CN109541533A - A kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering - Google Patents
A kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering Download PDFInfo
- Publication number
- CN109541533A CN109541533A CN201811416628.4A CN201811416628A CN109541533A CN 109541533 A CN109541533 A CN 109541533A CN 201811416628 A CN201811416628 A CN 201811416628A CN 109541533 A CN109541533 A CN 109541533A
- Authority
- CN
- China
- Prior art keywords
- target labels
- kalman filtering
- unscented kalman
- rssi
- observation
- 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
-
- 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
- G01S5/0294—Trajectory determination or predictive filtering, e.g. target tracking or Kalman filtering
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
Abstract
The invention discloses a kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering, belong to Internet of Things technical field of RFID, this method comprises: initially setting up the state model and observation model of target labels movement, and the Nonlinear Mapping relationship of tag signal strength RSSI and distance are constructed by off-line training；Then according to constructing objective function after the RSSI estimated distance of target labels, and the observation vector of acquisition system is solved to objective function by particle group optimizing；To filtering before being carried out again by Unscented kalman filtering to observation vector；Finally smoothly the track after the completion of filtering is smoothed with segmentation RTS.The present invention improves the precision of systematic observation vector by way of non-linear support vector regression and particle group optimizing, and smoothly track is carried out smoothly by Unscented kalman filtering and segmentation RTS on this basis, the error for reducing movement objective orbit tracking, greatly improves the precision of track following.
Description
Technical field
The radio frequency knowledge based on Unscented kalman filtering (Unscented Kalman Filter, UKF) that the present invention relates to a kind of
Not (Radio Frequency Identification, RFID) label indoor tracking method and equipment, belong to Internet of Things radio frequency
Identification technology field.
Background technique
Radio frequency identification is a kind of automatic identification technology of wireless communication, it completes Item Information using radio frequency signal
The advantages that acquisition and transmission have non line of sight, non-contact, at low cost, strong environmental adaptability, is widely used in ceasing with life
Cease relevant materials supply chain, material flow tracking, communications and transportation, access control, the fields such as Workshop Production.RFID system passes through read-write
Communication between device and electronic tag can carry out information data collection to object, provide for upper layer application and accurately and effectively count
According to support.RFID locating and tracking technology carries out object to be measured using the bidirectional data exchange between reader and electronic tag
Positioning and tracking, the location information of article is got while obtaining article ID, becomes the research hotspot of indoor positioning technologies.
Most common technology is GPS positioning by satellite positioning in outdoor positioning tracking at present.But ring indoors
In border, due to building construction complexity, satellite-signal decaying is caused even to be lost, and indoor spaces limited area, so defending
Star communication is unable to satisfy the high-precision demand of indoor positioning tracking.More commonly used technology is infrared in positioning indoors at present
Line, ZigBee, Wi-Fi, RFID etc..Wherein, RFID location technology is that have at low cost, strong environmental adaptability, Ke Yi
The advantages that reaching higher positioning accuracy in the very short time, therefore RFID location technology is got growing concern for.RFID
Positioning can be applied to item tracking, such as warehouse logistics, workshop inspection etc., can be used for personnel positioning such as mine staff
Tracking, the elderly's tracking, hospital patient management etc..Frequency recognition positiming method can be divided into location algorithm and non-ranging algorithm.
The essence of location algorithm is that the orientation or distance between measurement label and reader are positioned, the ranging side that each algorithm uses
Method is different, such as TOA, TDOA, AOA, RSSI etc..Range-free localization algorithm is based on scene analysis method.For example, VIRE method
Reference label is introduced, but the density of positioning accuracy and reference label is closely related, the bigger position error of density is smaller, still
When density is excessive, the interference of signal can be generated between label again, leads to the information collected inaccuracy, positioning accuracy is not high.
Summary of the invention
Goal of the invention: in view of the above shortcomings of the prior art, the object of the present invention is to provide one kind to be based on Unscented kalman
The RFID label tag indoor tracking method and equipment of filtering, this method carry out off-line training using non-linear support vector regression, lead to
The observation vector that population iteration obtains system is crossed, then observation vector is filtered by Unscented kalman filtering, finally
It is smoothed with the track that RTS completes filtering, effectively improves indoor tracking precision.
Technical solution: to achieve the above object, the technical solution adopted by the present invention are as follows:
A kind of RFID label tag indoor tracking method based on Unscented kalman filtering, this method comprises the following steps:
(1) according to the motion state of target labels, the state model x of system is establishedk+1=f (xk)+WkWith observation model zk
=h (xk)+Vk；Wherein subscript k indicates moment, xkThe state vector of expression system, including target labels in the position of x-axis direction
And speed and target labels are in the position and speed in y-axis direction；zkThe observation vector of expression system, f indicate nonlinear state
Equation functions, h indicate non-linear observation equation functions, WkIndicate zero-mean, the process noise that covariance matrix is Q, VkIndicate zero
Mean value, the observation noise that covariance matrix is R；
(2) RSSI for being evenly distributed on indoor reference label and reference label are passed through at a distance from reader non-linear
SVR is trained, and constructs the Nonlinear Mapping relationship of RSSI and distance；
(3) RSSI of the target labels at current time is obtained, according to the Nonlinear Mapping relationship that step (2) construct, estimation
Distance between target labels and reader out, building calculate the Nonlinear System of Equations of target labels position, and by nonlinear equation
Group Solve problems are converted into the optimization problem of objective function, are solved by particle group optimizing to objective function, obtain current time
Target labels observation coordinate；
(4) to filter before being carried out by observation track of the Unscented kalman filtering algorithm to the target labels before current time
Wave；
(5) to smooth after carrying out to filtered track, smoothed out track is the indoor tracking track of target labels.
In preferred embodiments, in the step (1) system state vector are as follows: xk=[pxk vx(k) pyk
vy(k)]T；Wherein, pxkIt is target labels in the position of x-axis direction, vx(k)Speed for target labels in x-axis direction, pykFor mesh
Mark position of the label in y-axis direction, vy(k)Speed for target labels in y-axis direction；
The nonlinear state function of system is related with the motion state of system；For the target labels of uniform motion, system
State model are as follows:T is sampling time interval；
For the target labels at the uniform velocity turned, the state model of system are as follows:Wherein T is sampling time interval, and ω is turning rate；
The observation model of system are as follows:
In preferred embodiments, step (2) specifically includes:
(2.1) reference is established according to the signal strength indication RSSI for being evenly distributed on indoor reference label that reader obtains
The RSSI matrix of label；The distance matrix of reference label is established according to the distance between reference label and reader；
(2.2) using the RSSI of reference label as the input value of sample, using the distance of reference label as the expectation of sample
Output valve, the RSSI of reference label are trained with apart from one-to-one correspondence by non-linear SVR；
(2.3) it according to the training result of non-linear SVR, establishes non-thread between input signal strength RSSI and output distance
Property mapping relations.
In preferred embodiments, the Nonlinear System of Equations in step (3) are as follows:
Wherein, diIt is the distance between the target labels estimated and i-th of reader, (x, y) is target labels coordinate,
(Xi,Yi) be reader position coordinates, i ∈ (1, M)；M is the number of reader.
In preferred embodiments, the objective function of the particle group optimizing in step (3) are as follows:
In preferred embodiments, the step of Unscented kalman filtering in the step (4) includes:
(4.1) the system mode x at k momentkIt is converted using UT and obtains Sigma point, and obtained using ratio amendment sampling policy
Take the corresponding mean value weight of Sigma pointAnd variance weight
(4.2) the one-step prediction X of Sigma point is calculatedi,k+1/k=f (xi,k), and the estimated value of system state amount is calculatedAnd error co-variance matrixWherein n is system mode vector
Dimension；
(4.3) the Sigma point of prediction is substituted into the observed quantity Z that observational equation calculates predictioni,k+1/k=h (Xi,k+1/k), and count
It calculates and obtains the predicted value of systematic perspective measurementAnd covariance, and according to the covariance of system prediction value
Calculate Kalman gainWherein:
(4.4) the observation vector z of subsequent time is utilizedk+1It is updated, obtains estimated value last in recursive processAnd varianceTarget after obtaining filtering estimation
Position.
In preferred embodiments, backward smoothly smooth using segmentation RTS in the step (5), by label
The whole process of movement is divided into multistage, and every section gradually reverse smooth.
A kind of computer equipment that another aspect of the present invention provides, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, based on nothing described in realization when the computer program is loaded on processor
The RFID label tag indoor tracking method of mark Kalman filtering.
The utility model has the advantages that compared with the prior art, the advantages of the present invention are as follows: in RFID label tag room according to the present invention with
Track method is effectively improved using the signal strength indication of non-linear support vector regression label with apart from off-line training is carried out
The precision of RSSI ranging, according to objective function is constructed after the RSSI estimated distance of target labels, by particle group optimizing to target
Then the observation vector that function solves acquisition system passes through Unscented kalman filtering so that the observation vector precision of system is higher
Observation vector is filtered, finally smoothly the track after the completion of filtering is smoothed with segmentation RTS, is effectively improved
Indoor tracking precision.Compared with prior art, the present invention realizes the feelings in less reference label and reader quantity
Under condition, the precision of systematic observation vector is improved by way of non-linear support vector regression and particle group optimizing, and
Smoothly track is carried out smoothly by Unscented kalman filtering and segmentation RTS on the basis of this, rather than directlys adopt target labels and arrives
The distance between reader be used as observation vector, the present invention using the position coordinates of target labels be used as observation vector, by SVR with
PSO is filtered after improving observation vector precision and smoothly, reduces the error of movement objective orbit tracking, greatly improve
The precision of track following.
Detailed description of the invention
Fig. 1 is the system model figure of label tracking in the embodiment of the present invention；
Fig. 2 is the flow diagram of label tracking in the embodiment of the present invention；
Fig. 3 is the motion model analogous diagram of label tracking in the embodiment of the present invention；
Fig. 4 is the simulation result Error Graph of label tracking in the embodiment of the present invention.
Specific embodiment
Below in conjunction with the drawings and specific embodiments, present invention is further described in detail.
As shown in Figure 1, being the system model figure that label indoor tracking method is implemented, specific requirement is as follows: in target area
4 readers and equally distributed M reference label are placed, a reader is placed in every nook and cranny usually in the zone, and
Every two meters of placements, one reference label；And a certain number of labels to be positioned are generated at random and are scattered in target area.Reader
Reading range can cover whole region, wherein the position coordinates of reader be (Xi,Yi),i∈(1,M)；
As shown in Fig. 2, a kind of RFID label tag indoor tracking based on Unscented kalman filtering disclosed by the embodiments of the present invention
Method mainly includes the following steps:
(1) according to the motion state of target labels, the state model x of system is establishedk+1=f (xk)+WkWith observation model zk
=h (xk)+Vk；Wherein subscript k indicates moment, xkThe state vector of expression system, including target labels in the position of x-axis direction
And speed and target labels are in the position and speed in y-axis direction；zkThe observation vector of expression system, f indicate nonlinear state
Equation functions, h indicate non-linear observation equation functions, WkIndicate zero-mean, the process noise that covariance matrix is Q, VkIndicate zero
Mean value, the observation noise that covariance matrix is R；
The state vector of system are as follows:
xk=[pxk vx(k) pyk vy(k)]T
Wherein, pxkIt is target labels in the position of x-axis direction, vx(k)Speed for target labels in x-axis direction, pykFor mesh
Mark position of the label in y-axis direction, vy(k)Speed for target labels in y-axis direction.
The nonlinear state function of system is related with the motion state of system.For the target labels of uniform motion, system
State model are as follows:T is sampling time interval；
For the target labels at the uniform velocity turned, the state model of system are as follows:Wherein T is sampling time interval, and ω is turning rate；
The observation model of system are as follows:
Process noise WkUsually taking variance is 0.15, observation noise VkUsually taking variance is 1.
(2) RSSI for being evenly distributed on indoor reference label and reference label are passed through at a distance from reader non-linear
SVR is trained, and constructs the Nonlinear Mapping relationship of RSSI and distance；Specific steps include:
(2.1) reference is established according to the signal strength indication RSSI for being evenly distributed on indoor reference label that reader obtains
The RSSI matrix of label；The distance matrix of reference label is established according to the distance between reference label and reader；
(2.2) using the RSSI of reference label as the input value of sample, using the distance of reference label as the expectation of sample
Output valve, the RSSI of reference label are trained with apart from one-to-one correspondence by non-linear SVR；
(2.3) it according to the training result of non-linear SVR, establishes non-thread between input signal strength RSSI and output distance
Property mapping relations.
(3) RSSI of the target labels at current time is obtained, according to the Nonlinear Mapping relationship that step (2) construct, estimation
Distance between target labels and reader out, building calculate the Nonlinear System of Equations of target labels position, and by nonlinear equation
Group Solve problems are converted into the optimization problem of objective function, are solved by particle group optimizing to objective function, obtain current time
Target labels observation coordinate；Specific steps are as follows:
(3.1) signal strength indication of the label to be positioned obtained according to reader establishes the RSSI matrix of label to be positioned,
Using the RSSI matrix of label to be positioned as the input of decision function, according to the Nonlinear Mapping of RSSI and distance in step (2)
Relationship obtains the distance matrix of label and reader to be positioned；
(3.2) it according to the distance matrix of label to be positioned and the position coordinates of reader, constructs and calculates mark to be positioned
Sign the Nonlinear System of Equations of position；
Wherein, diIt is the distance between the target labels estimated and i-th of reader, (x, y) is target labels coordinate,
(Xi,Yi) be reader position coordinates, i ∈ (1, M)；M is the number of reader.
(3.3) Solving Nonlinear Systems of Equations problem is converted to the optimization problem of objective function, it is logical using PSO optimization method
Cross the optimal solution that iteration seeks objective function.Wherein, the objective function of particle group optimizing are as follows:
(3.4) fitness value of calculating and more all particles changes grain according to global optimum and individual optimal value
The position and speed of son draws close the position coordinates that the optimal solution obtained from is target labels to optimal solution.
(4) to filter before being carried out by observation track of the Unscented kalman filtering algorithm to the target labels before current time
Wave；Specific steps include:
(4.1) the system mode x at k momentkIt is converted using UT and obtains Sigma point Xi,k, and sampling policy is corrected using ratio
Obtain the weight of the corresponding mean value of Sigma point and variance.The weight of the corresponding mean value of Sigma point is denoted asThe weight of variance
It is denoted as
In formula, λ=α2(n+v)-n, n are the dimension of system mode vector, value 4；α is for point set is arranged to mean value
The distance of point, usually the number of a very little, value 0.01, ν are a scale parameters, value 0, and β is higher order term information
Parameter, value 2.
(4.2) the one-step prediction X of Sigma point is calculatedi,k+1/k=f (xi,k), according to the prediction to Sigma point, it is weighted
Summation obtains the one-step prediction of system state amountAnd according to the one-step prediction of system state amount
Value, calculates the covariance matrix of system state amountThe Sigma point of prediction is substituted into and is seen
Survey equation, the observed quantity Z predictedi,k+1/k=h (Xi,k+1/k)；According to the observation predicted value to Sigma point, weighted sum is obtained
Take system prediction valueAnd obtain the covariance of system:
(4.3) Kalman gain is calculated according to the covariance of system prediction value:Utilize lower a period of time
The observation vector at quarter is updated, and obtains estimated value last in recursive process The side and
DifferenceTarget position after obtaining filtering estimation.
(5) backward recursion: smooth theoretical smooth to the progress of filtered track by RTS, smoothed out structure is mesh
Mark the indoor tracking track of label.It is smoothly smooth using segmentation RTS backward, the whole process of tag motion is divided into more
Section, every section gradually reverse smooth.The specific steps of sectionally smooth include:
(5.1) (k=N-1 ..., 1) is initialized, wherein N is the number of sampled point in each section of section；For smoothing process
In state vector；For the variance in smoothing process；
(5.2) flat gain is calculatedWherein CkFor cross covariance matrix；
(5.3) smooth vector sum variance is updated；
Experimental situation is configured that in this experiment, and area to be targeted is the room area of 8m*8m, in this region every
Place a reader, that is, M=4 in a corner；4*4 reference label is uniformly placed in whole region.The iteration of particle group optimizing
Total degree is set as 100.As shown in figure 3, giving the RFID label tag indoor tracking side in this example based on Unscented kalman filtering
The motion model analogous diagram of method.The motion profile of moving target are as follows: 0~20s does linear uniform motion on the basis of initial value；
20~40s, target do movement of at the uniform velocity turning left after linear uniform motion；
40~60s, target do linear uniform motion after movement of at the uniform velocity turning left；
60~80s, target do movement of at the uniform velocity turning right after uniformly accelerated motion；
80~100s, target do linear uniform motion after movement of at the uniform velocity turning right.
As shown in figure 4, giving the imitative of the RFID label tag indoor tracking method in this example based on Unscented kalman filtering
True resultant error figure.As seen from Figure 4, under the conditions of same experiment simulation, the error of RFID label tag positioning in the present invention
Significantly lower than the position error of classical VIRE and EKF method.From the foregoing, it will be observed that label tracking in the embodiment of the present invention with
The indoor tracking algorithm of the prior art, which is compared, has higher positioning accuracy, when target state changes, the present invention
In tracking still there is good tracking result, strong robustness.
Based on the same technical idea, the embodiment of the invention also provides a kind of computer equipments, which can
With include memory, processor and storage on a memory and the computer program that can run on a processor, the computer
Program realizes the above-mentioned RFID label tag indoor tracking method based on Unscented kalman filtering when being loaded on processor.
The foregoing is merely better embodiment of the invention, protection scope of the present invention is not with above embodiment
Limit, as long as those of ordinary skill in the art's equivalent modification or variation made by disclosure according to the present invention, should all be included in power
In the protection scope recorded in sharp claim.
Claims (8)
1. a kind of RFID label tag indoor tracking method based on Unscented kalman filtering, it is characterised in that: this method includes as follows
Step:
(1) according to the motion state of target labels, the state model x of system is establishedk+1=f (xk)+WkWith observation model zk=h
(xk)+Vk；Wherein subscript k indicates moment, xkThe state vector of expression system, position and speed including target labels in x-axis direction
Degree and target labels y-axis direction position and speed；zkThe observation vector of expression system, f indicate nonlinear state equation
Function, h indicate non-linear observation equation functions, WkIndicate zero-mean, the process noise that covariance matrix is Q, VkIndicate that zero is equal
Value, the observation noise that covariance matrix is R；
(2) RSSI for being evenly distributed on indoor reference label and reference label are passed through into non-linear SVR at a distance from reader
It is trained, constructs the Nonlinear Mapping relationship of RSSI and distance；
(3) RSSI of the target labels at current time is obtained, according to the Nonlinear Mapping relationship that step (2) construct, estimates mesh
Distance between label and reader is marked, building calculates the Nonlinear System of Equations of target labels position, and Nonlinear System of Equations is asked
Solution problem is converted into the optimization problem of objective function, is solved by particle group optimizing to objective function, obtains the mesh at current time
Mark the observation coordinate of label；
(4) to filtering before being carried out by observation track of the Unscented kalman filtering algorithm to the target labels before current time；
(5) to smooth after carrying out to filtered track, smoothed out track is the indoor tracking track of target labels.
2. a kind of RFID label tag indoor tracking method based on Unscented kalman filtering according to claim 1, feature
It is: the state vector of system in the step (1) are as follows: xk=[pxk vx(k)pyk vy(k)]T；Wherein, pxkIt is target labels in x
The position of axis direction, vx(k)Speed for target labels in x-axis direction, pykPosition for target labels in y-axis direction, vy(k)For
Speed of the target labels in y-axis direction；
The nonlinear state function of system is related with the motion state of system；For the target labels of uniform motion, the shape of system
States model are as follows:T is sampling time interval；
For the target labels at the uniform velocity turned, the state model of system are as follows:Wherein T is sampling time interval, and ω is turning rate；
The observation model of system are as follows:
3. a kind of RFID label tag indoor tracking method based on Unscented kalman filtering according to claim 1, feature
It is: is specifically included in the step (2):
(2.1) reference label is established according to the signal strength indication RSSI for being evenly distributed on indoor reference label that reader obtains
RSSI matrix；The distance matrix of reference label is established according to the distance between reference label and reader；
(2.2) it using the RSSI of reference label as the input value of sample, is exported the distance of reference label as the expectation of sample
Value, the RSSI of reference label are trained with apart from one-to-one correspondence by non-linear SVR；
(2.3) according to the training result of non-linear SVR, that establishes between input signal strength RSSI and output distance non-linear reflects
Penetrate relationship.
4. a kind of RFID label tag indoor tracking method based on Unscented kalman filtering according to claim 1, feature
It is: the Nonlinear System of Equations in the step (3) are as follows:
Wherein, diIt is the distance between the target labels estimated and i-th of reader, (x, y) is target labels coordinate, (Xi,
Yi) be reader position coordinates, i ∈ (1, M)；M is the number of reader.
5. a kind of RFID label tag indoor tracking method based on Unscented kalman filtering according to claim 4, feature
It is: the objective function of the particle group optimizing in the step (3) are as follows:
6. a kind of RFID label tag indoor tracking method based on Unscented kalman filtering according to claim 1, feature
Be: the step of Unscented kalman filtering in the step (4) includes:
(4.1) the system mode x at k momentkIt is converted using UT and obtains Sigma point, and obtained using ratio amendment sampling policy
The corresponding mean value weight of Sigma pointAnd variance weight Wi c；
(4.2) the one-step prediction X of Sigma point is calculatedi,k+1/k=f (xi,k), and the estimated value of system state amount is calculatedAnd error co-variance matrix Wherein n is the dimension of system mode vector；
(4.3) the Sigma point of prediction is substituted into the observed quantity Z that observational equation calculates predictioni,k+1/k=h (Xi,k+1/k), and calculate
The predicted value measured to systematic perspectiveAnd covariance, and calculated according to the covariance of system prediction value
Kalman gainWherein:
(4.4) the observation vector z of subsequent time is utilizedk+1It is updated, obtains estimated value last in recursive processAnd varianceTarget after obtaining filtering estimation
Position.
7. a kind of RFID label tag indoor tracking method based on Unscented kalman filtering according to claim 1, feature
It is: it is backward smoothly smooth using segmentation RTS in the step (5), the whole process of tag motion is divided into multistage,
Every section gradually reverse smooth.
8. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the computer program realizes any one of -7 institute according to claim 1 when being loaded on processor
The RFID label tag indoor tracking method based on Unscented kalman filtering stated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811416628.4A CN109541533A (en) | 2018-11-26 | 2018-11-26 | A kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811416628.4A CN109541533A (en) | 2018-11-26 | 2018-11-26 | A kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109541533A true CN109541533A (en) | 2019-03-29 |
Family
ID=65850017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811416628.4A Pending CN109541533A (en) | 2018-11-26 | 2018-11-26 | A kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109541533A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110320494A (en) * | 2019-07-19 | 2019-10-11 | 仲恺农业工程学院 | Ox indoor locating system and heuristic jump based on the UWB communication technology filter localization method |
| CN110657799A (en) * | 2019-09-26 | 2020-01-07 | 广东省海洋工程装备技术研究所 | Space real-time positioning method, computer device and computer readable storage medium |
| CN110944293A (en) * | 2019-11-26 | 2020-03-31 | 西安烽火电子科技有限责任公司 | Radio search positioning method based on path attenuation and Kalman filtering fusion |
| CN111624549A (en) * | 2020-05-14 | 2020-09-04 | 哈尔滨工程大学 | Passive filtering tracking method under non-common-view condition |
| CN111954158A (en) * | 2020-07-01 | 2020-11-17 | 珠海高凌信息科技股份有限公司 | RSS map-based joint filtering indoor single-target tracking method, device and medium |
| CN113258965A (en) * | 2021-05-17 | 2021-08-13 | 东南大学 | Millimeter wave distributed MIMO system AOA tracking method based on unscented Kalman filtering |
| CN113421289A (en) * | 2021-05-17 | 2021-09-21 | 同济大学 | High-precision vehicle track data extraction method for overcoming unmanned aerial vehicle shooting disturbance |
| CN113468899A (en) * | 2021-06-30 | 2021-10-01 | 中国科学技术大学 | RFID-based target tracking method without carrying label |
| CN113709662A (en) * | 2021-08-05 | 2021-11-26 | 北京理工大学重庆创新中心 | Ultra-wideband-based autonomous three-dimensional inversion positioning method |
| CN113805141A (en) * | 2021-08-31 | 2021-12-17 | 西北工业大学 | Single-station passive positioning method based on signal intensity |
| CN114485651A (en) * | 2022-02-15 | 2022-05-13 | 上海海事大学 | FLS and UKF combined navigation method, device, storage medium and equipment |
| CN116108873A (en) * | 2022-12-12 | 2023-05-12 | 天津大学 | Motion posture assessment system based on RFID/IMU fusion |
| CN116108873B (en) * | 2022-12-12 | 2024-04-19 | 天津大学 | Motion posture assessment system based on RFID/IMU fusion |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060010086A1 (en) * | 2004-07-10 | 2006-01-12 | Klein Elliot S | Data append method for sent postal mail |
| CN101867943A (en) * | 2010-06-23 | 2010-10-20 | 哈尔滨工业大学 | WLAN indoor tracking method based on particle filtering algorithm |
| CN106382931A (en) * | 2016-08-19 | 2017-02-08 | 北京羲和科技有限公司 | An indoor positioning method and a device therefor |
| CN108489495A (en) * | 2018-03-29 | 2018-09-04 | 东南大学 | A kind of RFID tag indoor orientation method and equipment based on SVR and PSO |
-
2018
- 2018-11-26 CN CN201811416628.4A patent/CN109541533A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060010086A1 (en) * | 2004-07-10 | 2006-01-12 | Klein Elliot S | Data append method for sent postal mail |
| CN101867943A (en) * | 2010-06-23 | 2010-10-20 | 哈尔滨工业大学 | WLAN indoor tracking method based on particle filtering algorithm |
| CN106382931A (en) * | 2016-08-19 | 2017-02-08 | 北京羲和科技有限公司 | An indoor positioning method and a device therefor |
| CN108489495A (en) * | 2018-03-29 | 2018-09-04 | 东南大学 | A kind of RFID tag indoor orientation method and equipment based on SVR and PSO |
Non-Patent Citations (1)
| Title |
|---|
| 张庆波 等: "基于无迹卡尔曼滤波的粒子群算法研究", 《中国科学技术大学学报》 * |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110320494A (en) * | 2019-07-19 | 2019-10-11 | 仲恺农业工程学院 | Ox indoor locating system and heuristic jump based on the UWB communication technology filter localization method |
| CN110657799B (en) * | 2019-09-26 | 2022-09-09 | 广东省海洋工程装备技术研究所 | Space real-time positioning method, computer device and computer readable storage medium |
| CN110657799A (en) * | 2019-09-26 | 2020-01-07 | 广东省海洋工程装备技术研究所 | Space real-time positioning method, computer device and computer readable storage medium |
| CN110944293A (en) * | 2019-11-26 | 2020-03-31 | 西安烽火电子科技有限责任公司 | Radio search positioning method based on path attenuation and Kalman filtering fusion |
| CN111624549A (en) * | 2020-05-14 | 2020-09-04 | 哈尔滨工程大学 | Passive filtering tracking method under non-common-view condition |
| CN111954158A (en) * | 2020-07-01 | 2020-11-17 | 珠海高凌信息科技股份有限公司 | RSS map-based joint filtering indoor single-target tracking method, device and medium |
| CN113421289B (en) * | 2021-05-17 | 2022-09-20 | 同济大学 | High-precision vehicle track data extraction method for overcoming unmanned aerial vehicle shooting disturbance |
| CN113421289A (en) * | 2021-05-17 | 2021-09-21 | 同济大学 | High-precision vehicle track data extraction method for overcoming unmanned aerial vehicle shooting disturbance |
| CN113258965B (en) * | 2021-05-17 | 2022-06-03 | 东南大学 | Millimeter wave distributed MIMO system AOA tracking method based on unscented Kalman filtering |
| CN113258965A (en) * | 2021-05-17 | 2021-08-13 | 东南大学 | Millimeter wave distributed MIMO system AOA tracking method based on unscented Kalman filtering |
| CN113468899A (en) * | 2021-06-30 | 2021-10-01 | 中国科学技术大学 | RFID-based target tracking method without carrying label |
| CN113709662A (en) * | 2021-08-05 | 2021-11-26 | 北京理工大学重庆创新中心 | Ultra-wideband-based autonomous three-dimensional inversion positioning method |
| CN113709662B (en) * | 2021-08-05 | 2023-12-01 | 北京理工大学重庆创新中心 | Autonomous three-dimensional inversion positioning method based on ultra-wideband |
| CN113805141A (en) * | 2021-08-31 | 2021-12-17 | 西北工业大学 | Single-station passive positioning method based on signal intensity |
| CN113805141B (en) * | 2021-08-31 | 2023-06-30 | 西北工业大学 | Single-station passive positioning method based on signal intensity |
| CN114485651B (en) * | 2022-02-15 | 2023-09-19 | 上海海事大学 | FLS and UKF combined navigation method, device, storage medium and equipment |
| CN114485651A (en) * | 2022-02-15 | 2022-05-13 | 上海海事大学 | FLS and UKF combined navigation method, device, storage medium and equipment |
| CN116108873A (en) * | 2022-12-12 | 2023-05-12 | 天津大学 | Motion posture assessment system based on RFID/IMU fusion |
| CN116108873B (en) * | 2022-12-12 | 2024-04-19 | 天津大学 | Motion posture assessment system based on RFID/IMU fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109541533A (en) | A kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering | |
| CN108489495A (en) | A kind of RFID tag indoor orientation method and equipment based on SVR and PSO | |
| CN101778399B (en) | Method for optimizing WLAN (Wireless Local Area Network) indoor ANN (Artificial Neural Network) positioning based on FCM (fuzzy C-mean) and least-squares curve surface fitting methods | |
| Ma et al. | Fusion of RSS and phase shift using the Kalman filter for RFID tracking | |
| CN112230243B (en) | Indoor map construction method for mobile robot | |
| CN106597363A (en) | Pedestrian location method in indoor WLAN environment | |
| CN103529424B (en) | RFID (radio frequency identification) and UKF (unscented Kalman filter) based method for rapidly tracking indoor target | |
| CN108716918A (en) | A kind of RSSI indoor positioning algorithms based on Grid Clustering | |
| CN105718971B (en) | A kind of multiple target passive type indoor activity recognition methods based on RFID | |
| CN111667216A (en) | Unmanned aerial vehicle indoor storage autonomous checking system and method | |
| CN106932752A (en) | A kind of real-time indoor orientation method based on RF phse monitoring | |
| CN111537952B (en) | RFID indoor three-dimensional positioning method based on deep learning | |
| Xu et al. | The principle, methods and recent progress in RFID positioning techniques: A review | |
| Seco et al. | RFID-based centralized cooperative localization in indoor environments | |
| Tsang et al. | A bluetooth-based indoor positioning system: a simple and rapid approach | |
| CN101977436A (en) | WLAN indoor positioning-based mobile subscriber position coordinate correction method | |
| CN110132273B (en) | Mobile robot navigation method based on RFID servo technology | |
| Wei et al. | RSSI-based location fingerprint method for RFID indoor positioning: a review | |
| CN110554353B (en) | Mobile robot absolute positioning method based on RFID system | |
| Wang et al. | RFID assisted object tracking for automating manufacturing assembly lines | |
| CN201174774Y (en) | Indoor positioning system based on 433 MHz wireless transmission network | |
| CN109766969B (en) | RFID indoor positioning algorithm based on asynchronous dominant motion evaluation | |
| CN108462939A (en) | A kind of indoor orientation method of earth magnetism Time-Series analysis | |
| Azenha et al. | A neural network approach for radio frequency based indoors localization | |
| Cherntanomwong et al. | Soft-clustering Technique for Fingerprint-based Localization. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190329 |