CN105866733A - Method and device for determining indoor position - Google Patents
Method and device for determining indoor position Download PDFInfo
- Publication number
- CN105866733A CN105866733A CN201610397509.3A CN201610397509A CN105866733A CN 105866733 A CN105866733 A CN 105866733A CN 201610397509 A CN201610397509 A CN 201610397509A CN 105866733 A CN105866733 A CN 105866733A
- Authority
- CN
- China
- Prior art keywords
- mean shift
- vector
- determined
- signal
- terminal
- 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
Classifications
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0252—Radio frequency fingerprinting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0257—Hybrid positioning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0273—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves using multipath or indirect path propagation signals in position determination
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/10—Small scale networks; Flat hierarchical networks
- H04W84/12—WLAN [Wireless Local Area Networks]
Abstract
The invention provides a method and device for determining an indoor position, and belongs to the technical field of positioning. The method and the device are used for solving the problem of low positioning precision of indoor positioning in the prior art. The method comprises the following steps that a first terminal obtains a first signal emitted by an emitting end at a pre-determined reference point; the first signal obtained by the first terminal is stored into a database; a second terminal obtains second signals emitted by at least one group of emitting end in a position to be determined; according to the mean vector and the standard deviation vector after the second signal deviation standardization, the emitting end weight is determined; according to the emitting end weight, the second signal and the first signal, a weighted K nearest neighbor algorithm is performed, and the coordinate point set of the position to be determined is determined; any one point of the coordinate point set of the position to be determined is determined into an initial point; a normal core function is selected by using the determined initial point as the center; the mean shift vector is determined; when the mean shift vector is smaller than the set threshold value, the minuend at the right side of the equation of the mean shift vector is determined to be the coordinate of the position to be determined.
Description
Technical field
The present invention relates to field of locating technology, more particularly relate to a kind of method determining indoor location and dress
Put.
Background technology
Indoor positioning refers to realize location, position in indoor environment, mainly use wireless telecommunications, architecture,
The multiple technologies such as inertial navigation location are integrated to form a set of indoor location locating system, thus realize personnel, object etc.
Monitoring position in the interior space.Owing to satellite fix cannot be used in indoor environment so that indoor positioning
Technology as the auxiliary positioning mode of satellite fix, solve satellite-signal arrive ground time more weak, can not wear
The problem of building thoroughly.
At present, indoor positioning technologies specifically includes that (English is: Radio Frequency based on RF identification
Identification, English abbreviation: RFID), ZigBee, (English is WLAN: Wireless Local
AreaNetworks, English abbreviation: WLAN), infrared technology etc..The common ground of above-mentioned technology is all
Utilize the signal message that multiple signal source is launched, determine the position of terminal by calculating the overlay area of superposition
Put.Thus it is little to cause the indoor positioning of above technology to there is signal cover, the problem that positioning precision is low.
In sum, prior art indoor positioning technologies, there is the problem that positioning precision is low.
Summary of the invention
The embodiment of the present invention provides a kind of method and device determining indoor location, in order to solve prior art room
, there is the problem that positioning precision is low in inner position technology.
The embodiment of the present invention provides a kind of method determining indoor location, including:
First terminal obtains, in predetermined reference point, the first signal that least one set transmitting terminal is launched, by institute
Described first signal stating first terminal acquisition stores database, and wherein, described first terminal gets
Described first signal is corresponding with described reference point locations;
The secondary signal that second terminal is launched at transmitting terminal described in position acquisition least one set to be determined, according to institute
State the mean vector after the standardization of secondary signal deviation and standard deviation vector, determine described transmitting terminal weight;Root
According to described transmitting terminal weight, described secondary signal and described first signal, it is weighted k nearest neighbor algorithm, really
Fixed described position coordinates point set to be determined;
Any point of described position coordinates point set to be determined is defined as initial point, with described determine initial
Centered by Dian, choose normal state kernel function, determine that Mean shift is vectorial and vectorial with described Mean shift
Corresponding Mean shift equality of vector;When described Mean shift vector is less than when setting threshold value, by described
Minuend on the right side of Mean shift equality of vector is defined as described position coordinates to be determined.
Preferably, before the signal that described first terminal obtains is stored database successively, also include:
The first signal obtaining described first terminal carries out Kalman filtering.
Preferably, when described Mean shift vector is more than when setting threshold value, according to initial Mean shift core
Window width updates described Mean shift vector sum Mean shift core window width;Wherein, described initial Mean shift
Preset value when core window width is to calculate described Mean shift vector for the first time.
The embodiment of the present invention also provides for a kind of device determining indoor location, including:
Creating unit, obtains what least one set transmitting terminal was launched for first terminal in predetermined reference point
First signal, described first signal obtained by described first terminal stores database, wherein, described
Described first signal that one terminal gets is corresponding with described reference point locations;
Computing unit, the launched at transmitting terminal described in position acquisition least one set to be determined for the second terminal
Binary signal, the mean vector after standardizing according to described secondary signal deviation and standard deviation vector, determine described
Transmitting terminal weight;According to described transmitting terminal weight, described secondary signal and described first signal, it is weighted
K nearest neighbor algorithm, determines described position coordinates point set to be determined;
Determine unit, for any point of described position coordinates point set to be determined is defined as initial point, with
Centered by the described initial point determined, choose normal state kernel function, determine Mean shift vector and with described
The Mean shift equality of vector that Mean shift vector is corresponding;When described Mean shift vector is less than setting threshold
During value, the minuend on the right side of described Mean shift equality of vector is defined as described position coordinates to be determined.
Preferably, described creating unit is additionally operable to:
The first signal obtaining described first terminal carries out Kalman filtering.
Preferably, described determine that unit is additionally operable to:
When described Mean shift vector is more than when setting threshold value, update according to initial Mean shift core window width
Described Mean shift vector sum Mean shift core window width;Wherein, described initial Mean shift core window width
For calculating preset value during described Mean shift vector for the first time.
In the embodiment of the present invention, it is provided that a kind of method and device determining indoor location, exist including first terminal
Predetermined reference point obtains the first signal that least one set transmitting terminal is launched, and is obtained by described first terminal
Described first signal store database, wherein, described first signal that described first terminal gets with
Described reference point locations is corresponding;Second terminal is launched at transmitting terminal described in position acquisition least one set to be determined
Secondary signal, the mean vector after standardizing according to described secondary signal deviation and standard deviation vector, determine institute
State transmitting terminal weight;According to described transmitting terminal weight, described secondary signal and described first signal, add
Power k nearest neighbor algorithm, determines described position coordinates point set to be determined;By described position coordinates point set to be determined
Any point closed is defined as initial point, centered by the described initial point determined, chooses normal state kernel function, depends on
Secondary determine Mean shift vector sum Mean shift core window width;When described Mean shift vector is less than setting
During threshold value, the minuend on the right side of described Mean shift equality of vector is defined as described position coordinates to be determined;
Wherein, described Mean shift core window width is according to all coordinate points in described position coordinates point set to be determined
Determine with the standard deviation of described initial point.In the above-mentioned methods, k nearest neighbor algorithm will be weighted and window width will be adaptive
Answer Mean shift to combine to position, first pass through weighting k nearest neighbor algorithm and determine position coordinates point set to be determined
Close, then determined the final coordinate of position to be determined by window width adaptive M ean shift.Above by algorithm
Position, simple to operate, improve positioning precision simultaneously.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to enforcement
In example or description of the prior art, the required accompanying drawing used is briefly described, it should be apparent that, describe below
In accompanying drawing be only some embodiments of the present invention, for those of ordinary skill in the art, do not paying
On the premise of going out creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
A kind of method flow schematic diagram determining indoor location that Fig. 1 provides for the embodiment of the present invention;
A kind of apparatus structure schematic diagram determining indoor location that Fig. 2 provides for the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clearly
Chu, be fully described by, it is clear that described embodiment be only a part of embodiment of the present invention rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creation
The every other embodiment obtained under property work premise, broadly falls into the scope of protection of the invention.
Before introducing a kind of method determining indoor location that the embodiment of the present invention is provided, first introduce several
The technical term that the present embodiments relate to:
1) RF identification, also known as radio frequency identification, is a kind of communication technology, can pass through radio signals
Identify specific objective and read and write related data, and setting up machinery or light between system and specific objective without identifying
Learn contact.
2) WLAN, it is particularly convenient data transmission system, it utilize radio frequency (English is:
Radio Frequency, English abbreviation: RF) technology, use electromagnetic wave, replace old-fashioned getting in the way
Copper twisted pairs (English is the Coaxial) LAN constituted, and is aloft communicatively coupled so that
WLAN can utilize simple access architecture to allow user pass through it, reaches, and " information is changed with oneself, facility
Walk all over the world " ideal state.
3) Zigbee is low-power consumption LAN protocol based on IEEE802.15.4 standard.According to this agreement
The technology of regulation is the wireless communication technology of a kind of short distance, low-power consumption.This title derives from the eight of honeybee
Word wave, due to honeybee (bee) be by circle in the air and " drone " (zig) shake wing " dancing " and companion
Transmission pollen place azimuth information, say, that honeybee relies on such mode to constitute the communication in colony.
Be characterized in closely, low complex degree, self-organizing, low-power consumption, low data rate, low cost.Main suitable
Share in automatically controlling and remote control field, various equipment can be embedded.In brief, ZigBee is exactly
A kind of cheap, the near radio networking mechanics of communication of low-power consumption.
What Fig. 1 was exemplary shows that a kind of method flow determining indoor location that the embodiment of the present invention provides shows
Being intended to, the method can apply in indoor positioning.
As it is shown in figure 1, a kind of method determining indoor location that the embodiment of the present invention provides, including following step
Rapid:
Step 101, first terminal obtains the first of least one set transmitting terminal transmitting in predetermined reference point
Signal, described first signal obtained by described first terminal stores database, and wherein, described first eventually
Described first signal that end gets is corresponding with described reference point locations;
Step 102, the second letter that the second terminal is launched at transmitting terminal described in position acquisition least one set to be determined
Number, the mean vector after standardizing according to described secondary signal deviation and standard deviation vector, determine described transmitting
End weight;According to described transmitting terminal weight, described secondary signal and described first signal, it is weighted K near
Adjacent algorithm, determines described position coordinates point set to be determined;
Step 103, is defined as initial point, with described by any point of described position coordinates point set to be determined
Centered by the initial point determined, choose normal state kernel function, determine Mean shift vector sum Mean shift successively
Core window width;When described Mean shift vector is less than when setting threshold value, by described Mean shift equality of vector
The minuend on right side is defined as described position coordinates to be determined;Wherein, described Mean shift core window width is root
Determine according to the standard deviation of all coordinate points in described position coordinates point set to be determined Yu described initial point.
It should be noted that terminal can be smart mobile phone, it is also possible to be panel computer, implement in the present invention
In example, the concrete form of terminal is not limited.
In a step 101, first terminal obtains what least one set transmitting terminal was launched in predetermined reference point
First signal, wherein, the reference point residing for first terminal is predetermined, and the quantity of reference point is permissible
Including multiple, in embodiments of the present invention, the particular number of the reference point residing for first terminal is not limited.
First terminal obtains, in reference point, the first signal that least one set transmitting terminal is launched, and wherein, transmitting terminal can
Multiple to include, in embodiments of the present invention, the quantity of transmitting terminal is not limited.First terminal will obtain
To many groups signal be respectively stored in database, if it should be noted that first terminal is will to obtain for the first time
The signal got stores database, then need first to set up database, wherein first terminal get first
Signal is corresponding with reference point locations.Such as, when the first letter that first terminal will get first reference point
Number set up database, then can be the first database by the database identification of foundation, wherein, the first data
In storehouse, the first signal of storage is corresponding with first terminal place reference point locations, and first terminal is second reference
The signal that point gets is corresponding with the position obtaining signal, stores in the first database.
It should be noted that the letter of the first signal that first terminal can be received due to complicated indoor environment
Number intensity interferes, and therefore, in embodiments of the present invention, needs the first letter receiving first terminal
Number carry out Kalman filtering, the noise filtering in the signal received by first terminal.
Further, when carrying out Kalman filtering, in the first signal that first terminal is received, have prominent
So the signal strength signal intensity of change judges, (is somebody's turn to do when certain point prediction value and its measured value differ by more than a certain numerical value
The determination of numerical value is relevant with the signal strength values received), and multiple measured values that this value is below are pre-with current
When the difference of measured value is more than this numerical value, it is judged that this point is normal transition point, now, the measured value that will currently put
It is set to the predicted value currently put;It is otherwise abnormal transition point, proceeds filtering according to original process.
In a step 102, the second terminal launch at transmitting terminal described in position acquisition least one set to be determined the
Binary signal, the mean vector after standardizing according to described secondary signal deviation and standard deviation vector, determine described
Transmitting terminal weight;According to described transmitting terminal weight, described secondary signal and described first signal, it is weighted
K nearest neighbor algorithm, determines described position coordinates point set to be determined.
Further, the mean vector of the secondary signal that the second terminal receives and standard deviation vector are carried out from
Difference standardization, and then calculate transmitting terminal weight in weighting k nearest neighbor algorithm, the second terminal is received many
The first signal that individual signal stores up with databases mates, and returns location point to be determined.
Assuming that the second terminal some location point to be determined receive the signal strength signal intensity of m secondary signal to
Amount, each signal strength signal intensity vector has n to arrange, and n is transmitting terminal number herein, then this signal matrix is m × n.
This matrix is taken average by row, then obtains the mean vector of 1 × n.Therefrom select the number that signal strength values is minimum
A and several B of signal strength values maximum.Each signal strength values in mean vector is all deducted A, and removes
With (B-A).In like manner, this matrix is taken standard deviation by row, do identical calculating.By by above-mentioned process
Signal strength values vector, is identified as the standard after the mean vector after deviation standardization standardizes with deviation
Difference vector.
Further, secondary signal is weighted k nearest neighbor algorithm, specifically includes procedure below:
First, the weights omega of jth transmitting terminal in multiple transmitting terminals is calculated by following first formulaj:
In formula (1), μjFor receive in position to be determined transmitting terminal deviation standardization after average
The jth number of vector, sjThe jth number of standard deviation vector after standardizing for deviation.
Then, the signal received at a certain reference point and position to be determined are calculated by following equation (2)
Put Euclidean distance a little:
In formula (2), diRepresent the Euclidean distance of i-th reference point and location point to be determined, Rij
Represent that i-th reference point receives jth number in the mean vector of signal,Represent in position to be determined
Receive jth number in the mean vector of signal.
Finally, according to weighting k nearest neighbor algorithm, by formula (3), described position coordinates to be determined is calculated:
In formula (3), YpBeing the coordinate of pth point in K closest approach, ε is the least number, keeps away
Exempting from denominator is 0.
In step 103, any point of position coordinates point set to be determined is defined as initial point, to determine
Initial point centered by, choose normal state kernel function, determine Mean shift successively by following equation (4)
Vector sum Mean shift core window width:
Wherein, mh,GX () is Mean shift vector, n is the number at current region midpoint, xiFor current region
The coordinate of middle i-th point, g (x) is the profile function of normal state kernel function, and h is Mean shift core window width, and x is
The position of current region Midst density maximum point, when Mean shift vector is more than threshold value, is updated to public affairs by x
Minuend on the right side of formula (4) equation.
Further, normal state kernel function is determined by following equation (5):
Wherein, d representation space dimension, his profile function can pass through following equation (6) and determine:
In formula (6), Mean shift core window width is that h, h can use following equation (7) to represent:
In formula (7), s be current region centered by x standard deviation a little, can be by following public affairs
Formula (8) determines:
When Mean shift vector is less than when setting threshold value, by the minuend on the right side of Mean shift equality of vector
It is defined as position coordinates to be determined;Wherein, Mean shift equality of vector is formula (4), formula (4)
The minuend on right side is the point that current region Midst density is maximum, will the position of the maximum point of region Midst density true
It is set to position coordinates to be determined.
Further, when Mean shift vector is more than when setting threshold value, according to initial Mean shift core window
Wide renewal Mean shift vector sum Mean shift core window width;Wherein, initial Mean shift core window width is
Calculate preset value during described Mean shift vector for the first time.
It should be noted that before calculating Mean shift vector for the first time, an initial Mean can be given
Shift core window width, according to given initial value, calculates the Mean shift vector under circulation for the first time.?
In circulation every time afterwards, all can calculate Mean shift vector sum Mean shift core window successively according to formula
Wide.When the Mean shift vector updated in previous cycle, can circulate, according to last time, the Mean shift obtained
Core window width calculates.
In the embodiment of the present invention, it is provided that a kind of method and device determining indoor location, weighting k nearest neighbor is calculated
Method and window width adaptive M ean shift combine and position, and first pass through weighting k nearest neighbor algorithm and determine to be determined
Position coordinates point set, the more final coordinate of position to be determined is determined by window width adaptive M ean shift.
Position above by algorithm, simple to operate, improve positioning precision simultaneously.
Based on same inventive concept, embodiments provide a kind of device determining indoor location, due to
This device solves the principle of technical problem and determines that the method for indoor location is similar to a kind of, the therefore reality of this device
Execute the enforcement of the method for may refer to, repeat no more in place of repetition.
As in figure 2 it is shown, a kind of apparatus structure schematic diagram determining indoor location provided for the embodiment of the present invention,
Including creating unit 201, computing unit 202 and determine unit 203.
Creating unit 201, obtains least one set transmitting terminal for first terminal in predetermined reference point and sends out
The first signal penetrated, described first signal obtained by described first terminal stores database, wherein, institute
State described first signal that first terminal gets corresponding with described reference point locations;
Computing unit 202, launches at transmitting terminal described in position acquisition least one set to be determined for the second terminal
Secondary signal, mean vector and the standard deviation vector after standardizing according to described secondary signal deviation, determine
Described transmitting terminal weight;According to described transmitting terminal weight, described secondary signal and described first signal, carry out
Weighting k nearest neighbor algorithm, determines described position coordinates point set to be determined;
Determine unit 203, for any point of described position coordinates point set to be determined is defined as initial point,
Centered by the described initial point determined, choose normal state kernel function, determine Mean shift vector and with institute
State the Mean shift equality of vector that Mean shift vector is corresponding;When described Mean shift vector is less than setting
When determining threshold value, the minuend on the right side of described Mean shift equality of vector is defined as described position to be determined and sits
Mark.
Preferably, described creating unit 201 is additionally operable to:
The first signal obtaining described first terminal carries out Kalman filtering.
Preferably, described determine that unit 203 is additionally operable to:
When described Mean shift vector is more than when setting threshold value, update according to initial Mean shift core window width
Described Mean shift vector sum Mean shift core window width;Wherein, described initial Mean shift core window width
For calculating preset value during described Mean shift vector for the first time.
Should be appreciated that the function realized according to unit that one of the above determines that the device of indoor location includes is only
The logical partitioning carried out, in actual application, can carry out superposition or the fractionation of said units.And this enforcement
A kind of method one determining indoor location that the function that the device that example provides is realized provides with above-described embodiment
One is corresponding, the more detailed handling process realized for this device, in said method embodiment one
It is described in detail, is not described in detail herein.
Those skilled in the art are it should be appreciated that embodiments of the invention can be provided as method, system or meter
Calculation machine program product.Therefore, the present invention can use complete hardware embodiment, complete software implementation or knot
The form of the embodiment in terms of conjunction software and hardware.And, the present invention can use and wherein wrap one or more
Computer-usable storage medium containing computer usable program code (include but not limited to magnetic disc store,
CD-ROM, optical memory etc.) form of the upper computer program implemented.
The present invention is with reference to method, equipment (system) and computer program product according to embodiments of the present invention
The flow chart of product and/or block diagram describe.It should be understood that can by computer program instructions flowchart and
/ or block diagram in each flow process and/or flow process in square frame and flow chart and/or block diagram and/
Or the combination of square frame.These computer program instructions can be provided to all-purpose computer, special-purpose computer, embedding
The processor of formula processor or other programmable data processing device is to produce a machine so that by calculating
The instruction that the processor of machine or other programmable data processing device performs produces for realizing at flow chart one
The device of the function specified in individual flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions may be alternatively stored in and computer or the process of other programmable datas can be guided to set
In the standby computer-readable memory worked in a specific way so that be stored in this computer-readable memory
Instruction produce and include the manufacture of command device, this command device realizes in one flow process or multiple of flow chart
The function specified in flow process and/or one square frame of block diagram or multiple square frame.
These computer program instructions also can be loaded in computer or other programmable data processing device, makes
Sequence of operations step must be performed to produce computer implemented place on computer or other programmable devices
Reason, thus the instruction performed on computer or other programmable devices provides for realizing flow chart one
The step of the function specified in flow process or multiple flow process and/or one square frame of block diagram or multiple square frame.
Although preferred embodiments of the present invention have been described, but those skilled in the art once know base
This creativeness concept, then can make other change and amendment to these embodiments.So, appended right is wanted
Ask and be intended to be construed to include preferred embodiment and fall into all changes and the amendment of the scope of the invention.
Obviously, those skilled in the art can carry out various change and modification without deviating from this to the present invention
Bright spirit and scope.So, if the present invention these amendment and modification belong to the claims in the present invention and
Within the scope of its equivalent technologies, then the present invention is also intended to comprise these change and modification.
Claims (7)
1. the method determining indoor location, it is characterised in that including:
First terminal obtains, in predetermined reference point, the first signal that least one set transmitting terminal is launched, by institute
Described first signal stating first terminal acquisition stores database, and wherein, described first terminal gets
Described first signal is corresponding with described reference point locations;
The secondary signal that second terminal is launched at transmitting terminal described in position acquisition least one set to be determined, according to institute
State the mean vector after the standardization of secondary signal deviation and standard deviation vector, determine described transmitting terminal weight;Root
According to described transmitting terminal weight, described secondary signal and described first signal, it is weighted k nearest neighbor algorithm, really
Fixed described position coordinates point set to be determined;
Any point of described position coordinates point set to be determined is defined as initial point, with described determine initial
Centered by Dian, choose normal state kernel function, determine that Mean shift is vectorial and vectorial with described Mean shift
Corresponding Mean shift equality of vector;When described Mean shift vector is less than when setting threshold value, by described
Minuend on the right side of Mean shift equality of vector is defined as described position coordinates to be determined.
2. the method for claim 1, it is characterised in that described in described first terminal is obtained
Before first signal stores database, also include:
The first signal obtaining described first terminal carries out Kalman filtering.
3. the method for claim 1, it is characterised in that described determine Mean shift vector, also
Including determining Mean shift core window width, wherein, described Mean shift core window width is according to described to be determined
In position coordinates point set, the standard deviation of all coordinate points and described initial point determines.
4. method as claimed in claim 3, it is characterised in that when described Mean shift vector is more than setting
When determining threshold value, update described Mean shift vector sum Mean shift according to initial Mean shift core window width
Core window width;Wherein, described initial Mean shift core window width is for calculating described Mean shift vector for the first time
Time preset value.
5. the device determining indoor location, it is characterised in that including:
Creating unit, obtains what least one set transmitting terminal was launched for first terminal in predetermined reference point
First signal, described first signal obtained by described first terminal stores database, wherein, described
Described first signal that one terminal gets is corresponding with described reference point locations;
Computing unit, the launched at transmitting terminal described in position acquisition least one set to be determined for the second terminal
Binary signal, the mean vector after standardizing according to described secondary signal deviation and standard deviation vector, determine described
Transmitting terminal weight;According to described transmitting terminal weight, described secondary signal and described first signal, it is weighted
K nearest neighbor algorithm, determines described position coordinates point set to be determined;
Determine unit, for any point of described position coordinates point set to be determined is defined as initial point, with
Centered by the described initial point determined, choose normal state kernel function, determine Mean shift vector and with described
The Mean shift equality of vector that Mean shift vector is corresponding;When described Mean shift vector is less than setting threshold
During value, the minuend on the right side of described Mean shift equality of vector is defined as described position coordinates to be determined.
6. device as claimed in claim 5, it is characterised in that described creating unit is additionally operable to:
The first signal obtaining described first terminal carries out Kalman filtering.
7. device as claimed in claim 5, it is characterised in that described determine that unit is additionally operable to:
When described Mean shift vector is more than when setting threshold value, update according to initial Mean shift core window width
Described Mean shift vector sum Mean shift core window width;Wherein, described initial Mean shift core window width
For calculating preset value during described Mean shift vector for the first time.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610397509.3A CN105866733A (en) | 2016-06-07 | 2016-06-07 | Method and device for determining indoor position |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610397509.3A CN105866733A (en) | 2016-06-07 | 2016-06-07 | Method and device for determining indoor position |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105866733A true CN105866733A (en) | 2016-08-17 |
Family
ID=56676926
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610397509.3A Pending CN105866733A (en) | 2016-06-07 | 2016-06-07 | Method and device for determining indoor position |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105866733A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108845288A (en) * | 2018-04-19 | 2018-11-20 | 网易(杭州)网络有限公司 | Space-location method, system and terminal device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110149266A1 (en) * | 2009-12-17 | 2011-06-23 | The Boeing Company | Position and Orientation Determination Using Movement Data |
CN102387345A (en) * | 2011-09-09 | 2012-03-21 | 浙江工业大学 | Safety monitoring system based on omnidirectional vision for old people living alone |
CN102685887A (en) * | 2012-05-29 | 2012-09-19 | 苏州大学 | Method, device and system for positioning node in wireless sensor network |
CN104883734A (en) * | 2015-05-12 | 2015-09-02 | 北京邮电大学 | Indoor passive positioning method based on geographic fingerprints |
CN104936148A (en) * | 2015-07-03 | 2015-09-23 | 中南大学 | Indoor positioning method for WIFI (Wireless Fidelity) based on fuzzy KNN (k-Nearest Neighbor) |
CN105472733A (en) * | 2015-11-17 | 2016-04-06 | 华南理工大学 | Indoor positioning method based on AP selection |
-
2016
- 2016-06-07 CN CN201610397509.3A patent/CN105866733A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110149266A1 (en) * | 2009-12-17 | 2011-06-23 | The Boeing Company | Position and Orientation Determination Using Movement Data |
CN102387345A (en) * | 2011-09-09 | 2012-03-21 | 浙江工业大学 | Safety monitoring system based on omnidirectional vision for old people living alone |
CN102685887A (en) * | 2012-05-29 | 2012-09-19 | 苏州大学 | Method, device and system for positioning node in wireless sensor network |
CN104883734A (en) * | 2015-05-12 | 2015-09-02 | 北京邮电大学 | Indoor passive positioning method based on geographic fingerprints |
CN104936148A (en) * | 2015-07-03 | 2015-09-23 | 中南大学 | Indoor positioning method for WIFI (Wireless Fidelity) based on fuzzy KNN (k-Nearest Neighbor) |
CN105472733A (en) * | 2015-11-17 | 2016-04-06 | 华南理工大学 | Indoor positioning method based on AP selection |
Non-Patent Citations (1)
Title |
---|
王丽佳等: ""采用改进 Mean Shift 算法的移动机器人行人跟踪"", 《光学精密工程》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108845288A (en) * | 2018-04-19 | 2018-11-20 | 网易(杭州)网络有限公司 | Space-location method, system and terminal device |
CN108845288B (en) * | 2018-04-19 | 2021-01-15 | 网易(杭州)网络有限公司 | Space positioning method, system and terminal equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105430664B (en) | It is a kind of to be fitted the method and apparatus that path loss is propagated in prediction based on classification | |
CN103889051B (en) | Indoor WLAN fingerprint positioning methods based on AP ID filterings and Kalman filtering | |
CN108871332A (en) | A kind of RFID indoor locating system and method based on XGBoost | |
CN107730000A (en) | Coolant leakage detection method and device for air-conditioning | |
CN109756842B (en) | Wireless indoor positioning method and system based on attention mechanism | |
CN108984785A (en) | A kind of update method and device of the fingerprint base based on historical data and increment | |
CN109212476A (en) | A kind of RFID indoor positioning algorithms based on DDPG | |
CN114501530B (en) | Method and device for determining antenna parameters based on deep reinforcement learning | |
CN107179524A (en) | Fire-fighting equipment localization method, device, system and computer-readable recording medium | |
CN113596989B (en) | Indoor positioning method and system for intelligent workshop | |
CN110232584A (en) | Parking lot site selecting method, device, computer readable storage medium and terminal device | |
CN107588775A (en) | A kind of new indoor localization method | |
CN103298107A (en) | Indoor wireless positioning AP (access point) rapid deployment method based on weighted undirected graph | |
Gomes et al. | Clustering and hierarchical classification for high-precision RFID indoor location systems | |
CN112272074A (en) | Information transmission rate control method and system based on neural network | |
CN108260076A (en) | Method, platform and the system of unmanned plane running orbit monitoring | |
CN107526058A (en) | Indoor orientation method, apparatus and system | |
CN113915840B (en) | Refrigerator and food material positioning method thereof | |
CN105866733A (en) | Method and device for determining indoor position | |
Xie et al. | An improved indoor location algorithm based on backpropagation neural network | |
CN109899932A (en) | The control method and device of air-conditioning | |
CN112469116A (en) | Positioning method, positioning device, electronic equipment and computer readable storage medium | |
CN109889981A (en) | A kind of localization method and system based on two sorting techniques | |
CN112738883B (en) | Method and device for determining position of air base station | |
Ren et al. | A novel high precision and low consumption indoor positioning algorithm for internet of things |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160817 |
|
RJ01 | Rejection of invention patent application after publication |