CN113630720A - Indoor positioning method based on WiFi signal strength and generation countermeasure network - Google Patents
Indoor positioning method based on WiFi signal strength and generation countermeasure network Download PDFInfo
- Publication number
- CN113630720A CN113630720A CN202110973537.6A CN202110973537A CN113630720A CN 113630720 A CN113630720 A CN 113630720A CN 202110973537 A CN202110973537 A CN 202110973537A CN 113630720 A CN113630720 A CN 113630720A
- Authority
- CN
- China
- Prior art keywords
- data
- antenna
- rssi
- aoa
- antennas
- 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 34
- 238000007781 pre-processing Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000003491 array Methods 0.000 description 4
- 238000003780 insertion Methods 0.000 description 3
- 230000037431 insertion Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 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
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/04—Position of source determined by a plurality of spaced direction-finders
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/10—Small scale networks; Flat hierarchical networks
- H04W84/12—WLAN [Wireless Local Area Networks]
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
本发明公开了一种基于WiFi信号强度和生成对抗网络的定位方法：布置接收端和发射端；分别收集4天线和8天线CSI数据，收集4天线的收发端距离为d1和d2下的接收信号强度数据；对4天线和8天线CSI数据进行预处理；将预处理后的4天线、8天线CSI数据作为原始数据和真实数据进行训练，得到训练好的生成对抗网络模型；使用4天线RSSI数据计算路径损耗模型得到路径损耗模型的参数；收集待测试数据；计算AOA与RSSI，联合AOA与RSSI得到目标位置。本发明在实际AP是4天线时，通过训练好的生成对抗模型生成超过4天线阵列孔径分辨率的CSI数据；训练好的模型生成的数据和未处理的原始4天线数据相比，提升了天线阵列的孔径，减少了数据的干扰，从而提升了AOA估计精度。
The invention discloses a positioning method based on WiFi signal strength and generating a confrontation network: arranging a receiving end and a transmitting end; collecting CSI data of 4 antennas and 8 antennas respectively, and collecting the received signals under the distances d1 and d2 of the sending and receiving ends of the 4 antennas Strength data; preprocess the 4-antenna and 8-antenna CSI data; train the pre-processed 4-antenna and 8-antenna CSI data as original data and real data to obtain a trained generative adversarial network model; use 4-antenna RSSI data Calculate the path loss model to obtain the parameters of the path loss model; collect the data to be tested; calculate AOA and RSSI, and combine AOA and RSSI to obtain the target position. When the actual AP has 4 antennas, the invention generates CSI data exceeding the aperture resolution of the 4-antenna array through the trained generative confrontation model; the data generated by the trained model is compared with the unprocessed original 4-antenna data, and the antenna is improved. The aperture of the array reduces the interference of data, thereby improving the accuracy of AOA estimation.
Description
Technical Field
The invention belongs to the field of WiFi positioning, and relates to an indoor positioning method based on WiFi signal strength and generation of a countermeasure network.
Background
As indoor positioning plays an increasingly important role in many applications such as security monitoring, patient monitoring, elderly care, etc., the demand for accurate indoor positioning is also increasing. In indoor scenarios, however, GPS signals often fail to provide accurate location services for mobile devices due to the obstruction of buildings. Due to the characteristics of low price and easy deployment of WiFi equipment, WiFi-based indoor positioning methods are widely adopted.
Conventional indoor positioning techniques suffer from a number of drawbacks. The method for positioning by using Received Signal Strength (RSSI) needs to deploy a plurality of access points, positioning is realized by measuring RSSI through a plurality of APs together, or RSSI data is measured at each position by consuming a large amount of manpower, a fingerprint database is established to realize positioning, and meanwhile, the positioning method based on RSSI is easily influenced by the environment; the positioning method based on the AOA is limited by the number of antennas and the array aperture, cannot provide fine-grained AOA resolution, can only provide client direction information, and cannot obtain distance information, so that hardware needs to be modified to obtain the high-resolution AOA to improve positioning accuracy, or a plurality of APs need to be deployed to meet the accuracy requirement of indoor positioning. In order to realize accurate indoor positioning, the methods all need a plurality of APs or modify hardware, and the requirements of low cost and easy deployment of indoor positioning are difficult to meet.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an indoor positioning method based on WiFi signal strength and generation countermeasure network, which solves the problem that a large number of APs need to be deployed or hardware needs to be modified, and can obtain an accurate positioning result under the condition that only a single WiFi access point is used and the hardware is not changed.
In order to achieve the purpose, the invention adopts the following technical scheme to solve the problem:
a positioning method based on WiFi signal strength and generation countermeasure network specifically comprises the following steps:
step 1, arranging a receiving end and a transmitting end, wherein the receiving equipment is 4 antennae and 8 antennae, the transmitting equipment is 1 antenna, and the distances between the 4 antennae and the 8 antennae and the transmitting equipment are the same;
step 3, preprocessing the 4-antenna CSI data and the 8-antenna CSI data;
step 4, inputting the preprocessed 4-antenna CSI data as original data and 8-antenna CSI data as real data into a generated confrontation network model for training to obtain a trained generated confrontation network model;
step 5, calculating a path loss model by using the RSSI data of the 4 antennas collected in the step 2 to obtain parameters of the path loss model, namely an expression of the distance d of the transmitting and receiving ends;
step 6, collecting data to be tested, specifically collecting 4-antenna CSI data and RSSI data, and preprocessing the 4-antenna CSI data;
and 7, using the data to be tested for the generation countermeasure network model in the step 4 and the path loss model obtained in the step 5, calculating to obtain AOA and RSSI, and combining the AOA and RSSI to obtain the target position.
Further, in step 1, the receiving device and the transmitting device transmit signals by using an OFDM scheme, and the CSI data is formatted as Tx × Rx × Sub, where Tx is the number of transmit antennas, Rx is the number of receive antennas, and Sub is the number of available subcarriers.
Further, the preprocessing in step 3 refers to performing data calibration and performing a 0 value interpolation operation on the 4-antenna CSI data after the data calibration.
Further, the generation countermeasure network is a pix2pix model.
Further, the path loss model in step 5 adopts a Shadowing model shown in formula (3):
in the formula, R and t are RSSI and path loss factor at the reference distance, respectively, and are calculated by formulas (5) and (4), respectively:
R＝abs(RSSI1)-10nlgd1 (5)
wherein, RSSI1 and RSSI2 are the RSSI data of 4 antennas under the transceiving end distances d1 and d2 obtained in step 2, respectively.
Further, the preprocessing in step 6 is data calibration and 0 value insertion operation.
Further, the step 7 specifically includes the following sub-steps:
step 71, substituting the 4-antenna CSI data in the data to be tested obtained in the step 6 into the trained generation countermeasure network model obtained in the step 4 to obtain processed data, and performing AOA estimation on the processed data to obtain an AOA value;
step 72, screening the 4-antenna RSSI data obtained in the step 6 to obtain the 4-antenna RSSI data after screening;
step 73, substituting the screened 4-antenna RSSI data obtained in the step 72 into the parameter-determined path loss model obtained in the step 5 to obtain a value of the distance d;
step 74, selecting one AOA value with stable distribution from the AOA values obtained in the step 71;
and step 75, combining the value of the distance d obtained in the step 73 with the AOA value obtained in the step 74 to obtain the position of the target source, and ending the positioning.
Further, in step 71, the Music algorithm is used to perform AOA estimation on the processed data.
Further, in the step 72, the 4-antenna RSSI data obtained in the step 6 is screened by using a least square method shown in formula (6); the least squares formula is as follows:
wherein, P and θ respectively represent RSSI data of 4 antennas obtained in step 6 and AOA values obtained in step 7;
and
respectively, the interference-free RSSI and AOA measured by the AP when the environment is clean.
Compared with the prior art, the invention has the following technical effects:
1. the method of the invention jointly estimates the target position by using the AOA and the RSSI, thus the target positioning can be completed only by one access point without deploying a plurality of access points or modifying hardware. Therefore, the method of the invention has simple equipment and convenient deployment.
2. By using the trained generation countermeasure network model, when the actual AP is 4 antennas, CSI data which exceeds the aperture resolution of 4 antenna arrays and is close to the aperture resolution of 8 antenna arrays can be generated through the trained generation countermeasure network model; compared with the original 4-antenna data which is not processed by the model, the aperture of the antenna array is improved, the interference of the data is reduced, and therefore the estimation precision of the AOA is improved.
3. The least square method is used for reducing the influence of the environment on the positioning accuracy, and when data are collected, RSSI can be continuously collected, but the RSSI is easily interfered by the outside world, for example, by other signals, the distance estimation error can be caused, so that the least square method is used, the RSSI with the minimum interference is selected by combining the least square method with the AOA, the distance is calculated, and the positioning accuracy of a decimeter level is achieved.
Drawings
FIG. 1 is a flow chart of an indoor positioning method of the present invention based on WiFi signal strength and generation of countermeasure networks;
FIG. 2 is a schematic diagram of the deployment of the apparatus provided by the present invention;
FIG. 3 is a graph of the results of an embodiment of the present invention;
the invention is further explained below with reference to the drawings and the detailed description.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the specific contents of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention. Details which are not described in detail in the embodiments of the invention belong to the prior art which is known to the person skilled in the art.
Referring to fig. 1 and fig. 2, the positioning method based on WiFi signal strength and generation of a countermeasure network of the present invention specifically includes the following steps:
step 1, arranging a receiving end and a transmitting end. The receiving device is 4 antennas and 8 antennas, the transmitting device is 1 antenna, and the distances between the 4 antennas and the 8 antennas and the transmitting device are the same.
When the 8-antenna CSI data are collected, the environment is as simple as possible, so that the influence of the complex environment on the CSI data is reduced, and the robustness of the 8-antenna CSI data on different practical application scenes is improved.
The RSSI data (i.e., received signal strength data) for the 4 antennas is used in subsequent steps as reference data in generating the path loss model.
In this embodiment, the receiving device and the transmitting device transmit signals by using the OFDM scheme, and have 48 available subcarriers, so the format of the CSI data is Tx Rx Sub, where Tx is the number of transmitting antennas, Rx is the number of receiving antennas, and Sub is the number of available subcarriers. The CSI is 1 × 4 × 48 when the AP is 4 antennas, and 1 × 8 × 48 when the AP is 8 antennas.
And step 3, preprocessing the 4-antenna CSI data and the 8-antenna CSI data collected in the step 2, specifically, performing data calibration to eliminate phase offset generated by sampling time offset and sampling frequency offset. In addition, in order to match the dimensions of the 4-antenna CSI data with the dimensions of the 8-antenna CSI data when training the network, a 0 value interpolation operation is performed on the 4-antenna CSI data after data calibration.
And 4, inputting the 4-antenna CSI data preprocessed in the step 3 as original data and 8-antenna CSI data as real data into a generated countermeasure network model for training to obtain a trained generated countermeasure network model.
Preferably, the generation of the countermeasure network in this embodiment employs a pix2pix model.
By using the trained generation countermeasure network model, when the actual AP is 4 antennas, CSI data which exceeds the aperture resolution of 4 antenna arrays and is close to the aperture resolution of 8 antenna arrays can be generated through the trained generation countermeasure network model; compared with the original 4-antenna data (namely, the 4-antenna CSI data obtained in the step 2) which is not subjected to model processing, the data generated by the trained model improves the aperture of the antenna array, reduces the interference of the data, and improves the estimation accuracy of the AOA.
And 5, calculating a path loss model by using the RSSI data of the 4 antennas collected in the step 2 to obtain parameters of the path loss model, namely an expression of the distance d of the transmitting and receiving ends.
Preferably, in this embodiment, the path loss model is a Shadowing model shown in formula (3).
In the formula, R and t are RSSI and path loss factor at the reference distance, respectively, and are calculated by formulas (5) and (4), respectively.
R＝abs(RSSI1)-10nlgd1 (5)
Wherein, RSSI1 and RSSI2 are the RSSI data of 4 antennas under the transceiving end distances d1 and d2 obtained in step 2, respectively.
And 6, collecting data to be tested. Specifically, 4-antenna CSI data and RSSI data are collected. Preprocessing the CSI data of the 4 antennas, wherein the preprocessing is data calibration and 0 value insertion operation to obtain preprocessed CSI data of the 4 antennas;
and 7, using the data to be tested obtained in the step 6 for generating a confrontation network model in the step 4 and a path loss model obtained in the step 5, calculating to obtain AOA and RSSI, and combining the AOA and RSSI to obtain the target position.
Step 71, substituting the 4-antenna CSI data in the data to be tested obtained in the step 6 into the trained generation countermeasure network model obtained in the step 4 to obtain processed data, and performing AOA estimation on the processed data to obtain an AOA value;
preferably, in this embodiment, the Music algorithm is adopted to perform AOA estimation on the processed data.
Step 72, using the least square method shown in formula 6 to screen the 4-antenna RSSI data obtained in step 6, and obtaining the 4-antenna RSSI data after screening (i.e. the RSSI with the smallest difference between AOA and RSSI);
the least squares formulation is as follows:
wherein, P and θ respectively represent RSSI data of 4 antennas obtained in step 6 and AOA values obtained in step 7;
and
respectively, the interference-free RSSI and AOA measured by the AP when the environment is clean.
In this step, by calculating a deviation value between the AOA and the RSSI, when the deviation is minimum, the RSSI is finally determined, and optimization of the positioning result is achieved.
And 73, substituting the screened 4-antenna RSSI data obtained in the step 72 into the parameter-determined path loss model obtained in the step 5 to obtain a value of the distance d.
Step 74, selecting one AOA value with smooth distribution from the AOA values obtained in step 71.
And step 75, combining the value of the distance d obtained in the step 73 with the AOA value obtained in the step 74 to obtain the position of the target source, and ending the positioning.
In the invention, the direction of the target source can only be obtained by singly measuring the AOA, the specific position cannot be obtained, and the positioning cannot be carried out when only one access point is used, so the target position is jointly estimated by using the AOA and the RSSI. Since the RSSI is easily affected by the environment, the position of the target source is obtained from the AOA and the RSSI by using the least square estimation, taking the value when the deviation between the AOA and the RSSI is the minimum as the parameter of the position estimation and using the path loss model.
Example (b):
to verify the feasibility and effectiveness of the method of the invention, the invention was tested as follows:
and (3) experimental setting: the number of transmitting end antennas is 1, the number of receiving end equipment antennas is 4 and 8 respectively, the 4 antenna receiving end is responsible for collecting original data, and the 8 antenna receiving end is responsible for collecting real data, namely target data.
Step 1, data are collected. At the receiving end 4, the data is collected every 10 degrees between-60 degrees and 60 degrees, and 3000 data packets are collected each time. This data is used as the original data when training the network; at the receiving end 8, the real data is collected. Between-60 ° and 60 °, data was collected every 10 degrees, 3000 packets at a time, and this data was used as the real target data in training the network.
At 4 antennas, data at the transmitting and receiving ends with distances of 1 meter and 1.5 meters are collected again, and the collection is to obtain a path loss model.
And 3, inputting the data preprocessed in the step 2, and training the generation countermeasure network.
And 4, substituting the RSSI of 1 meter and the RSSI of 1.5 meters according to the formulas (3), (4) and (5) to obtain a path loss model, and solving the values of the parameters R and t.
And step 5, collecting the CSI data and the RSSI data of the antenna to be measured 4 as the data to be measured, and collecting 3000 data packets in total, wherein each data packet comprises the CSI data and the RSSI data. Preprocessing the CSI data of the 4 antennas, wherein the preprocessing is data calibration and 0 value insertion operation to obtain preprocessed CSI data of the 4 antennas;
and 6, testing the trained model by using the 4-antenna CSI data preprocessed in the step 5, inputting the data into a generation countermeasure network to obtain super-resolution output data, performing AOA estimation on the output data by using a Music algorithm to obtain an AOA value, and selecting one AOA value with stable distribution from the AOA values. And (5) screening out an RSSI value meeting the requirement by using a least square method for the RSSI value obtained in the step (5). This RSSI value is input into the path loss model to obtain the distance. And obtaining the position of the target by combining the AOA value and the RSSI.
As can be seen from fig. 3, at 30 °, the mean square error obtained using the method of the present invention (the line at the lower part of the graph) is smaller than the mean square error of the original data localization result (the line at the upper part of the graph).
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (9)
1. A positioning method based on WiFi signal strength and generation countermeasure network is characterized by comprising the following steps:
step 1, arranging a receiving end and a transmitting end, wherein the receiving equipment is 4 antennae and 8 antennae, the transmitting equipment is 1 antenna, and the distances between the 4 antennae and the 8 antennae and the transmitting equipment are the same;
step 2, respectively collecting 4-antenna CSI data and 8-antenna CSI data; meanwhile, the received signal strength data of 4 antennas with the transmitting and receiving end distances of d1 and d2 are collected respectively to obtain RSSI1 and RSSI 2;
step 3, preprocessing the 4-antenna CSI data and the 8-antenna CSI data;
step 4, inputting the preprocessed 4-antenna CSI data as original data and 8-antenna CSI data as real data into a generated confrontation network model for training to obtain a trained generated confrontation network model;
step 5, calculating a path loss model by using the RSSI data of the 4 antennas collected in the step 2 to obtain parameters of the path loss model, namely an expression of the distance d of the transmitting and receiving ends;
step 6, collecting data to be tested, specifically collecting 4-antenna CSI data and RSSI data, and preprocessing the 4-antenna CSI data;
and 7, using the data to be tested for the generation countermeasure network model in the step 4 and the path loss model obtained in the step 5, calculating to obtain AOA and RSSI, and combining the AOA and RSSI to obtain the target position.
2. The WiFi signal strength and generation countermeasure network based positioning method of claim 1, wherein in the step 1, the receiving device and the sending device transmit signals using OFDM, having 48 available subcarriers, and the format of CSI data is Tx Rx Sub, where Tx is the number of transmit antennas, Rx is the number of receive antennas, and Sub is the number of available subcarriers.
3. The positioning method based on WiFi signal strength and generation countermeasure network of claim 1, wherein the preprocessing in step 3 is to perform data calibration and perform 0 interpolation operation on 4-antenna CSI data after data calibration.
4. The WiFi signal strength and generative countering network based positioning method of claim 1 wherein the generative countering network is a pix2pix model.
5. The WiFi signal strength and generation countermeasure network based positioning method of claim 1, wherein the path loss model in step 5 adopts a Shadowing model shown in formula (3):
in the formula, R and t are RSSI and path loss factor at the reference distance, respectively, and are calculated by formulas (5) and (4), respectively:
R＝abs(RSSI1)-10nlgd1 (5)
wherein, RSSI1 and RSSI2 are the RSSI data of 4 antennas under the transceiving end distances d1 and d2 obtained in step 2, respectively.
6. The WiFi signal strength and generation countermeasure network based location method of claim 1, wherein the preprocessing in step 6 is a data calibration and insert 0 value operation.
7. The WiFi signal strength and generation countermeasure network based positioning method of claim 1 wherein said step 7 specifically includes the following sub-steps:
step 71, substituting the 4-antenna CSI data in the data to be tested obtained in the step 6 into the trained generation countermeasure network model obtained in the step 4 to obtain processed data, and performing AOA estimation on the processed data to obtain an AOA value;
step 72, screening the 4-antenna RSSI data obtained in the step 6 to obtain the 4-antenna RSSI data after screening;
step 73, substituting the screened 4-antenna RSSI data obtained in the step 72 into the parameter-determined path loss model obtained in the step 5 to obtain a value of the distance d;
step 74, selecting one AOA value with stable distribution from the AOA values obtained in the step 71;
and step 75, combining the value of the distance d obtained in the step 73 with the AOA value obtained in the step 74 to obtain the position of the target source, and ending the positioning.
8. The WiFi signal strength and generation countermeasure network based positioning method of claim 7 wherein in step 71, the Music algorithm is used to perform AOA estimation on the processed data.
9. The WiFi signal strength and generation countermeasure network based positioning method of claim 7, wherein in the step 72, the 4 antennas RSSI data obtained in the step 6 is screened by using the least square method shown in formula (6); the least squares formula is as follows:
wherein, P and θ respectively represent RSSI data of 4 antennas obtained in step 6 and AOA values obtained in step 7;
and
respectively, the interference-free RSSI and AOA measured by the AP when the environment is clean.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110973537.6A CN113630720B (en) | 2021-08-24 | 2021-08-24 | Indoor localization method based on WiFi signal strength and generative adversarial network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110973537.6A CN113630720B (en) | 2021-08-24 | 2021-08-24 | Indoor localization method based on WiFi signal strength and generative adversarial network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113630720A true CN113630720A (en) | 2021-11-09 |
| CN113630720B CN113630720B (en) | 2022-06-03 |
Family
ID=78387440
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110973537.6A Active CN113630720B (en) | 2021-08-24 | 2021-08-24 | Indoor localization method based on WiFi signal strength and generative adversarial network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113630720B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114745684A (en) * | 2022-04-13 | 2022-07-12 | 天津工业大学 | CSI indoor positioning method based on multi-mode GAN |
| CN114758364A (en) * | 2022-02-09 | 2022-07-15 | 四川大学 | Industrial IoT scene fusion positioning method and system based on deep learning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102405418A (en) * | 2009-04-22 | 2012-04-04 | 真实定位公司 | Network autonomous wireless location system |
| CN108318861A (en) * | 2017-12-29 | 2018-07-24 | 重庆邮电大学 | One kind being based on CSI precision distance measurement localization methods |
| CN111182459A (en) * | 2019-12-31 | 2020-05-19 | 西安电子科技大学 | Indoor wireless positioning method based on channel state information and wireless communication system |
| CN113613170A (en) * | 2021-08-16 | 2021-11-05 | 苏州云享阁智能科技有限公司 | High-precision indoor positioning system and method based on low-cost antenna extension |
-
2021
- 2021-08-24 CN CN202110973537.6A patent/CN113630720B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102405418A (en) * | 2009-04-22 | 2012-04-04 | 真实定位公司 | Network autonomous wireless location system |
| CN108318861A (en) * | 2017-12-29 | 2018-07-24 | 重庆邮电大学 | One kind being based on CSI precision distance measurement localization methods |
| CN111182459A (en) * | 2019-12-31 | 2020-05-19 | 西安电子科技大学 | Indoor wireless positioning method based on channel state information and wireless communication system |
| CN113613170A (en) * | 2021-08-16 | 2021-11-05 | 苏州云享阁智能科技有限公司 | High-precision indoor positioning system and method based on low-cost antenna extension |
Non-Patent Citations (2)
| Title |
|---|
| 郑阳: "基于到达角的室内定位关键技术", 《西安电子科技大学》 * |
| 陈中康: "基于深度学习的高铁移动通信信道预测和信号检测研究", 《南京邮电大学》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114758364A (en) * | 2022-02-09 | 2022-07-15 | 四川大学 | Industrial IoT scene fusion positioning method and system based on deep learning |
| CN114745684A (en) * | 2022-04-13 | 2022-07-12 | 天津工业大学 | CSI indoor positioning method based on multi-mode GAN |
| CN114745684B (en) * | 2022-04-13 | 2024-07-26 | 天津工业大学 | Multi-mode GAN-based CSI indoor positioning method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113630720B (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2549812B1 (en) | RF Fingerprinting for Location Estimate | |
| JP5691613B2 (en) | Mobile terminal position estimation apparatus, mobile terminal position estimation method, and radio wave environment index calculation method | |
| CN106842123B (en) | An indoor positioning method and an indoor positioning system | |
| US20240196361A1 (en) | Method of positioning a node in a cellular network | |
| CN108512621A (en) | A kind of Wireless Channel Modeling method based on neural network | |
| WO2019154992A1 (en) | Position estimation device and communication device | |
| CN113630720A (en) | Indoor positioning method based on WiFi signal strength and generation countermeasure network | |
| CN107015198A (en) | A kind of indoor orientation method based on the irregular laying of antenna | |
| CN104684072B (en) | Method, apparatus, AP and the terminal positioned in real time | |
| Anderson et al. | Modeling environmental effects on directionality in wireless networks | |
| CN108089147A (en) | Improved shortwave unit localization method | |
| CN115150737A (en) | Method, device and non-volatile storage medium for determining angle of arrival | |
| CN115908547A (en) | Wireless positioning method based on deep learning | |
| Choi et al. | Channel extrapolation for FDD massive MIMO: Procedure and experimental results | |
| CN110441731A (en) | Narrow band electromagnetic radiation source object localization method | |
| Ali et al. | Time of arrival estimation for WLAN indoor positioning systems using matrix pencil super resolution algorithm | |
| Xiao et al. | NomLoc: Calibration-free indoor localization with nomadic access points | |
| Astafiev et al. | Algorithm for preliminary processing channel state information of the WIFI communication channel for building indoor positioning systems | |
| CN104023389B (en) | A kind of quick AP matching locating methods | |
| Dil et al. | On the calibration and performance of RSS-based localization methods | |
| JP4014941B2 (en) | Arrival direction estimation apparatus and arrival direction estimation method | |
| Lieske et al. | Indoor-to-outdoor radio channel measurements in sub-GHz unlicensed frequency bands | |
| CN107425926A (en) | The method and system that Site Survey starts | |
| Wu et al. | DorFin: WiFi fingerprint-based localization revisited | |
| Liu et al. | A Precise ranging with subcarrier diversity for 5g nr indoor positioning |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230207 Address after: 710043 10102, Building 1, No. 99, Yanxiang Road, Yanta District, Xi'an City, Shaanxi Province Patentee after: ZPJ Electric Co.,Ltd. Address before: 710069 No. 229 Taibai North Road, Shaanxi, Xi'an Patentee before: NORTHWEST University |
|
| TR01 | Transfer of patent right |