CN110602658B - Continuous positioning method - Google Patents
Continuous positioning method Download PDFInfo
- Publication number
- CN110602658B CN110602658B CN201810605541.5A CN201810605541A CN110602658B CN 110602658 B CN110602658 B CN 110602658B CN 201810605541 A CN201810605541 A CN 201810605541A CN 110602658 B CN110602658 B CN 110602658B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- floor
- fingerprints
- positioning
- clustering
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—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)
- Navigation (AREA)
Abstract
The invention discloses a continuous positioning method, which comprises the following steps: 1. preparing data: dividing fingerprint points at each floor and building exit in a building, and then carrying out fingerprint acquisition; 2. clustering according to the similarity between the fingerprints; 3. adding connected information to the clustering area; 4. external sensor excitation; 5. and constructing an HMM model. The method improves the floor recognition effect in the continuous dynamic environment by means of wifi fingerprint matching, clustering, a Viterbi algorithm based on HMM, floor switching excitation and the like; the smoothness of continuous positioning can be improved, and the positioning error is reduced; the positioning continuity can be optimized; the effect of floor judgment can be optimized; the stability of floor switching can be optimized, and the experience of floor switching is improved; the efficiency of floor judgement can obtain promoting.
Description
Technical Field
The invention relates to a positioning method, in particular to a continuous positioning method.
Background
In indoor positioning, accurate floor judgment has important significance; in indoor positioning, the continuous and smooth positioning effect is significant to users. The existing positioning method has the following disadvantages: judging and jumping floors of floors, particularly in a courtyard area; the floor switching delay is large and the switching is not timely; floor switching errors; ping-pong switching; the positioning is not smooth and the shaking is large. Therefore, the invention provides a continuous positioning method, which improves the floor recognition effect in a continuous dynamic environment by using wifi fingerprint matching, clustering, a viterbi algorithm based on HMM, floor switching excitation and other means; the smoothness of continuous positioning can be improved, and the positioning error is reduced; the positioning continuity can be optimized; the effect of floor judgment can be optimized; the stability of floor switching can be optimized, and the experience of floor switching is improved; the efficiency of floor judgment can be improved.
Disclosure of Invention
The present invention is directed to a continuous positioning method to solve the above-mentioned problems of the background art.
In order to achieve the purpose, the invention provides the following technical scheme:
a continuous positioning method, comprising:
1. preparing data: dividing fingerprint points at each floor and building exit in the building, and then carrying out fingerprint acquisition;
2. clustering according to similarity between fingerprints: clustering the collected fingerprints according to Euclidean distances between the fingerprints, and automatically classifying the scattered fingerprints into corresponding areas after clustering;
3. adding connected information to the clustering area: adding the connectivity of each area by using the path topological relation in the building;
4. external sensor excitation: the system comprises a barometer, an accelerometer, a base station signal, an optical sensor and a magnetometer sensor, wherein the barometer, the accelerometer, the base station signal, the optical sensor and the magnetometer sensor are used for judging the processes of going upstairs, going downstairs and going upstairs and downstairs, and when the fact that floor switching or indoor and outdoor switching possibly occurs is judged, an observation probability matrix used for an HMM model is correspondingly adjusted;
5. constructing an HMM model:
number of HMM state variables: 7;
HMM observation number of variables: 3;
state transition matrix: a = [ a ] ij ]A is a matrix of 7x7, i belongs to [1,7 ]]J belongs to [1,7 ]]；
Observing a probability matrix: b = [ B ] j (k)]B is a 7x3 matrix, j belongs to [1,7 ]]K belongs to [1,3 ]]；
The state transition matrix A is generated as follows, where r j Is the area, r at time t +1 i Is the area, r, at time t ij There are four different values:
r ij =1, adjacent;
r ij = infinity, not contiguous;
r ij =2, adjacent across;
r ij =0, identical;
the generation method of the observation probability matrix B comprises the following steps:
on the basis of this formula, if the external sensor excitation in the fourth step occurs, the probability of the corresponding region changes.
As a further scheme of the invention: the fingerprint acquisition method in the first step comprises the following steps: planning and collecting routes or areas according to an indoor map; marking point positions needing to be acquired on the acquisition route; and recording the coordinates and fingerprint information of each point location to be acquired.
As a further scheme of the invention: the method for ensuring each layer of user to show the fingerprint in the first step comprises the following steps: before positioning, collecting fingerprint information of all target areas, and establishing a fingerprint database; during positioning, the positioning terminal collects the peripheral fingerprint information of the current position, compares the peripheral fingerprint information with fingerprints in a fingerprint database, searches for similar fingerprints, and determines the current position according to the positions of the similar fingerprints; the positioning process is an active matching fingerprint library, and the user is not required to present the fingerprint.
As a further scheme of the invention: in the fourth step, the ping-pong effect suppression method is adopted, and the switching must be performed for several times or only with a definite change excitation.
Compared with the prior art, the invention has the beneficial effects that:
the method improves the floor recognition effect in the continuous dynamic environment by means of wifi fingerprint matching, clustering, HMM-based viterbi algorithm, floor switching excitation and the like; the smoothness of continuous positioning can be improved, and the positioning error is reduced; the positioning continuity can be optimized; the effect of floor judgment can be optimized; the stability of floor switching can be optimized, and the experience of floor switching is improved; the efficiency of floor judgment can be improved.
Drawings
Fig. 1 is a flow chart of the continuous positioning method, where so represents various sensors for determining the change of floors and indoor and outdoor.
FIG. 2 is a schematic diagram of fingerprint acquisition points in a continuous positioning method.
FIG. 3 is a schematic diagram of clustering according to similarity between fingerprints in a continuous positioning method.
Fig. 4 is a schematic diagram of adding connected information to a clustering region in a continuous positioning method.
FIG. 5 is a schematic diagram of external sensor actuation in a continuous positioning method.
Fig. 6 is one of the schematic diagrams of an example of floor tracking in the continuous location method.
Fig. 7 is a second schematic diagram of an example of floor tracking in a continuous location method.
Detailed Description
The technical solution of the present patent will be described in further detail with reference to the following embodiments.
Referring to fig. 1-7, a method of continuous positioning includes:
1. preparing data: dividing fingerprint points at each floor and building exit in a building, and then carrying out fingerprint acquisition; as in fig. 2, the small circles indicate fingerprint acquisition points;
fingerprint: the fingerprint refers to a set of signal strengths of surrounding APs (wireless access points) received by a positioning terminal at a certain fixed position, and the set can be used as a feature for distinguishing different positions. Such as: (mac 1: rssi1, mac2: rssi2, mac3: rssi3, \ 8230; \8230;), wherein macx refers to the device address of the AP and rssix refers to the signal strength of the device received;
the fingerprint acquisition method comprises the following steps: planning and collecting routes or areas according to an indoor map; marking point positions needing to be acquired on the acquisition route; recording the coordinates and fingerprint information of each point location to be acquired; such as: the 10 th site acquisition information of the first floor of the department store (department store; F1;10, 100, 50 mac1;
method for ensuring each layer of user to present fingerprint: before positioning, collecting fingerprint information of all target areas, and establishing a fingerprint database; during positioning, the positioning terminal collects the peripheral fingerprint information of the current position, compares the peripheral fingerprint information with fingerprints in a fingerprint database, searches for similar fingerprints, and determines the current position according to the positions of the similar fingerprints; the positioning process is to actively match the fingerprint database, and the user does not need to show the fingerprint;
2. clustering according to similarity between fingerprints: clustering the acquired fingerprints according to Euclidean distances between the fingerprints, and automatically classifying the scattered fingerprints into corresponding areas (areas) after clustering, wherein the areas correspond to clustering results as shown in FIG. 3;
3. adding connected information to the clustering area: adding the connectivity of each area by utilizing the path topological relation inside the building; as shown in fig. 4;
4. external sensor excitation: the sensors such as the barometer, the accelerometer, the base station signal, the optical sensor and the magnetometer can be used for judging the processes of going upstairs, going downstairs, going in and out of the building and the like, and when the fact that floor switching or indoor and outdoor switching is possible is judged, the observation probability matrix for the HMM model is correspondingly adjusted;
whether the floor switching of the user occurs or not can be identified by measuring the change of the air pressure by utilizing the air pressure; whether a user goes upstairs or downstairs can be determined by using the accelerometer; the base station and the optical sensor can be used for identifying whether indoor and outdoor changes are carried out or not; with the magnetometer it is possible to identify whether the user is in the vicinity of the elevator; the devices are sensor devices which are commonly used in the market and are provided with mobile phones (positioning terminals), the methods for carrying out floor switching judgment and indoor and outdoor judgment by using the devices have ready-made algorithms, and the methods refer to the scheme that the advantages of the scheme are achieved, and meanwhile, the results of the existing algorithms can be conveniently utilized to serve as external input of the scheme, so that the effect is assisted to be improved; the fingerprint does not refer to the fingerprint of a human finger, but is a common term in the field of indoor positioning, and refers to the peripheral wireless WiFi signal characteristic (WiFi fingerprint) of a certain fixed position, and the principle of the fingerprint of the human body can be used for distinguishing different positions (WiFi fingerprint matching);
preferably, a ping-pong effect suppression method is adopted, and the switching must be realized continuously for several times or with a certain change excitation;
5. constructing an HMM model:
number of HMM state variables: 7;
HMM observes number of variables: 3;
state transition matrix: a = [ a ] ij ]A is a matrix of 7x7, i belongs to [1,7 ]]J belongs to [1,7 ]]；
Observing a probability matrix: b = [ B ] j (k)]B is a matrix of 7x3, j belongs to [1,7 ]]K is [1,3 ]]；
The state transition matrix A is generated as follows, where rj is area, r at time t +1 i Is the area, r, at time t ij There are four different values:
r ij =1, adjacent;
r ij infinity, not contiguous;
r ij =2, adjacent across;
r ij =0, same;
the observation probability matrix B is generated as follows:
all road sections in the denominator are selected to be the areas (Euclidean distance) top3 closest to the observation point Ok, and the meaning of the formula is as follows: the closer the region is to the observation point, the greater its probability. On the basis of this formula, if the external sensor excitation in the fourth step occurs, the probability of the corresponding region changes.
Floor tracking example: as shown in fig. 6-7, the small red square represents the observation position when the user actually walks, and often he is located in the middle of two or more regions, so that it is difficult to accurately determine which region belongs to, and more accurate path tracking can be obtained by using the Viterbi algorithm based on HMM; external excitation: such as: n times, on a certain floor, the air pressure change/accelerator presents obvious characteristics such as stair climbing, elevator lifting, geomagnetic occurrence and the like and can be used as external excitation of the change of the HMM; by using a model fingerprint method, on one hand, the judgment interference is reduced; on the other hand, the speed is increased. The star in fig. 6 represents the actual walking trajectory; the open arrows in fig. 7 represent the final inferred path and sequence of regions traversed.
Although the preferred embodiments of the present invention have been described in detail, the present invention is not limited to the above embodiments, and various changes can be made without departing from the spirit of the present invention within the knowledge of those skilled in the art.
Claims (4)
1. A continuous positioning method, comprising:
1. preparing data: dividing fingerprint points at each floor and building exit in the building, and then carrying out fingerprint acquisition;
2. clustering according to similarity among fingerprints: clustering the acquired fingerprints according to Euclidean distances between the fingerprints, and automatically classifying the scattered fingerprints into corresponding areas after clustering;
3. adding connected information to the clustering area: adding the connectivity of each area by utilizing the path topological relation inside the building;
4. external sensor excitation: the system comprises a barometer, an accelerometer, a base station signal, an optical sensor and a magnetometer sensor, wherein the barometer, the accelerometer, the base station signal, the optical sensor and the magnetometer sensor are used for judging the processes of going upstairs, going downstairs and going upstairs and downstairs, and when the fact that floor switching or indoor and outdoor switching possibly occurs is judged, an observation probability matrix used for an HMM model is correspondingly adjusted;
5. constructing an HMM model:
number of HMM state variables: 7;
HMM observes number of variables: 3;
state transition matrix: a = [ a ] ij ]A is a matrix of 7x7, i belongs to [1,7 ]]J belongs to [1,7 ]]；
Observing a probability matrix: b = [ B ] j (k)]B is 7x3Matrix, j belongs to [1,7 ]]K is [1,3 ]]；
The state transition matrix A is generated as follows, where r j Is the area, r at time t +1 i Is area, r at time t ij There are four different values:
r ij =1, adjacent;
r ij = infinity, not contiguous;
r ij =2, adjacent across;
r ij =0, identical;
the generation method of the observation probability matrix B comprises the following steps:
on the basis of this formula, if the external sensor excitation in the fourth step occurs, the probability of the corresponding region changes.
2. The continuous positioning method according to claim 1, wherein the fingerprint acquisition method in step one comprises: planning and collecting routes or areas according to an indoor map; marking point positions needing to be acquired on the acquisition route; and recording the coordinates and fingerprint information of each point location to be acquired.
3. The continuous positioning method according to claim 1, wherein the method for ensuring each layer of user to show fingerprint in step one comprises: before positioning, collecting fingerprint information of all target areas, and establishing a fingerprint database; during positioning, the positioning terminal collects the peripheral fingerprint information of the current position, compares the peripheral fingerprint information with fingerprints in a fingerprint library, searches for similar fingerprints, and determines the current position according to the positions of the similar fingerprints; the positioning process is an active matching fingerprint library, and the user is not required to present the fingerprint.
4. The continuous positioning method as claimed in claim 1, wherein the ping-pong effect suppression method is adopted in step four, and the switching must be performed several times in succession or with a certain variation excitation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810605541.5A CN110602658B (en) | 2018-06-13 | 2018-06-13 | Continuous positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810605541.5A CN110602658B (en) | 2018-06-13 | 2018-06-13 | Continuous positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110602658A CN110602658A (en) | 2019-12-20 |
| CN110602658B true CN110602658B (en) | 2022-12-30 |
Family
ID=68849590
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810605541.5A Active CN110602658B (en) | 2018-06-13 | 2018-06-13 | Continuous positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110602658B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152823A (en) * | 2013-02-26 | 2013-06-12 | 清华大学 | Wireless indoor positioning method |
| CN105372628A (en) * | 2015-11-19 | 2016-03-02 | 上海雅丰信息科技有限公司 | Wi-Fi-based indoor positioning navigation method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9838850B2 (en) * | 2017-05-12 | 2017-12-05 | Mapsted Corp. | Systems and methods for determining indoor location and floor of a mobile device |
-
2018
- 2018-06-13 CN CN201810605541.5A patent/CN110602658B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103152823A (en) * | 2013-02-26 | 2013-06-12 | 清华大学 | Wireless indoor positioning method |
| CN105372628A (en) * | 2015-11-19 | 2016-03-02 | 上海雅丰信息科技有限公司 | Wi-Fi-based indoor positioning navigation method |
Non-Patent Citations (2)
| Title |
|---|
| HIWL:An Unsupervised Learning Algorithm for IndoorWireless Localization;LI Li等;《2013 12th IEEE International Conference on Trust, Security and Privacy in Computing and Communications》;20131231;全文 * |
| 一种基于隐马尔可夫模型的指纹匹配定位算法;张静等;《物联网与无线通信——第二届全国物联网技术与应用学术会议和第十一届全国无线电应用与管理学术会议论文集》;20161210;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110602658A (en) | 2019-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111491367B (en) | Indoor positioning method based on crowd sensing and multi-fusion technology | |
| CN105263113B (en) | A kind of WiFi location fingerprints map constructing method and its system based on crowdsourcing | |
| CN109525935B (en) | Intelligent floor sensing method and control system for universal indoor environment | |
| CN106714110B (en) | Wi-Fi position fingerprint map automatic construction method and system | |
| CN110118549B (en) | Multi-source information fusion positioning method and device | |
| CN108632761B (en) | Indoor positioning method based on particle filter algorithm | |
| CN107635204B (en) | Indoor fusion positioning method and device assisted by exercise behaviors and storage medium | |
| US10466056B2 (en) | Trajectory matching using ambient signals | |
| Alzantot et al. | Crowdinside: Automatic construction of indoor floorplans | |
| KR101751731B1 (en) | Location tracking system and method | |
| CN107339992B (en) | Indoor positioning and landmark semantic identification method based on behaviors | |
| CN108534779B (en) | Indoor positioning map construction method based on track correction and fingerprint improvement | |
| CN104359480B (en) | Mixing chamber indoor location method by using inert navigation and Wi-Fi fingerprint | |
| CN103874191B (en) | A kind of localization method based on WiFi wireless networks | |
| US11885900B2 (en) | Method and system for tracking a mobile device | |
| CN112135248B (en) | WIFI fingerprint positioning method based on K-means optimal estimation | |
| CN111901749A (en) | High-precision three-dimensional indoor positioning method based on multi-source fusion | |
| CN113566820B (en) | Fused pedestrian positioning method based on position fingerprint and PDR algorithm | |
| CN111698774A (en) | Indoor positioning method and device based on multi-source information fusion | |
| CN108632763A (en) | A kind of indoor positioning weighting k nearest neighbor method based on WiFi fingerprints | |
| CN106646352B (en) | Bluetooth positioning accuracy optimization method based on sensor space mode | |
| WO2022022654A1 (en) | Indoor map generation method and apparatus | |
| CN111556432B (en) | Crowdsourcing fingerprint database construction method based on map information screening and matching | |
| JP5966542B2 (en) | Trajectory analysis apparatus and trajectory analysis program | |
| CN110602658B (en) | Continuous positioning method |
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 |