CN112929823A - Hybrid Wi-Fi indoor positioning method - Google Patents
Hybrid Wi-Fi indoor positioning method Download PDFInfo
- Publication number
- CN112929823A CN112929823A CN202110232924.4A CN202110232924A CN112929823A CN 112929823 A CN112929823 A CN 112929823A CN 202110232924 A CN202110232924 A CN 202110232924A CN 112929823 A CN112929823 A CN 112929823A
- Authority
- CN
- China
- Prior art keywords
- module
- positioning
- data
- beacon
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- 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
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- 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
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
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 hybrid Wi-Fi indoor positioning method which comprises an offline training scheme and an online positioning scheme, wherein the offline training scheme comprises a data collection module, a data preprocessing module, a signal attenuation model module and a classifier set module, and the online positioning scheme comprises a data acquisition module, a data processing module, a coarse positioning module and a fine positioning module. According to the scheme, two types of Wi-Fi positioning algorithms are combined into a complete indoor positioning process, the rough range of the target is determined through rough positioning, then two classifiers are selected from a given range for fine positioning, the positioning stability is improved, a plurality of two classifiers are selected and trained instead of one multi-classifier in the scheme, the complexity of model training is reduced, and when the target is positioned on line, after the area where the target is located is determined through the rough positioning, the position of the target can be calculated only by calling a few classifiers in the area.
Description
Technical Field
The invention belongs to the technical field of positioning, and particularly relates to a hybrid Wi-Fi indoor positioning method.
Background
In the age of 5G internet of things, with the popularization of mobile internet, indoor positioning becomes a very demanding requirement, and various indoor positioning technologies, such as RFID positioning, WIFI positioning, UWB positioning, ultrasonic positioning, and the like, get more and more attention and development. Among them, Wi-Fi positioning technology is favored in many fields due to the advantages of low equipment cost, relatively high positioning accuracy, low power consumption, etc. Currently, Wi-Fi indoor positioning technologies are mainly classified into two main categories, measurement-based and location-based fingerprints: 1. Wi-Fi indoor positioning based on measurements: parameter information is extracted from the received Wi-Fi signals, the absolute distance between the target user and the Wi-Fi beacon is calculated according to the parameters, and then the actual coordinates are positioned by using a geometric method. The current mainstream measurement parameters include RSSI, AOA, TOA, TDOA, and the like. Common geometric methods include trilateral localization, triangulation, and triangulation centroid localization. 2. Wi-Fi indoor positioning based on location fingerprints. The method is divided into two stages, firstly, an off-line stage: collecting Wi-Fi signals at each position of the indoor environment, and extracting features from the Wi-Fi signals as fingerprints of the position; then, an online positioning stage: and matching the received signals with the fingerprints of all positions by using a classification algorithm so as to obtain a positioning result. The classification algorithms commonly used are KNN, SVM, decision trees, neural networks, etc.
Although the concept of Wi-Fi positioning has been proposed for a long time, some manufacturers have entered into commercial deployment, since Wi-Fi signal propagation is susceptible to environmental impact, even in the same location, information such as measured signal strength, signal arrival angle, signal arrival time, etc. is always fluctuating, which brings a great challenge to the accuracy of Wi-Fi positioning. Although the dependence on the measurement data is weakened, factors such as fingerprint feature extraction and classifier selection are additionally added. Moreover, the accuracy of the positioning result strongly depends on the extraction of the fingerprint characteristics and the selection of a later classifier. Currently, the commonly used classifiers include KNN, SVM, decision trees, neural networks, and the like. In a real-world situation, the generalization performance of a classifier is usually limited, that is, different data measured at the same location may obtain different classification results after passing through the classifier, thereby reducing the accuracy of positioning.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a hybrid Wi-Fi indoor positioning method, which solves the problem that although a Wi-Fi positioning concept has been proposed for a long time, some manufacturers enter into commercial deployment, but because Wi-Fi signal propagation is easily influenced by the environment, even in the same position, information such as measured signal strength, signal arrival angle and signal arrival time is always fluctuated, which brings great challenge to the accuracy of Wi-Fi positioning.
In order to achieve the purpose, the invention provides the following technical scheme: a hybrid Wi-Fi indoor positioning method comprises an offline training and an online positioning, wherein the offline training comprises a data collection module, a data preprocessing module, a signal attenuation model module and a classifier set module, and the online positioning comprises a data acquisition module, a data processing module, a coarse positioning module and a fine positioning module.
Preferably, the data collection module is specifically configured to, during an offline training stage, first acquire Wi-Fi signals at different indoor locations to obtain a training data set, where each location corresponds to multiple data packets of multiple Wi-Fi beacons.
Preferably, the data preprocessing module extracts four key fields of major, minor, rssi and time from a training data set, where major + minor can uniquely identify a Wi-Fi beacon, rssi represents the strength of a Wi-Fi signal, and time represents a timestamp of the data, then the rssi data of the same Wi-Fi beacon at the same position is merged into the same sequence, the rssi data of different beacons is aligned according to the timestamp, if more than 60% of data in the rssi sequence of a certain beacon is smaller than a certain threshold, the beacon is considered to be far away, in order to reduce interference of the beacon data on a positioning result, all data of the beacon are directly deleted from the training data set, and finally, in order to reduce the influence of environmental noise, each rssi sequence is filtered to obtain an effective training data set.
Preferably, the signal attenuation model module is specifically an offline training stage, coordinates of each sampling position and coordinates of a beacon are known, so that a propagation distance d corresponding to each rssi sequence can be obtained, then data of the same beacon at different sampling positions in an effective training data set are integrated together, next, signal attenuation model parameters corresponding to each beacon are sequentially solved, first, each distance-signal strength key value pair is split, and then, the values are substituted into a formula
In the method, parameters are fitted
And
。
preferably, the classifier set module is specifically configured in such a manner that different positions are trained respectively based on an effective training data set to obtain two classifier sets, and although the number of classifiers is large, only a few classifiers are used in actual positioning, so that the real-time performance of the system is not greatly affected.
Preferably, the data acquisition module is specifically responsible for collecting data sent by Wi-Fi beacon broadcasting in real time, and a test data set is formed every 1 s.
Preferably, the data processing module extracts three key fields, namely major, minor and rsi, from the test data set, and then performs kalman filtering to reduce the influence of environmental noise and obtain an effective test data set.
Preferably, the rough positioning module specifically selects data of three Wi-Fi beacons with the largest rssi from the preprocessed valid test data set, then finds a corresponding model from the signal attenuation model set to calculate a distance from a target position to each beacon, and calculates a position coordinate of the target, because the Wi-Fi signal has large fluctuation, a calculation result may have a large deviation from an actual position, and the module takes a circular area with an origin and a radius of 5m as a target area.
Preferably, the fine positioning module specifically finds out the classifiers in the target area from the two classifier sets, performs predictive classification on the preprocessed effective test data set, and finally weights the predictive result of each classifier as the final positioning result.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the scheme, only the coarse positioning result based on the RSSI is used as an intermediate result for finding out the approximate area where the target is located; and then according to the position fingerprint in the target area, confirm the accurate position of the target user, it is fast to position, position effectually.
2. Different from the mode of selecting a single classifier in the traditional Wi-Fi indoor positioning algorithm based on the position fingerprint, the scheme selects and trains a plurality of two classifiers instead of one multi-classifier, although the number of the classifiers is increased, the complexity of model training is reduced, and in the process of online positioning, after the approximate region where the target is located is determined through rough positioning, the position of the target can be calculated only by calling a few classifiers in the region.
3. According to the scheme, two types of Wi-Fi positioning algorithms are combined into a complete indoor positioning process, the rough range of a target is determined through rough positioning, then two classifiers are selected from a given range for fine positioning, and the stability of a positioning result is improved.
Drawings
FIG. 1 is a schematic flow chart of the technical solution of the present invention;
FIG. 2 is a schematic representation of a training data set according to the present invention;
FIG. 3 is a schematic diagram of an effective training data set of the present invention;
FIG. 4 is a schematic diagram of model parameter fitting according to the present invention;
FIG. 5 is a schematic diagram of a set of signal attenuation models in accordance with the present invention;
FIG. 6 is a diagram illustrating a two-classifier training process according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments 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 of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-6, the present invention provides a technical solution: a mixed Wi-Fi indoor positioning method comprises an offline training and an online positioning, wherein the offline training comprises a data collection module, a data preprocessing module, a signal attenuation model module and a classifier set module, and the online positioning comprises a data acquisition module, a data processing module, a coarse positioning module and a fine positioning module.
In the embodiment, the rough positioning result based on RSSI is only used as an intermediate result to find out the approximate area where the target is located, and then the accurate position of the target user is determined according to the position fingerprint in the target area, the positioning speed is high, the positioning effect is good, the scheme is different from the mode of selecting a single classifier in the traditional Wi-Fi indoor positioning algorithm based on the position fingerprint, a plurality of two classifiers are selected and trained instead of a multi-classifier, although the number of the classifiers is increased, the complexity of model training is reduced, and in the process of online positioning, after the rough positioning is determined to be the approximate area where the target is located, the position of the target can be calculated by only calling a few classifiers in the area, the scheme combines the two types of Wi-Fi positioning algorithms into a complete indoor positioning flow, firstly, the rough positioning is used for determining the approximate range of the target, and then two classifiers are selected from a given range for fine positioning, so that the stability of the positioning result is improved.
Specifically, the data collection module is configured to, during an offline training stage, first acquire Wi-Fi signals at different indoor locations to obtain a training data set, where each location corresponds to multiple data packets of multiple Wi-Fi beacons.
In this embodiment, the Wi-Fi signal acquisition can be performed on different indoor locations through the data collection module, so as to form a training data set.
Specifically, the data preprocessing module extracts four key fields of major, minor, rssi and time from a training data set, wherein major + minor can uniquely identify a Wi-Fi beacon, rssi represents the strength of Wi-Fi signals, and time represents a timestamp of the data, then rssi data of the same Wi-Fi beacon at the same position is merged into the same sequence, rssi data of different beacons are aligned according to the timestamp time, if more than 60% of data in the rssi sequence of a certain beacon are smaller than a certain threshold value, the beacon is considered to be far away, in order to reduce interference of the beacon data on a positioning result, all data of the beacon are directly deleted from the training data set, and finally, in order to reduce the influence of environmental noise, each rssi sequence is filtered to obtain an effective training data set.
In this embodiment, the data training set may be processed by the data preprocessing module to obtain an effective training data set.
Specifically, the signal attenuation model module is an off-line training stage, coordinates of each sampling position and coordinates of a beacon are known, so that a propagation distance d corresponding to each rsi sequence can be obtained, then data of the same beacon at different sampling positions in an effective training data set are integrated, next, signal attenuation model parameters corresponding to each beacon are solved in sequence, firstly, each distance-signal strength key value pair is split, and then, the values are substituted into a formula
In the method, parameters are fitted
And
。
in this embodiment, the signal attenuation module may integrate data of the same beacon at different sampling positions in the effective training data set, and then sequentially solve the signal attenuation model parameters corresponding to each beacon.
Specifically, the classifier set module is used for training different positions respectively based on an effective training data set to obtain two classifier sets, and although the number of the classifiers is large, only a few classifiers are used during actual positioning, so that the real-time performance of the system is not greatly influenced.
In the embodiment, a plurality of two classifiers are not a multi-classifier, although the number of the classifiers is increased, the complexity of model training is reduced, and in the online positioning, after the approximate region where the target is located is determined through rough positioning, the position of the target can be calculated by only calling a few classifiers in the region.
Specifically, the data acquisition module is responsible for collecting data sent by Wi-Fi beacon broadcasting in real time, and a test data set is formed every 1 s.
In this embodiment, the data acquisition module may collect data transmitted by Wi-Fi beacon broadcasts in real time to form a plurality of sets of test data sets.
Specifically, the data processing module extracts three key fields, namely major, minor and rsi, from the test data set, and then performs kalman filtering, so that the influence of environmental noise is reduced, and an effective test data set is obtained.
In this embodiment, the data processing module may extract from the test data set, and then perform kalman filtering, thereby reducing the influence of environmental noise and obtaining an effective test data set.
Specifically, the rough positioning module selects data of three Wi-Fi beacons with the largest rssi from the preprocessed effective test data set, then finds a corresponding model from the signal attenuation model set to calculate the distance from the target position to each beacon, and calculates the position coordinates of the target, because the Wi-Fi signals fluctuate greatly, the calculation result may have a large deviation from the actual position, and the module takes a circular area with an origin and a radius of 5m as a target area.
In this embodiment, the coarse positioning module may find a corresponding model from the signal attenuation model set to calculate a distance from the target position to each beacon, and calculate a position coordinate of the target.
Specifically, the fine positioning module finds out the classifiers in the target area from the two classifier sets, performs predictive classification on the preprocessed effective test data set, and finally weights the predictive results of the classifiers to obtain the final positioning result.
In this embodiment, the fine positioning module may perform prediction classification on the preprocessed effective test data set, and finally, weight the prediction results of the classifiers as the final positioning result, thereby improving the positioning accuracy.
The working principle and the using process of the invention are as follows: firstly, performing off-line training, wherein the off-line training comprises four steps, a first step of data collection module is used for acquiring Wi-Fi signals at different indoor positions during an off-line training stage to obtain a training data set, each position corresponds to a plurality of data packets of a plurality of Wi-Fi beacons, a second step of data preprocessing module is used for extracting four key fields of major, minor, rssi and time from the training data set, wherein the major and the minor can uniquely identify one Wi-Fi beacon, the rssi represents the strength of the Wi-Fi signals, the time represents the time stamp of the data, then the rssi data of the same Wi-Fi beacon at the same position are merged into the same sequence, the rssi data of different beacons are aligned according to the time stamp, if more than 60% of the data in the rssi sequence of one beacon are smaller than a certain threshold value, the beacon is considered to be far away, and the beacon data generate interference on positioning results in order to reduce the beacon data, directly deleting all data of the beacon from the training data set, and finally, filtering each rssi sequence to obtain an effective training data set in order to reduce the influence of environmental noise, integrating data of the same beacon at different sampling positions in the effective training data set together by using a signal attenuation model module in an off-line training stage, wherein the coordinate of each sampling position and the coordinate of the beacon are known, and therefore, the propagation distance d corresponding to each rssi sequence can be obtained, then, the data of the same beacon at different sampling positions in the effective training data set are integrated, next, the signal attenuation model parameter corresponding to each beacon is solved in sequence, firstly, each distance-signal intensity key value pair is split, and then, the split is substituted into a formula
In the method, parameters are fitted
And
the fourth step of classifier set module, this scheme trains different positions separately based on the effective training data set, get the two classifier sets, although there are more classifiers, in the actual positioning, only use few classifiers, therefore do not have too great influence on the real-time of the system, then carry on the online positioning step, the online positioning still includes four steps, specifically, the first step of data acquisition module, responsible for collecting the data that Wi-Fi beacon broadcasts and sends in real time, make up the test data set every 1s, the second step of data processing module, extract three key fields of major, minor and rsi from the test data set, then carry on Kalman filtering, reduce the influence of the environmental noise, get the effective test data set, the third step of coarse positioning module, choose the data of three Wi-Fi beacons with the biggest rsi from the effective test data set after the preconditioning, then finding out the corresponding model from the signal attenuation model set to calculate the distance from the target position to each beacon, calculating the position coordinate of the target, because the Wi-Fi signal has large fluctuation, the calculation result may have large deviation with the actual position, so the module takes a circular area with the origin and the radius of 5m as the target area, the fourth step is a fine positioning module, finding out the classifier in the target area from the classifier set, carrying out prediction classification on the preprocessed effective test data set, weighting the prediction result of each classifier as the final positioning result, using the coarse positioning result based on RSSI as the intermediate result to find out the approximate area where the target is located, further determining the accurate position of the target user according to the position fingerprint in the target area, the positioning speed is high, the positioning effect is good, different from the mode of selecting a single classifier in the traditional Wi-Fi indoor positioning algorithm based on the position fingerprint, the scheme selects and trains a plurality of two classesThe method comprises the steps of determining an approximate range of a target through rough positioning, selecting two classifiers from a given range for fine positioning, and improving stability of a positioning result.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. A hybrid Wi-Fi indoor positioning method is characterized in that: the positioning scheme comprises offline training and online positioning, the offline training comprises a data collection module, a data preprocessing module, a signal attenuation model module and a classifier set module, and the online positioning comprises a data acquisition module, a data processing module, a coarse positioning module and a fine positioning module.
2. A hybrid Wi-Fi indoor positioning method according to claim 1, wherein: the data collection module is specifically used for acquiring Wi-Fi signals at different indoor positions to obtain a training data set during an offline training stage, wherein each position corresponds to a plurality of data packets of a plurality of Wi-Fi beacons.
3. A hybrid Wi-Fi indoor positioning method according to claim 2, wherein: the data preprocessing module extracts four key fields of major, minor, rssi and time from a training data set, wherein the major + minor can uniquely identify a Wi-Fi beacon, the rssi represents the strength of a Wi-Fi signal, the time represents a time stamp of the data, then the rssi data of the same Wi-Fi beacon at the same position are merged into the same sequence, the rssi data of different beacons are aligned according to the time stamp, if more than 60% of data in the rssi sequence of a certain beacon are smaller than a certain threshold value, the beacon distance is considered to be far, in order to reduce the interference of the beacon data on a positioning result, all data of the beacon are directly deleted from the training data set, and finally, in order to reduce the influence of environmental noise, each rssi sequence is filtered to obtain an effective training data set.
4. A hybrid Wi-Fi indoor positioning method according to claim 3, wherein: the signal attenuation model module is specifically an off-line training stage, coordinates of each sampling position and coordinates of a beacon are known, so that the propagation distance d corresponding to each rsi sequence can be obtained, then data of the same beacon at different sampling positions in an effective training data set are integrated, next, signal attenuation model parameters corresponding to each beacon are solved in sequence, firstly, each distance-signal intensity key value pair is split, and then, the distance-signal intensity key value pairs are substituted into a formula
In the method, parameters are fitted
And
。
5. a hybrid Wi-Fi indoor positioning method of claim 4, wherein: the classifier set module is specifically based on an effective training data set, different positions are trained respectively to obtain two classifier sets, although the number of classifiers is large, only a few classifiers are used during actual positioning, and therefore the real-time performance of the system is not greatly influenced.
6. A hybrid Wi-Fi indoor positioning method according to claim 5, wherein: the data acquisition module is specifically responsible for collecting data sent by Wi-Fi beacon broadcasting in real time, and a test data set is formed every 1 s.
7. A hybrid Wi-Fi indoor positioning method according to claim 6, wherein: the data processing module extracts three key fields of major, minor and rsi from the test data set, and then performs Kalman filtering to reduce the influence of environmental noise and obtain an effective test data set.
8. A hybrid Wi-Fi indoor positioning method according to claim 7, wherein: the rough positioning module specifically selects data of three Wi-Fi beacons with the largest rssi from a preprocessed effective test data set, then finds a corresponding model from a signal attenuation model set to calculate the distance from a target position to each beacon, and calculates the position coordinates of the target, because the Wi-Fi signals have large fluctuation, a calculation result may have a large deviation from an actual position, and the module takes a circular area with an origin and a radius of 5m as a target area.
9. A hybrid Wi-Fi indoor positioning method according to claim 8, wherein: the fine positioning module is used for finding out the classifiers in the target area from the two classifier sets, carrying out prediction classification on the preprocessed effective test data set, and weighting the prediction results of all the classifiers to serve as the final positioning results.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110232924.4A CN112929823A (en) | 2021-03-03 | 2021-03-03 | Hybrid Wi-Fi indoor positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110232924.4A CN112929823A (en) | 2021-03-03 | 2021-03-03 | Hybrid Wi-Fi indoor positioning method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112929823A true CN112929823A (en) | 2021-06-08 |
Family
ID=76173156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110232924.4A Pending CN112929823A (en) | 2021-03-03 | 2021-03-03 | Hybrid Wi-Fi indoor positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112929823A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114423076A (en) * | 2021-12-27 | 2022-04-29 | 深圳云天励飞技术股份有限公司 | Fingerprint data generation method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103796304A (en) * | 2014-01-15 | 2014-05-14 | 内蒙古科技大学 | Coal mine underground positioning method based on virtual training set and Markov chain |
| CN104602342A (en) * | 2015-01-13 | 2015-05-06 | 浙江大学 | IBeacon device based efficient indoor positioning method |
| CN106131959A (en) * | 2016-08-11 | 2016-11-16 | 电子科技大学 | A kind of dual-positioning method divided based on Wi Fi signal space |
| US20180067187A1 (en) * | 2015-03-27 | 2018-03-08 | Pcms Holdings, Inc. | System and method for indoor localization using beacons |
-
2021
- 2021-03-03 CN CN202110232924.4A patent/CN112929823A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103796304A (en) * | 2014-01-15 | 2014-05-14 | 内蒙古科技大学 | Coal mine underground positioning method based on virtual training set and Markov chain |
| CN104602342A (en) * | 2015-01-13 | 2015-05-06 | 浙江大学 | IBeacon device based efficient indoor positioning method |
| US20180067187A1 (en) * | 2015-03-27 | 2018-03-08 | Pcms Holdings, Inc. | System and method for indoor localization using beacons |
| CN106131959A (en) * | 2016-08-11 | 2016-11-16 | 电子科技大学 | A kind of dual-positioning method divided based on Wi Fi signal space |
Non-Patent Citations (2)
| Title |
|---|
| 徐乐等: "基于三点定位与加权坐标的三角定位算法", 《计算机工程与应用》 * |
| 陶佳峰等: "基于RSSI的室内测距模型优化技术", 《传感器与微系统》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114423076A (en) * | 2021-12-27 | 2022-04-29 | 深圳云天励飞技术股份有限公司 | Fingerprint data generation method and device, electronic equipment and storage medium |
| CN114423076B (en) * | 2021-12-27 | 2024-03-22 | 深圳云天励飞技术股份有限公司 | Fingerprint data generation method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106851573B (en) | Log path loss model-based joint weighting K nearest neighbor indoor positioning method | |
| CN109275095B (en) | Bluetooth-based indoor positioning system, positioning equipment and positioning method | |
| CN103476115B (en) | A kind of Wi-Fi fingerprint positioning method based on AP collection similarity | |
| CN112533149B (en) | Moving target positioning algorithm based on UWB mobile node | |
| CN109951798A (en) | Merge the enhancing location fingerprint indoor orientation method of Wi-Fi and bluetooth | |
| CN105704652B (en) | Fingerprint base acquisition and optimization method in a kind of positioning of WLAN/ bluetooth | |
| CN109672973B (en) | Indoor positioning fusion method based on strongest AP | |
| CN109640269B (en) | Fingerprint positioning method based on CSI and time domain fusion algorithm | |
| CN106412839A (en) | Indoor positioning and tracking method based on secondary partition and gradient fingerprint match | |
| CN105120433A (en) | WLAN indoor positioning method based on continuous sampling and fuzzy clustering | |
| CN109444813A (en) | A kind of RFID indoor orientation method based on BP and DNN amphineura network | |
| CN104703143A (en) | Indoor positioning method based on WIFI signal strength | |
| CN103209478A (en) | Indoor positioning method based on classified thresholds and signal strength weight | |
| CN105898713A (en) | WiFi fingerprint indoor positioning method based on weighted cosine similarity | |
| CN104185275A (en) | Indoor positioning method based on WLAN | |
| CN104619020A (en) | RSSI and TOA distance measurement based WIFI indoor positioning method | |
| CN107703480A (en) | Mixed kernel function indoor orientation method based on machine learning | |
| CN104602342A (en) | IBeacon device based efficient indoor positioning method | |
| CN110351660B (en) | Bluetooth indoor positioning method based on double-step fingerprint matching architecture | |
| CN112261606B (en) | Self-adaptive indoor fusion positioning method based on dynamic environment | |
| CN106646339A (en) | Online matching and positioning method in wireless position fingerprint indoor positioning | |
| CN111901749A (en) | High-precision three-dimensional indoor positioning method based on multi-source fusion | |
| Tao et al. | AIPS: An accurate indoor positioning system with fingerprint map adaptation | |
| CN109100697B (en) | Target condensation method based on ground monitoring radar system | |
| Siyang et al. | WKNN indoor Wi-Fi localization method using k-means clustering based radio mapping |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210608 |