
step 3-3: when the number of the anchor nodes of the line-of-sight link is insufficient, the constructed non-line-of-sight autoregressive model can be adopted to predict and correct the positioning result of the non-line-of-sight link;
step 3-4: performing adaptive weighted fusion on the sight distance positioning result and the corrected non-sight distance positioning result to obtain a preliminary fusion positioning result of sight distance and non-sight distance;
step 3-5: more accurate positioning and tracking results are obtained through nonlinear filtering algorithms including, but not limited to, extended kalman filtering, volumetric kalman filtering, and the like.
And 4, step 4: and based on the WLAN positioning of fusing the fingerprint data with the measurement model.
The offline acquisition workload of fingerprint positioning is considered to be large, and under the condition that the number of fingerprints is limited, the positioning accuracy can be effectively improved by fusing fingerprint data and measurement positioning data.
Step 4-1: and acquiring CSI, and preprocessing CSI amplitude and phase data, including outlier detection, filtering and the like. And then, two initial positioning results are obtained according to the two types of positioning algorithms, namely, on one hand, the fingerprint positioning result is obtained through a CSI fingerprint positioning algorithm, and on the other hand, the measurement positioning result is obtained through the vision distance and non-vision distance measurement fusion positioning algorithm.
Step 4-2: fingerprint determination by intelligent fusion algorithmAnd fusing the bit result and the measurement positioning result. The Bayesian fusion algorithm and the neural network fusion algorithm are intensively researched, because the Bayesian data fusion method can fully utilize the prior information of the data parameters, and the neural network algorithm has strong self-learning and self-adaptive capability and nonlinear processing capability. Taking the adaptive bayesian data fusion method as an example, before selecting fingerprint positioning data and measurement positioning data, the reliability of the fingerprint positioning data and the measurement positioning data is estimated, and therefore, the confidence distance between the data is defined:
wherein x is i And x j Respectively a one-time fingerprint positioning data and a measurement positioning data, p i (x|x i ) And p j (x|x j ) The probability density distribution of the fingerprint positioning result and the measurement positioning result are respectively. A confidence distance matrix is further calculated. And then, grading the reliability of the positioning data by combining the confidence distance according to the stability of fingerprint positioning and measurement positioning, and calculating an adaptive relationship matrix. Calculating the optimal fusion number and the weight factor by the relationship matrix, and calculating the fusion result of fingerprint positioning and measurement positioning.
And 5: and establishing a WLAN positioning performance verification experiment system based on the wireless channel state information.
In order to perform more comprehensive performance verification on the WLAN positioning method based on the channel state information, research is performed through the following steps:
step 5-1: analyzing software and hardware configuration parameters influencing positioning performance, designing a software and hardware scheme with adjustable parameters, and realizing a police WLAN positioning experiment verification system based on channel state information;
step 5-2: theoretically estimating the performance of each subsystem and the performance of the whole system in advance, and mainly investigating and distinguishing performance indexes such as accuracy, measurement accuracy, subsystem positioning error, subsystem algorithm complexity, subsystem stability, whole positioning error, whole algorithm complexity, whole stability and the like;
step 5-3: based on the realized police WLAN positioning verification system platform, the actual effect of each subsystem and the whole system on the main performance indexes is measured through a plurality of cross verification experiments;
step 5-4: and comparing and analyzing the experimental result and the theoretical estimated value, and comprehensively evaluating and researching the performance of the positioning method.
It should be understood by those skilled in the art that the present invention is not limited to the exemplary embodiments described above, and any person skilled in the art can substitute or change the technical solution and concept of the present invention within the technical scope of the present invention.
Claims (5)
1. A high-precision method for police wireless local area networks is characterized by comprising the following steps:
step 1: calculating a WLAN positioning error lower bound of the complex environment based on the channel state information;
and 2, step: intelligently distinguishing visual distance transmission from non-visual distance transmission;
and 3, step 3: WLAN positioning based on channel state information measurement positioning data fusion is adopted;
and 4, step 4: and WLAN positioning based on the fusion of fingerprint data and a measurement model is adopted.
2. The method for high precision of police wireless local area network according to claim 1, wherein the step 1 specifically comprises:
step 1-1: establishing a wireless channel model under a line-of-sight multipath scene by modeling the direct path and the multipath related parameters as random variables;
step 1-2: establishing a distance and angle unbiased estimation theoretical model based on channel state information under a line-of-sight multipath scene;
step 1-3: according to the unbiased estimation model, a measurement error model of the distance and the angle under the sight distance scene is solved;
step 1-4: establishing a channel model under a non-line-of-sight scene by modeling multipath parameters as random variables;
step 1-5: establishing an unbiased estimation theoretical model of distance and angle in a non-line-of-sight scene;
step 1-6: solving a measurement error model under a non-line-of-sight scene according to the channel model and the unbiased estimation model;
step 1-7: and deducing a Fisher information matrix of the WLAN positioning error in the complex environment, and further solving a Clarithrome lower bound of the positioning error based on the channel state information.
3. The method for high precision of police wireless local area network according to claim 1, wherein the step 2 specifically comprises:
step 2-1: firstly, respectively acquiring CSI data in a sight distance scene and a non-sight distance scene, calculating CSI amplitude and phase, preprocessing the amplitude and phase data, then calculating candidate features, combining the candidate features to form a plurality of candidate feature clusters, respectively taking the candidate feature clusters and a distinguishing result as input and output for training a distinguishing model for each feature cluster, and screening and improving the adopted distinguishing model from a classification algorithm;
step 2-1: output of the discrimination model;
step 2-3: and training a plurality of distinguishing models according to different CSI feature clusters and different classification algorithms, and then testing, evaluating and contrastively analyzing the distinguishing models to select the optimal feature cluster and the optimal distinguishing model.
4. The method for high precision of police wireless local area network according to claim 1, wherein the step 3 specifically comprises:
step 3-1: respectively calculating a line-of-sight link positioning result and a non-line-of-sight link positioning result by a distance and angle measurement algorithm according to respective distance and angle measurement data of the line-of-sight link and the non-line-of-sight link;
step 3-2: when the number of anchor nodes of the line-of-sight links is sufficient, establishing a non-line-of-sight positioning autoregressive model by taking the positioning results of a plurality of line-of-sight links as a reference;
step 3-3: when the number of the anchor nodes of the line-of-sight link is insufficient, predicting and correcting a non-line-of-sight link positioning result by adopting a constructed non-line-of-sight autoregressive model;
step 3-4: performing self-adaptive weighted fusion on the sight distance positioning result and the corrected non-sight distance positioning result to obtain a preliminary fusion positioning result of sight distance and non-sight distance;
step 3-5: and obtaining more accurate positioning and tracking results through a nonlinear filtering algorithm, wherein the nonlinear filtering algorithm is an extended Kalman filtering algorithm and a volumetric Kalman filtering algorithm.
5. The method for the high precision of the police wireless local area network according to claim 1, wherein the step 5 specifically comprises;
step 4-1: collecting CSI, preprocessing CSI amplitude and phase data, and then solving two initial positioning results according to two types of positioning algorithms, namely solving a fingerprint positioning result through a CSI fingerprint positioning algorithm on one hand, and solving a measurement positioning result through a sight distance and non-sight distance measurement fusion positioning algorithm on the other hand;
step 4-2: the fingerprint positioning result and the measurement positioning result are fused by adopting an intelligent fusion algorithm, before the fingerprint positioning and the measurement positioning data are selected, the reliability of the fingerprint positioning and measurement positioning data is estimated, and therefore, the confidence distance between the data is defined:
wherein x i And x j Respectively a one-time fingerprint positioning data and a measurement positioning data, p i (x|x i ) And p j (x|x j ) And respectively calculating probability density distribution of a fingerprint positioning result and a measurement positioning result, further calculating a confidence distance matrix, grading the reliability of the positioning data according to the stability of the fingerprint positioning and the measurement positioning by combining the confidence distance, calculating an adaptive relation matrix, calculating an optimal fusion number and a weight factor by the relation matrix, and calculating a fusion result of the fingerprint positioning and the measurement positioning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210741437.5A CN115190418B (en) | 2022-06-27 | 2022-06-27 | High-precision positioning method for police wireless local area network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210741437.5A CN115190418B (en) | 2022-06-27 | 2022-06-27 | High-precision positioning method for police wireless local area network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115190418A true CN115190418A (en) | 2022-10-14 |
| CN115190418B CN115190418B (en) | 2024-04-19 |
Family
ID=83514923
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210741437.5A Active CN115190418B (en) | 2022-06-27 | 2022-06-27 | High-precision positioning method for police wireless local area network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115190418B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070133487A1 (en) * | 2005-12-12 | 2007-06-14 | Nokia Corporation | Mobile location method for WLAN-type systems |
| US20090196267A1 (en) * | 2008-02-01 | 2009-08-06 | Walker Sr Jonathan B | Systems and methods for providing location based services (lbs) utilizing wlan and/or gps signals for seamless indoor and outdoor tracking |
| CN103532647A (en) * | 2013-10-14 | 2014-01-22 | 无锡清华信息科学与技术国家实验室物联网技术中心 | Sight distance propagation path judging method and system on basis of time domain features of WiFi (Wireless Fidelity) physical layer |
| CN106792808A (en) * | 2016-12-08 | 2017-05-31 | 南京邮电大学 | Los path recognition methods under a kind of indoor environment based on channel condition information |
| US10637544B1 (en) * | 2018-04-24 | 2020-04-28 | Genghiscomm Holdings, LLC | Distributed radio system |
| US20210383175A1 (en) * | 2020-06-08 | 2021-12-09 | Wuhan University | Adaptive inversion method of internet-of-things environmental parameters based on rfid multi-feature fusion sensing model |
-
2022
- 2022-06-27 CN CN202210741437.5A patent/CN115190418B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070133487A1 (en) * | 2005-12-12 | 2007-06-14 | Nokia Corporation | Mobile location method for WLAN-type systems |
| US20090196267A1 (en) * | 2008-02-01 | 2009-08-06 | Walker Sr Jonathan B | Systems and methods for providing location based services (lbs) utilizing wlan and/or gps signals for seamless indoor and outdoor tracking |
| CN103532647A (en) * | 2013-10-14 | 2014-01-22 | 无锡清华信息科学与技术国家实验室物联网技术中心 | Sight distance propagation path judging method and system on basis of time domain features of WiFi (Wireless Fidelity) physical layer |
| CN106792808A (en) * | 2016-12-08 | 2017-05-31 | 南京邮电大学 | Los path recognition methods under a kind of indoor environment based on channel condition information |
| US10637544B1 (en) * | 2018-04-24 | 2020-04-28 | Genghiscomm Holdings, LLC | Distributed radio system |
| US20210383175A1 (en) * | 2020-06-08 | 2021-12-09 | Wuhan University | Adaptive inversion method of internet-of-things environmental parameters based on rfid multi-feature fusion sensing model |
Non-Patent Citations (2)
| Title |
|---|
| CAN WANG: "Design of Low Coupling MIMO Antenna Array with Parasitic Ground Structure", 《2018 INTERNATIONAL CONFERENCE ON MICROWAVE AND MILLIMETER WAVE TECHNOLOGY (ICMMT)》, 6 December 2018 (2018-12-06) * |
| 刘鹏: "机器人单兵室内定位理论与关键技术分析", 《火力与指挥控制》, 15 March 2022 (2022-03-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115190418B (en) | 2024-04-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112533149B (en) | Moving target positioning algorithm based on UWB mobile node | |
| CN109814066B (en) | RSSI indoor positioning distance measurement method and indoor positioning platform based on neural network learning | |
| CN112748397A (en) | UWB positioning method based on self-adaptive BP neural network under non-line-of-sight condition | |
| Zhu et al. | BLS-location: A wireless fingerprint localization algorithm based on broad learning | |
| CN109212476B (en) | RFID indoor positioning algorithm based on DDPG | |
| CN112560981B (en) | Training method, device, apparatus, program, and storage medium for generating countermeasure model | |
| CN110501671A (en) | A kind of method for tracking target and device based on measurement distribution | |
| Zhang et al. | Weighted adaptive KNN algorithm with historical information fusion for fingerprint positioning | |
| US20230222647A1 (en) | Method and system for detecting change to structure by using drone | |
| WO2023169589A1 (en) | Predictive channel modeling method based on adversarial network and long short-term memory network | |
| CN115342814B (en) | Unmanned ship positioning method based on multi-sensor data fusion | |
| CN112099619A (en) | Time window length self-adaptive selection method of mixed sight brain-computer interface | |
| Sun et al. | A novel GCN based indoor localization system with multiple access points | |
| Ren et al. | Improved shape-based distance method for correlation analysis of multi-radar data fusion in self-driving vehicle | |
| CN111082878B (en) | Target tracking method based on underwater mobile wireless sensor network | |
| CN117237902A (en) | Robot character recognition system based on deep learning | |
| CN116259161B (en) | Power failure early warning system | |
| CN115190418B (en) | High-precision positioning method for police wireless local area network | |
| CN115618743B (en) | State evaluation method and state evaluation system of sighting telescope system | |
| CN112269401A (en) | Self-adaptive active sensor tracking method based on tracking precision and risk control | |
| CN113852433B (en) | Wireless channel shadow fading model prediction method based on computer vision | |
| Huang et al. | QSFDEW: a fingerprint positioning method based on quadtree search and fractal direction entropy weighting | |
| KR20120048375A (en) | Knn/pcm hybrid mehod using gath-geva method for indoor location determination in waln | |
| Tariq et al. | WSN Localization Method Based on Hybrid PSO-GRNN Approach. | |
| CN114679683A (en) | Indoor intelligent positioning method based on derivative fingerprint migration |
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 |