CN104902562A - Indoor positioning method based on multi-layer fingerprint matching - Google Patents
Indoor positioning method based on multi-layer fingerprint matching Download PDFInfo
- Publication number
- CN104902562A CN104902562A CN201410680271.6A CN201410680271A CN104902562A CN 104902562 A CN104902562 A CN 104902562A CN 201410680271 A CN201410680271 A CN 201410680271A CN 104902562 A CN104902562 A CN 104902562A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- distance
- rss
- map
- user
- 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
Abstract
The invention discloses an indoor positioning method based on multi-layer fingerprint matching. The indoor positioning method based on multi-layer fingerprint matching includes a first step of building four layers of fingerprint maps according to indoor environment; a second step of matching a signal intensity vector actually received by a user in a rule fingerprint map and a random fingerprint map to obtain positioning results of the two times of matching by using a k-nearest neighbor method; a third step of transforming the signal intensity vector actually received by the user into a distance vector, and matching the distance vector in a rule fingerprint distance map and the random fingerprint distance map to obtain positioning results of the two times of matching by using the k-nearest neighbor method; a fourth step of averaging user estimated position coordinates obtained according to the four-layer fingerprint matching to obtain final user estimated position coordinates. The indoor positioning method based on multi-layer fingerprint matching provided by the invention builds a fingerprint database according to received signal intensity and actual positions of rule reference points and random reference points and distances based on a path-loss model, thereby reducing effects of indoor multipath environment by using a multi-layer fingerprint strategy and improving indoor positioning accuracy.
Description
Technical field
The invention provides a kind of indoor orientation method based on multilayer fingerprint matching.Be exactly in conjunction with WiFi fingerprint and path-loss model specifically, consider the rule interestingness of reference node and the localization method of random selecting simultaneously.Setting up four layers of fingerprint map, is regular fingerprint map, random fingerprint map, regular fingerprint distance map, random fingerprint distance map respectively.Four layers of map are utilized comprehensively to locate target.Belong to WiFi indoor positioning and wireless transmission and navigation field.
Background technology
Along with the development of human society, people increase day by day for the demand of own location information.GLONASS (Global Navigation Satellite System) (GNSS) is carried out outdoor positioning and is had very high accuracy.But transmit because its signal can not penetrate building, cause it can not effectively locate in indoor environment.In order to meet people to random time, the location requirement of optional position, indoor positioning technologies has become the primary study direction of domestic and international expert and scholar.
In order to solve highly dense groups of building district and an indoor positioning difficult problem, domestic and international expert proposes a series of technical scheme.As super-broadband tech, ultrasonic technology, they all need larger infrastructure to drop into, and cost is larger; In REID, radiofrequency signal can not be used for communicating, and is difficult to integrate with other system; The system of infrared technique and Bluetooth technology lacks good stability.Along with the development of intelligent terminal and the day by day perfect of WLAN facility, from the angle of technology maturation and large-scale application, WiFi indoor positioning technologies becomes a kind of extensive main flow gradually, and has the technology of unlimited potentiality.
WiFi technology is easily subject to indoor multipath environmental limit, the present invention proposes a kind of multilayer fingerprint that utilizes and carries out the indoor orientation method mated, improve the accuracy utilizing WiFi to carry out indoor positioning, reduce the impact of indoor complex environment on positioning result.
Summary of the invention
The object of the invention is to: a kind of indoor orientation method based on multilayer fingerprint matching is provided, according to rule reference point and random reference point received signal strength and physical location and build fingerprint database based on the distance of path-loss model, adopt the strategy of multilayer fingerprint to solve the impact of indoor multipath environment, improve indoor position accuracy.
Technical scheme of the present invention:
Based on the WiFi location technology that indoor environment uses, the present invention proposes a kind of four layers of fingerprint matching indoor orientation method.The method utilizes the difference of reference node rule interestingness and random selecting, with received signal strength and distance for benchmark, devises four layers of fingerprint map.After obtaining the signal receiving strength value of target location, utilize this intensity level can position on regular fingerprint and random fingerprint map.After utilizing path-attenuation model that signal strength values is converted to distance, can position on regular fingerprint distance map and random fingerprint distance map again.The comprehensive result to four layers of fingerprint matching, the location of realize target position.
The invention provides a kind of indoor orientation method based on multilayer fingerprint matching, mainly comprise four layers of fingerprint map, it is respectively:
(1) regular fingerprint map: wherein reference node is according to getting any rule interestingness at a certain distance, the received signal strength information of the main stored reference point of this fingerprint map.Distance relation on map between two points is their WiFi received signal strength value.
(2) random fingerprint map: wherein reference node is by program random selecting, the received signal strength information of the main stored reference point of this fingerprint map.Distance relation on map between two points is their WiFi received signal strength value.
(3) regular fingerprint distance map: according to Distance-loss model formula, by the received signal strength information of reference point stored in regular fingerprint map, is converted to range information, composition rule fingerprint distance map.
(4) random fingerprint distance map: according to Distance-loss model formula, by the received signal strength information of reference point stored in regular fingerprint map, be converted to range information, composition rule fingerprint distance map.
A kind of indoor orientation method based on multilayer fingerprint matching of the present invention, it comprises following step:
Step one: according to indoor environment, builds four layers of fingerprint map;
Wherein, for fingerprint map, store that each reference node receives from the signal receiving strength value of each signal access point (AP) and the actual range between each reference node and AP.To i-th signal access point, the received signal strength value received is stored as vector:
RSS
i=(RSS
i1,RSS
i2,…RSS
ij,…,RSS
in)
Wherein, RSS
iit is the received signal strength vector of the position of i-th reference point.RSS
ijit is the signal receiving strength that i-th reference node receives from a jth AP.The positional information of the reference node of rule interestingness and the reference node of random selecting be combined with corresponding range information, common composition comprises the fingerprint database of regular fingerprint and random fingerprint.
For distance map, according to path-loss model, the received signal strength vector in fingerprint map is converted into distance vector, namely in distance map, stores the spacing of each reference node and each AP.
Wherein, path-loss model equation is:
Wherein, P
rxfor decibels of power receiver, i.e. signal receiving strength value.
for the received signal strength value (RSSI value) at distance AP1m place.N is path loss index, and its value is determined by specific environment.D
0for the distance that reference distance 1m, d are between reference node and AP.Therefore, according to path-loss model formula, the expression formula obtaining the spacing of each reference node and AP is:
For i-th reference node, represent that itself and each signal access point position relation vector are:
d
i=(d
i1,d
i2,…d
ij,…,d
in)
Wherein, d
iit is the distance vector of i-th reference point.D
ijit is the distance of i-th reference node and a jth AP.The positional information of the reference node of rule interestingness and the reference node of random selecting and distance and position fingerprint are gathered together, constitutes the distance map comprising rule and random fingerprint.
Step 2: mate with regular fingerprint map and random fingerprint map according to the actual signal strength vector received of user, adopts k near neighbor method to try to achieve the positioning result of twice coupling.
Wherein, actual for the user signal receiving strength vector received mates with the signal receiving strength vector of reference point locations all in offline database by fingerprint map.Received signal strength vector
RSS=(RSS
1,RSS
2,…RSS
j,…,RSS
n)
Wherein, RSS
jrepresent the received signal strength value from a jth reference node that user receives.
Wherein, the received signal strength vector RSS of actual received signal strength RSS and i-th reference node
ibetween Euclidean distance be:
Adopt k near neighbor method, mate respectively according to regular fingerprint map and random fingerprint map, for k the value that Euclidean distance is minimum, the mean value of the coordinate of k corresponding reference node, the i.e. estimated position of position:
Two estimated coordinates values of user position can be obtained according to regular fingerprint map and random fingerprint map, be respectively (x
1, y
1), (x
2, y
2).
Step 3: actual for the user signal strength vector received is converted into distance vector and mates with regular fingerprint distance map and random fingerprint distance map, adopt k near neighbor method to try to achieve the positioning result of twice coupling.
According to path-loss model formula, the expression formula that can obtain the spacing of customer location and AP is:
Now, user received signal intensity value is converted into the distance of each AP of user distance, and the distance vector obtaining user is:
d=(d
1,d
2,…d
j,…d
n)
Wherein, d
jrepresent the distance between user and a jth AP.Definition d and d
ibetween Euclidean distance be:
Adopt k near neighbor method, mate respectively according to regular fingerprint distance map and random fingerprint distance map, for k the value that Euclidean distance is minimum, the mean value of the coordinate of k corresponding reference node is the estimated position of user, therefore, two estimated coordinates values of user position can be obtained, be respectively (x
3, y
3), (x
4, y
4).
Step 4: be averaged by the user estimated position coordinate obtained according to four layers of fingerprint matching, obtains final user estimated position coordinate.
Wherein, the expression formula of final user estimated position coordinate (x, y) is:
The invention has the advantages that:
One, the fingerprint map based on received signal strength and the propagation distance map based on path-loss model has been considered, physical location by reference to point carries out mating locating with the position calculated respectively, reduces indoor multipath environment and there is the impact of barrier on setting accuracy.
Two, consider fixed reference node and random reference node, and utilized multilayer fingerprint repeatedly to mate, improve indoor position accuracy.
Accompanying drawing explanation
Fig. 1 indoor positioning scene graph.
Fig. 2 the method for the invention flow chart.
Fig. 3 four layers of fingerprint schematic diagram of the present invention.
Fig. 4 reference node of the present invention chooses schematic diagram.
Fig. 5 positioning result figure of the present invention.
In figure, symbol, code name are described as follows:
AP Access Point WAP (wireless access point)
WIFI Wireless Fidelity adopting wireless fidelity technology
Embodiment
See Fig. 1, be typical indoor positioning scene, whole region is that the access point (AP) of 30m*30m, WiFi is arranged on four corners, the coordinate of four AP is respectively (0,0), (0,30), (30,30), (30,0).
See Fig. 2, it is the method for the invention flow chart.A kind of mixing indoor orientation method based on WiFi received signal strength of the present invention, its step is as follows:
Step 1: according to selected indoor test region, build four layers of fingerprint map;
Wherein, for regular fingerprint map, be the grid of 3m*3m by whole Region dividing, the center of each grid is with reference to the stage, store that each reference node receives from the signal receiving strength value of each signal access point (AP) and the actual range between each reference node and AP.
Wherein, for random fingerprint map, program random selecting 75 reference nodes, store received signal strength value.
For distance map, according to path-loss model, the received signal strength vector in fingerprint map is converted into distance vector, namely in distance map, stores the spacing of each reference node and each AP.
Wherein, path-loss model equation is:
Wherein, the received signal strength value at distance AP1m place
path loss index n=3, reference distance d
0=1m, therefore, according to path-loss model formula, the expression formula that can obtain the spacing of each reference node and AP is:
See Fig. 3, Fig. 4 is the distribution map of four layers of fingerprint map, and the positional information of the reference point of correspondence, the positional information of the reference node of rule interestingness and the reference node of random selecting and distance and position fingerprint are gathered together, constitutes the distance map comprising rule and random fingerprint.
Step 2: mate with regular fingerprint map and random fingerprint map according to the actual signal strength vector received of user, adopts k near neighbor method to try to achieve the positioning result of twice coupling.
Wherein, the signal strength signal intensity received is stored as vector by fingerprint map:
RSS=(RSS
1,RSS
2,…RSS
j,…,RSS
n),
Wherein, the received signal strength vector RSS of actual received signal strength RSS and i-th reference node
ibetween Euclidean distance be:
Adopt k near neighbor method, mate respectively according to regular fingerprint map and random fingerprint map, obtain two estimated coordinates values of user position, be respectively (x
1, y
1), (x
2, y
2).
Step 3: actual for the user signal strength vector received is converted into distance vector and mates with regular fingerprint distance map and random fingerprint distance map, adopt k near neighbor method to try to achieve the positioning result of twice coupling.
According to path-loss model formula, user received signal intensity value is converted into the distance of each AP of user distance, the distance vector that can obtain user is: d=(d
1, d
2... d
j... d
n)
Definition d and d
ibetween Euclidean distance be:
Adopt k near neighbor method, mate respectively according to regular fingerprint distance map and random fingerprint distance map, for k the value that Euclidean distance is minimum, the mean value of the coordinate of k corresponding reference node is the estimated position of user, therefore, two estimated coordinates values of user position can be obtained, be respectively (x
3, y
3), (x
4, y
4).
Step 4: be averaged by the user estimated position coordinate obtained according to four layers of fingerprint matching, obtains final user estimated position coordinate.
Wherein, the expression formula of final user estimated position coordinate (x, y) is:
See Fig. 5, for testing the simulation result obtained in the scene shown in Fig. 1 according to method of the present invention.X-Y axle is the coordinate of estimated position.Star-like graticule represents actual motion path, vertical line graticule represents the result of regular fingerprint positioning method, square graticule represents the result of random fingerprint localization method, real point graticule is the result of multilayer fingerprint positioning method, result shows that the result only relying on regular fingerprint method or random fingerprint to obtain in some position is comparatively large with actual motion path deviation, and the method that the present invention proposes still can obtain good positioning result.Can find out that the position error of employing multilayer fingerprint positioning method is minimum from the statistics of table 1, average localization error result is 1.2912m, and positioning precision is improved.
Table 1
In sum, the present invention propose based on multilayer fingerprint matching indoor orientation method, considered four layers of fingerprint map, be respectively regular fingerprint map, random fingerprint map, regular fingerprint distance map, random fingerprint distance map.Four layers of map are utilized to position target.The method considers reference node rule interestingness and random selecting, and respectively with received signal strength and distance for benchmark, repeatedly position, reduce indoor multipath environment and there is the impact of barrier on setting accuracy, improve indoor position accuracy.
Claims (1)
1. based on an indoor orientation method for multilayer fingerprint matching, it is characterized in that: it comprises the following steps:
Step one: according to indoor environment, builds four layers of fingerprint map;
Wherein, for fingerprint map, store that each reference node receives from the signal receiving strength value of each signal access point AP and the actual range between each reference node and AP; To i-th signal access point, the received signal strength value received is stored as vector:
RSS
i=(RSS
i1,RSS
i2,…RSS
ij,…,RSS
in)
Wherein, RSS
ibe the received signal strength vector of the position of i-th reference point, RSS
ijit is the signal receiving strength that i-th reference node receives from a jth AP; The positional information of the reference node of rule interestingness and the reference node of random selecting be combined with corresponding range information, common composition comprises the fingerprint database of regular fingerprint and random fingerprint;
For distance map, according to path-loss model, the received signal strength vector in fingerprint map is converted into distance vector, namely in distance map, stores the spacing of each reference node and each AP;
Wherein, path-loss model equation is:
Wherein, P
rxfor decibels of power receiver, i.e. signal receiving strength value,
for received signal strength value and the RSSI value at distance AP1m place; N is path loss index, and its value is determined by specific environment; d
0for the distance that reference distance 1m, d are between reference node and AP, therefore, according to path-loss model formula, the expression formula obtaining the spacing of each reference node and AP is:
For i-th reference node, represent that itself and each signal access point position relation vector are:
d
i=(d
i1,d
i2,…d
ij,…,d
in)
Wherein, d
ibe the distance vector of i-th reference point, d
ijbe the distance of i-th reference node and a jth AP, the positional information of the reference node of rule interestingness and the reference node of random selecting and distance and position fingerprint are gathered together, constitute the distance map comprising rule and random fingerprint;
Step 2: mate with regular fingerprint map and random fingerprint map according to the actual signal strength vector received of user, adopts k near neighbor method to try to achieve the positioning result of twice coupling;
Wherein, actual for the user signal receiving strength vector received mates with the signal receiving strength vector of reference point locations all in offline database by fingerprint map, received signal strength vector
RSS=(RSS
1,RSS
2,…RSS
j,…,RSS
n)
Wherein, RSS
jrepresent the received signal strength value from a jth reference node that user receives;
Wherein, the received signal strength vector RSS of actual received signal strength RSS and i-th reference node
ibetween Euclidean distance be:
Adopt k near neighbor method, mate respectively according to regular fingerprint map and random fingerprint map, for k the value that Euclidean distance is minimum, the mean value of the coordinate of k corresponding reference node, the i.e. estimated position of position:
Two estimated coordinates values of user position can be obtained according to regular fingerprint map and random fingerprint map, be respectively (x
1, y
1), (x
2, y
2);
Step 3: actual for the user signal strength vector received is converted into distance vector and mates with regular fingerprint distance map and random fingerprint distance map, adopt k near neighbor method to try to achieve the positioning result of twice coupling;
According to path-loss model formula, the expression formula obtaining the spacing of customer location and AP is:
Now, user received signal intensity value is converted into the distance of each AP of user distance, and the distance vector obtaining user is:
d=(d
1,d
2,…d
j,…d
n)
Wherein, d
jrepresent the distance between user and a jth AP; Definition d and d
ibetween Euclidean distance be:
Adopt k near neighbor method, mate respectively according to regular fingerprint distance map and random fingerprint distance map, for k the value that Euclidean distance is minimum, the mean value of the coordinate of k corresponding reference node is the estimated position of user, therefore, obtain two estimated coordinates values of user position, be respectively (x
3, y
3), (x
4, y
4);
Step 4: be averaged by the user estimated position coordinate obtained according to four layers of fingerprint matching, obtains final user estimated position coordinate;
Wherein, the expression formula of final user estimated position coordinate (x, y) is:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410680271.6A CN104902562B (en) | 2014-11-24 | 2014-11-24 | A kind of indoor orientation method based on multilayer fingerprint matching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410680271.6A CN104902562B (en) | 2014-11-24 | 2014-11-24 | A kind of indoor orientation method based on multilayer fingerprint matching |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104902562A true CN104902562A (en) | 2015-09-09 |
CN104902562B CN104902562B (en) | 2018-04-10 |
Family
ID=54034886
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410680271.6A Active CN104902562B (en) | 2014-11-24 | 2014-11-24 | A kind of indoor orientation method based on multilayer fingerprint matching |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104902562B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105137390A (en) * | 2015-09-14 | 2015-12-09 | 上海工程技术大学 | Indoor positioning method based on AP with adjustable transmitted power |
CN105338489A (en) * | 2015-11-17 | 2016-02-17 | 中国电子科技集团公司第五十四研究所 | Intelligent terminal for indoor positioning and bluetooth indoor positioning system |
CN105704676A (en) * | 2016-01-20 | 2016-06-22 | 上海交通大学 | Method for improving fingerprint indoor positioning precision through employing signal time correlation |
CN105718549A (en) * | 2016-01-16 | 2016-06-29 | 深圳先进技术研究院 | Airship based three-dimensional WiFi (Wireless Fidelity) fingerprint drawing system and method |
CN106612495A (en) * | 2015-10-23 | 2017-05-03 | 北斗导航位置服务(北京)有限公司 | Indoor positioning method and system based on propagation loss learning |
CN106610293A (en) * | 2015-10-23 | 2017-05-03 | 北斗导航位置服务(北京)有限公司 | Indoor positioning method and system based on intensity difference |
CN107426816A (en) * | 2017-07-24 | 2017-12-01 | 南京邮电大学 | The implementation method that a kind of WiFi positioning is merged with map match |
CN107438223A (en) * | 2016-05-26 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Indoor orientation method and device |
CN107484123A (en) * | 2017-07-21 | 2017-12-15 | 中山大学 | A kind of WiFi indoor orientation methods based on integrated HWKNN |
CN109275095A (en) * | 2018-11-09 | 2019-01-25 | 中科数字健康科学研究院(南京)有限公司 | A kind of indoor locating system based on bluetooth, positioning device and localization method |
CN110784837A (en) * | 2019-09-16 | 2020-02-11 | 华东交通大学 | Indoor positioning method, device, medium and electronic equipment |
CN112055308A (en) * | 2020-08-21 | 2020-12-08 | 中通服咨询设计研究院有限公司 | Multi-layer high-robustness fingerprint positioning method |
TWI799969B (en) * | 2021-08-30 | 2023-04-21 | 新加坡商鴻運科股份有限公司 | Indoor positioning method based on image visual features and electronic device |
US11698467B2 (en) | 2021-08-30 | 2023-07-11 | Nanning Fulian Fugui Precision Industrial Co., Ltd. | Indoor positioning method based on image visual features and electronic device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102711239A (en) * | 2012-05-10 | 2012-10-03 | 电子科技大学 | RSS (received signal strength) fingerprint database based secondary fuzzy clustering indoor-positioning method |
CN103458369A (en) * | 2013-08-09 | 2013-12-18 | 南京信息工程大学 | WiFi indoor positioning method based on anchor point and position fingerprints |
CN103596267A (en) * | 2013-11-29 | 2014-02-19 | 哈尔滨工业大学 | Fingerprint map matching method based on Euclidean distances |
-
2014
- 2014-11-24 CN CN201410680271.6A patent/CN104902562B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102711239A (en) * | 2012-05-10 | 2012-10-03 | 电子科技大学 | RSS (received signal strength) fingerprint database based secondary fuzzy clustering indoor-positioning method |
CN103458369A (en) * | 2013-08-09 | 2013-12-18 | 南京信息工程大学 | WiFi indoor positioning method based on anchor point and position fingerprints |
CN103596267A (en) * | 2013-11-29 | 2014-02-19 | 哈尔滨工业大学 | Fingerprint map matching method based on Euclidean distances |
Non-Patent Citations (1)
Title |
---|
PEERAPONG TORTEEKA: "Hybrid technique for indoor positioning system based on Wi-Fi received signal strength indication", 《2014 INTERNATIONAL CONFERENCE ON INDOOR POSITIONING AND INDOOR NAVIGATION(IPIN)》 * |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105137390B (en) * | 2015-09-14 | 2017-11-14 | 上海工程技术大学 | A kind of indoor orientation method based on adjustable transmission power AP |
CN105137390A (en) * | 2015-09-14 | 2015-12-09 | 上海工程技术大学 | Indoor positioning method based on AP with adjustable transmitted power |
CN106612495B (en) * | 2015-10-23 | 2019-10-25 | 北斗导航位置服务(北京)有限公司 | A kind of indoor orientation method and system based on propagation loss study |
CN106610293B (en) * | 2015-10-23 | 2019-10-01 | 北斗导航位置服务(北京)有限公司 | A kind of indoor orientation method and system based on intensity difference |
CN106612495A (en) * | 2015-10-23 | 2017-05-03 | 北斗导航位置服务(北京)有限公司 | Indoor positioning method and system based on propagation loss learning |
CN106610293A (en) * | 2015-10-23 | 2017-05-03 | 北斗导航位置服务(北京)有限公司 | Indoor positioning method and system based on intensity difference |
CN105338489B (en) * | 2015-11-17 | 2018-08-14 | 中国电子科技集团公司第五十四研究所 | A kind of intelligent terminal and bluetooth indoor locating system for indoor positioning |
CN105338489A (en) * | 2015-11-17 | 2016-02-17 | 中国电子科技集团公司第五十四研究所 | Intelligent terminal for indoor positioning and bluetooth indoor positioning system |
CN105718549A (en) * | 2016-01-16 | 2016-06-29 | 深圳先进技术研究院 | Airship based three-dimensional WiFi (Wireless Fidelity) fingerprint drawing system and method |
CN105704676B (en) * | 2016-01-20 | 2019-02-22 | 上海交通大学 | The method for improving fingerprint indoor position accuracy using signal time correlation |
CN105704676A (en) * | 2016-01-20 | 2016-06-22 | 上海交通大学 | Method for improving fingerprint indoor positioning precision through employing signal time correlation |
CN107438223A (en) * | 2016-05-26 | 2017-12-05 | 北京京东尚科信息技术有限公司 | Indoor orientation method and device |
CN107438223B (en) * | 2016-05-26 | 2019-12-03 | 北京京东尚科信息技术有限公司 | Indoor orientation method and device |
CN107484123B (en) * | 2017-07-21 | 2020-06-09 | 中山大学 | WiFi indoor positioning method based on integrated HWKNN |
CN107484123A (en) * | 2017-07-21 | 2017-12-15 | 中山大学 | A kind of WiFi indoor orientation methods based on integrated HWKNN |
CN107426816A (en) * | 2017-07-24 | 2017-12-01 | 南京邮电大学 | The implementation method that a kind of WiFi positioning is merged with map match |
CN109275095A (en) * | 2018-11-09 | 2019-01-25 | 中科数字健康科学研究院(南京)有限公司 | A kind of indoor locating system based on bluetooth, positioning device and localization method |
CN109275095B (en) * | 2018-11-09 | 2024-01-16 | 中科数字健康科学研究院(南京)有限公司 | Bluetooth-based indoor positioning system, positioning equipment and positioning method |
CN110784837A (en) * | 2019-09-16 | 2020-02-11 | 华东交通大学 | Indoor positioning method, device, medium and electronic equipment |
CN112055308A (en) * | 2020-08-21 | 2020-12-08 | 中通服咨询设计研究院有限公司 | Multi-layer high-robustness fingerprint positioning method |
CN112055308B (en) * | 2020-08-21 | 2024-02-27 | 中通服咨询设计研究院有限公司 | Multi-layer high-robustness fingerprint positioning method |
TWI799969B (en) * | 2021-08-30 | 2023-04-21 | 新加坡商鴻運科股份有限公司 | Indoor positioning method based on image visual features and electronic device |
US11698467B2 (en) | 2021-08-30 | 2023-07-11 | Nanning Fulian Fugui Precision Industrial Co., Ltd. | Indoor positioning method based on image visual features and electronic device |
Also Published As
Publication number | Publication date |
---|---|
CN104902562B (en) | 2018-04-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104902562A (en) | Indoor positioning method based on multi-layer fingerprint matching | |
CN103402258B (en) | Wi-Fi (Wireless Fidelity)-based indoor positioning system and method | |
Yan et al. | Review of range-based positioning algorithms | |
CN106488548B (en) | A kind of determination method and device of indoor multipath error | |
CN103686999B (en) | Indoor wireless positioning method based on WiFi signal | |
CN102752855A (en) | Indoor personnel positioning system and method based on path rule and prediction | |
CN105137390A (en) | Indoor positioning method based on AP with adjustable transmitted power | |
CN105474031A (en) | 3D sectorized path-loss models for 3D positioning of mobile terminals | |
CN104581931A (en) | Positioning method, device and terminal | |
CN104125538A (en) | WIFI (wireless fidelity) network based RSSI (received signal strength indicator) signal strength secondary locating method and device | |
CN102879762B (en) | Dynamic positioning method for vehicles in tunnel based on radio frequency receipt signal intensity value | |
CN105916201A (en) | KNN fingerprint positioning method based on RSS Euclidean distance fitting | |
CN106211327A (en) | A kind of method automatically generating location fingerprint data | |
CN104135766A (en) | Method of cooperative positioning between wireless networks based on grid division | |
CN110730418A (en) | Indoor three-dimensional positioning improvement algorithm based on least square method | |
CN102264127B (en) | Three-dimensional positioning method of Wireless Sensor Network based on degree of coplanarity | |
CN110972056A (en) | UWB indoor positioning method based on machine learning | |
CN102880673B (en) | A kind of indoor orientation method | |
CN107396280A (en) | A kind of indoor locating system and method based on RSSI | |
CN103096465A (en) | Environment self-adaption multi-target direct locating method | |
Arai et al. | Color radiomap interpolation for efficient fingerprint wifi-based indoor location estimation | |
CN104581944A (en) | WSN node locating method for self-adaptation precision control | |
CN104050254A (en) | Method for building 3D (three dimensional) indoor feature library by using indoor data | |
Bandiera et al. | TDOA localization in asynchronous WSNs | |
Lou et al. | High-accuracy positioning algorithm based on uwb |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |