CN109996205A - Data Fusion of Sensor method, apparatus, electronic equipment and storage medium - Google Patents
Data Fusion of Sensor method, apparatus, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN109996205A CN109996205A CN201910292114.0A CN201910292114A CN109996205A CN 109996205 A CN109996205 A CN 109996205A CN 201910292114 A CN201910292114 A CN 201910292114A CN 109996205 A CN109996205 A CN 109996205A
- Authority
- CN
- China
- Prior art keywords
- posterior probability
- sensor
- target device
- approximate
- approximate posterior
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000004927 fusion Effects 0.000 title claims abstract description 88
- 238000000034 method Methods 0.000 title claims abstract description 76
- 230000008569 process Effects 0.000 claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 20
- 230000006870 function Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 5
- 230000001360 synchronised effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 12
- 238000012545 processing Methods 0.000 description 12
- 230000005540 biological transmission Effects 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 238000005315 distribution function Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 235000015170 shellfish Nutrition 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- 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
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The embodiment of the present application provides a kind of Data Fusion of Sensor method, apparatus, electronic equipment and storage medium, belongs to information fusion technology field.The described method includes: obtaining the wireless signal that target device is sent, the signal strength of the wireless signal is determined；Approximate posterior probability is obtained after carrying out calculation process to the signal strength based on Predetermined filter；The approximate posterior probability is sent to fusion center, so that the fusion center determines based on the approximate posterior probability position of the target device.The method carries out approximate posterior probability using Predetermined filter by sensor and calculates, then calculated result is summarized to fusion center and merges the position for determining target device, reduces integral operation complexity, improves total system reliability and robustness.
Description
Technical field
This application involves information to merge field, in particular to a kind of Data Fusion of Sensor method, apparatus, electronics
Equipment and storage medium.
Background technique
The definition of Data Fusion of Sensor may be summarized to be the multiple similar or inhomogeneity sensing for being distributed in different location
Local data's resource provided by device is integrated, and is analyzed it using computer technology, eliminate multi-sensor information it
Between redundancy and contradiction that may be present, be subject to complementation, reduce its not certainty, obtain measurand consistency explain and retouch
It states, to improve the rapidity and correctness of the system decision-making, planning, reaction, system is made to obtain more fully information.
It, can when therefore generalling use Data Fusion of Sensor and carry out location estimation, such as being positioned in navigation system
To obtain the acquisition of monocular cam, binocular camera, depth camera, ultrasonic sensor, infrared sensor etc. equipment
Data relevant to position realize positioning then by carrying out data fusion to the collected data of above equipment.
But in extensive sensing network, the data obtained in the prior art to sensor carry out centralized processing estimation mesh
Cursor position, big, the higher problem of computational complexity that there are operands.
Summary of the invention
In view of this, the embodiment of the present application be designed to provide a kind of Data Fusion of Sensor method, apparatus, electronics is set
Standby and storage medium has the data obtained in technology to sensor to carry out centralized processing estimation target position, there is fortune to improve
Calculation amount is big, the higher problem of computational complexity.
The embodiment of the present application provides a kind of Data Fusion of Sensor method, which comprises obtains target device hair
The wireless signal sent determines the signal strength of the wireless signal；The signal strength is transported based on Predetermined filter
Approximate posterior probability is obtained after calculation processing；The approximate posterior probability is sent to fusion center, for the fusion center base
The position of the target device is determined in the approximate posterior probability.
During above-mentioned realization, in the letter for the wireless signal that sensor side sends target device based on Predetermined filter
Number intensity obtains approximate posterior probability after carrying out calculation process, then by approximate posterior probability be sent to fusion center carry out it is subsequent
Target device positioning, thus avoid in massive wireless sensor by fusion center to all the sensors transmission Lai
Signal strength carries out Predetermined filter processing, enhances the reliability and robustness of entire positioning system.
Further, it is determined that the signal strength of the wireless signal, comprising: determine wireless communication based on nonlinear state model
Number signal strength；The nonlinear state model includes:Wherein, xk=f (xk-1)+vk-1It retouches
State state vector xkVariation, xk=[xk,yk,θk]T, xk,ykCoordinate value for the target device at the k moment, θkFor for retouching
The parameter of state change is stated, k is discrete time, vk-1And wkFor Gaussian noise；zk=h (xk)+wkSensor measurement signal is described
Intensity zk=[z1 k,…,zM k]TMensuration mode, zm kIt indicates to number the measuring signal intensity for the sensor for being m, 1≤m at the k moment
≤M。
During above-mentioned realization, the signal strength of wireless signal is determined using nonlinear state model by sensor,
Accuracy is higher compared with Linear state model, is more suitable for the calculating of approximate posterior probability.
Further, approximate posterior probability is obtained after carrying out calculation process to the signal strength based on Predetermined filter,
It include: to set lossless Kalman filter for the Predetermined filter, it is quasi- using the maximum a posteriori probability under Bayesian frame
Then, the signal strength is filtered based on the lossless Kalman filter, to obtain approximate posterior probability；It is described
Maximum posteriori criterion includes:Wherein,To make posterior probability function
The maximum parameter value of value, z1:k=z1 1:k,…,zm 1:k。
During above-mentioned realization, position becomes a part of state in nonlinear state model, and is based on lossless card
Kalman Filtering can carry out the estimation that state is approximate posterior probability to nonlinear state model, therefore be filtered using lossless Kalman
Wave energy is enough more quasi-ly to estimate the position of target device.
Further, the approximate posterior probability is sent to fusion center, comprising: will be described based on default sending cycle
Approximate posterior probability, which synchronizes, is sent to fusion center.
During above-mentioned realization, the approximate posterior probability of acquisition is periodically synchronized and is sent in fusion by sensor
The heart, to avoid fusion center from carrying out invalid computation when not receiving enough data volumes, to improve resource utilization.
The embodiment of the present application provides a kind of Data Fusion of Sensor method, which comprises receives multiple sensors
The multiple approximate posterior probability corresponding with target device sent, the multiple approximation posterior probability is the multiple sensor pair
The signal strength of wireless signal obtains after carrying out Predetermined filter calculation process；By the multiple approximate posterior probability in Bayes
Soft merging is carried out under frame, determines the position of the target device.
During above-mentioned realization, Bayes is carried out by multiple approximate posterior probability of the fusion center to multiple sensors
Soft merging under frame, thus avoid in massive wireless sensor by fusion center to all the sensors transmission Lai
Signal strength carries out Predetermined filter processing, enhances the reliability and robustness of entire positioning system；Soft merging is than passing simultaneously
Hard merging mode of uniting is more applicable for information judgement, and positioning accuracy is higher.
Further, the multiple approximate posterior probability is subjected under Bayesian frame soft merging, determines the target
The position of equipment, comprising: soft merging is carried out to the multiple approximate posterior probability based on soft merging formula, to obtain merging posteriority
Probability, the merging posterior probability are Gaussian Profile, and the mean value vector for merging posterior probability is to meet under Bayesian frame
The result of maximum posteriori criterion；Determine position of the front two element of the mean value vector as the target device；Institute
Stating mean value vector isWhereinThe sensor that expression number is m is calculated close
Like the covariance of posterior probability；The soft merging formula includes:Its
In, m is sensor number, and A is normaliztion constant, and M is number of sensors, and 1≤m≤M, q are that the approximation of posterior probability function is asked
Solution.
During above-mentioned realization, the numerical procedure of soft merging, can attenuating portion significantly by introducing the inverse operation of covariance
Unreliable calculating (unreliable to mean that covariance matrix is larger) the bring negative effect for dividing local sensor to upload, has more
Good setting accuracy.
The embodiment of the present application provides a kind of Data Fusion of Sensor device, and described device includes: that signal strength determines mould
Block sends out the wireless signal transmitted for obtaining target device, determines the signal strength of the wireless signal；Approximate posterior probability meter
Module is calculated, for obtaining approximate posterior probability after carrying out calculation process to the signal strength based on lossless Predetermined filter；Hair
Module is sent, for the approximate posterior probability to be sent to fusion center, so that the fusion center is based on the approximate posteriority
The position of target device described in determine the probability.
Further, the signal strength determining module is specifically used for: determining wireless signal based on nonlinear state model
Signal strength, the nonlinear state model includes:Wherein, xk=f (xk-1)+vk-1Description
State vector xkVariation, xk=[xk,yk,θk]T, xk,ykCoordinate value for the target device at the k moment, θkFor for describing
The parameter of state change, k are discrete time, vk-1And wkFor Gaussian noise；zk=h (xk)+wkIt is strong that sensor measurement signal is described
Spend zk=[z1 k,…,zM k]TMensuration mode, zm kIt indicates to number the measuring signal intensity for the sensor for being m at the k moment, 1≤m≤
M。
Further, the approximate posterior probability computing module is specifically used for: setting lossless for the Predetermined filter
Kalman filter, using the maximum posteriori criterion under Bayesian frame, based on the lossless Kalman filter to institute
It states signal strength to be filtered, to obtain approximate posterior probability；The maximum posteriori criterion includes:Wherein,To make the maximum parameter value of posterior probability function value, z1:k
=z1 1:k,…,zm 1:k。
Further, the sending module is specifically used for: based on default sending cycle that the approximate posterior probability is synchronous
It is sent to fusion center.
The embodiment of the present application provides a kind of Data Fusion of Sensor device, and described device includes: receiving module, for connecing
Multiple approximate posterior probability corresponding with target device that multiple sensors transmit are received, the multiple approximation posterior probability is described
Multiple sensors obtain after carrying out Predetermined filter calculation process to the signal strength of wireless signal；Merging module is used for institute
It states approximate posterior probability and carries out soft merging under Bayesian frame, determine the position of the target device.
Further, the merging module is specifically used for: based on soft merging formula to the multiple approximate posterior probability into
Row soft merging, to obtain merging posterior probability, the merging posterior probability is Gaussian Profile, the mean value for merging posterior probability
Vector is the result for meeting maximum posteriori criterion under Bayesian frame；Determine the front two element conduct of the mean value vector
The position of the target device；The mean value vector isWhereinIndicate that number is
The covariance for the approximate posterior probability that the sensor of m is calculated；The soft merging formula includes:Wherein, m is sensor number, and A is normaliztion constant, and M is sensing
Device quantity, 1≤m≤M, q are the approximate solution of posterior probability function.
The embodiment of the present application also provides a kind of electronic equipment, the electronic equipment includes processor and memory, described
Computer program instructions are stored in memory, the processor reads and runs the computer program in the memory
When instruction, the step in any of the above-described the method is executed.
The embodiment of the present application also provides a kind of read/write memory medium, calculating is stored in the read/write memory medium
Machine program instruction when the computer program instructions are read and run by a processor, executes in any of the above-described the method
The step of.
Detailed description of the invention
Technical solution in ord to more clearly illustrate embodiments of the present application will make below to required in the embodiment of the present application
Attached drawing is briefly described, it should be understood that the following drawings illustrates only some embodiments of the application, therefore should not be seen
Work is the restriction to range, for those of ordinary skill in the art, without creative efforts, can be with
Other relevant attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of Data Fusion of Sensor method provided by the embodiments of the present application；
Fig. 2 is the flow diagram of another Data Fusion of Sensor method provided by the embodiments of the present application；
Fig. 3 is a kind of structural block diagram of Data Fusion of Sensor device provided by the embodiments of the present application；
Fig. 4 is a kind of structure for the electronic equipment that can be applied to Data Fusion of Sensor method provided by the embodiments of the present application
Block diagram.
Icon: 30- Data Fusion of Sensor dress；31- signal strength determining module；32- approximation posterior probability computing module；
33- merging module；40- electronic equipment；41- memory；42- storage control；43- processor.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application is described.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.Meanwhile the application's
In description, term " first ", " second " etc. are only used for distinguishing description, are not understood to indicate or imply relative importance.
First embodiment
Through the applicant the study found that Data Fusion of Sensor because can combination sensor is original or processed data, mention
For more acurrate more robust estimation, therefore in many instances with application.Wherein, the target position estimation in wireless sensor network
It is widely used sensing data fusion.The calculating common scheme of location estimation is that the sensing node in sensor network is surveyed
The wireless signal that mobile target issues is measured, and specifically has base by the radio wave characteristic of the signal come estimated position information
In the RSSI method of wireless signal strength, there is the AOA (Chinese name: angle of arrival ranging, English based on radio wave angle of arrival
Literary full name: Angle-of-Arrival) method, and the TDOA (Chinese name: reaching time-difference side based on reaching time-difference
The methods of method, full name in English: Time Difference of Arrival).In these methods, the location estimation side based on RSSI
Method complexity is minimum, and does not require additional hardware, facilitates realization, but conventional RSSI method accuracy of measurement is relatively low,
And the wireless signal strength of the received target of sensor is carried out three-point fix by usually fusion center, there are computational complexity compared with
Problem high, locating accuracy is low.
To solve the above-mentioned problems, the embodiment of the present application provides a kind of Data Fusion of Sensor method, it should be understood that
Be, the executing subject of the Data Fusion of Sensor method can be computer, Cloud Server, intelligent terminal or other be able to carry out
The electronic equipment of calculation process.
Referring to FIG. 1, Fig. 1 is a kind of flow diagram of Data Fusion of Sensor method provided by the embodiments of the present application.
The specific steps of the Data Fusion of Sensor method can be such that
Step S12: sensor obtains the wireless signal that target device is sent, and determines that the signal of the wireless signal is strong
Degree.
Target device in the present embodiment can be smart phone, ZigBee equipment, radio-frequency apparatus or other can emit
The electronic equipment of wireless signal, sensor are the calculating that can be received wireless signal and carry out its signal strength.
Optionally, the expression of signal strength can use received signal strength (full name in English: Received Signal
Strength Indication, english abbreviation: RSSI), RSSI is commonly used to determine link quality, and whether increases broadcast
Send intensity.
Step S14: the sensor is based on obtaining approximation after Predetermined filter carries out calculation process to the signal strength
The approximate posterior probability is sent to fusion center by posterior probability.
Optionally, Predetermined filter can be lossless Kalman filter (full name in English: Unscented Kalman
Filter, english abbreviation: UKF), particle filter (full name in English: Particle Filter), extended Kalman filter (English
Literary full name: Extended Kalman Filter, english abbreviation: EKF) or other posterior probability that can solve unknown state
Bayesian frame under nonlinear filter.
Posterior probability is one of basic conception of information theory.In a communications system, after receiving some message,
The probability that the message that receiving end is recognized is sent is known as posterior probability.The calculating of posterior probability will be using prior probability as base
Plinth, posterior probability can be calculated according to by Bayesian formula with prior probability and likelihood function.It is sensed in the present embodiment
Device individually calculate acquisition posterior probability be not true posterior probability analytic value, only approximate solution value is acceptable in error
In the range of be used to estimated location information.
Step S16: fusion center receives multiple approximate posteriority corresponding with target device that the multiple sensor is sent
The multiple approximate posterior probability is carried out under Bayesian frame soft merging, determines the position of the target device by probability.
Optionally, fusion center is to communicate to connect with each sensor in wireless sensor network, which can
To be computer, Cloud Server, intelligent terminal or other electronic equipments with operational capability.
Bayesian frame can be the calculating constraint environment for meeting Bayesian Estimation.Wherein, Bayesian Estimation is to utilize shellfish
This theorem of leaf combines new evidence and pervious prior probability, to obtain new probability.It provides a kind of calculating hypothesis probability
Method, based on the assumption that prior probability, it is given assume under observe the probability of different data and the data observed itself.
Soft merging in the present embodiment can be understood as the data fusion carried out under Bayesian frame, which needs
Meet maximum posteriori criterion.
In the above-described embodiments, the signal for wireless signal target device sent based on Predetermined filter in sensor side
Intensity obtains approximate posterior probability after carrying out calculation process, and it is subsequent that approximate posterior probability is then sent to fusion center progress
Target device positioning, thus avoid in massive wireless sensor by fusion center to all the sensors transmission Lai letter
Number intensity carries out Predetermined filter processing, enhances the reliability and robustness of entire positioning system；Soft merging is than tradition simultaneously
Hard merging mode is more applicable for information judgement, and positioning accuracy is higher.
Referring to FIG. 2, the process that Fig. 2 is another Data Fusion of Sensor method provided by the embodiments of the present application is illustrated
Figure.The specific steps of the Data Fusion of Sensor method can be such that
Step S22: sensor obtains the wireless signal that target device is sent, based on described in the determination of nonlinear state model
The RSSI of wireless signal.
The nonlinear state model includesWherein, xk=f (xk-1)+vk-1Description state
Vector xkVariation, xk=[xk,yk,θk]T, xk,ykCoordinate value for the target device at the k moment, θkFor for describing state
The parameter of variation, k are discrete time, vk-1And wkFor Gaussian noise；zk=h (xk)+wkSensor measurement RSSI, that is, z is describedk=
[z1 k,…,zM k]TMensuration mode, zm kIt indicates to number measurement RSSI, 1≤m≤M for the sensor for being m at the k moment.
Optionally, in above-mentioned nonlinear state modelh(xk)=-
23.28·log10[d(xk,s)]-2.4+wk, wherein ω=0.5rad/s, T=0.05s, R=3m andy0=10m, d (xk,
S)]=[d1,d2,...,dM]T,
In the above-described embodiments, the RSSI value for determining wireless signal using nonlinear state model by sensor, with line
Character states model is higher compared to accuracy, is more suitable for the calculating of approximate posterior probability.
Step S24: sensor uses the maximum posteriori criterion under Bayesian frame, is based on lossless Kalman filter
The signal strength is filtered, to obtain approximate posterior probability, and the approximate posterior probability is sent to fusion
Center.
The maximum posteriori criterion includes:Wherein,To make
The maximum parameter value of posterior probability function value, z1:k=z1 1:k,…,zm 1:k。
Optionally, the detailed process that lossless Kalman filter is filtered the signal strength can with reference to
Lower code:
Wherein, λ=α2(L+ κ)-L, α=1e-3, L xkDimension,It is to matrix (L+ λ) PkAsk equal
I-th row of root,WithFor the standing parameter in UKF.
In the present embodiment by above-mentioned UKF obtain the result is that the sensor that number is m calculates resulting mean value vector
And covariance matrix, it can be expressed asWithBecause of state vectorGaussian distributed, therefore mean value and covariance can be used
It determines probability-distribution function, thus only transmitting mean value and covariance and can not have to send entire posterior probability to fusion center
Function.
Further, the sensor in same wireless sensor network can be same to fusion center based on same predetermined period
Step sends approximate posterior probability, so that fusion center is avoided to carry out invalid computation when not receiving enough data volumes, thus
It improves resource utilization.
In the above-described embodiments, position becomes a part of state in nonlinear state model, and is based on lossless karr
Graceful filtering can carry out state to nonlinear state model and be the estimation of approximate posterior probability, therefore use lossless Kalman filtering
The position of target device can be estimated more quasi-ly.
Step S26: fusion center is based on soft merging formula and carries out soft merging to the multiple approximate posterior probability, to obtain
Merge posterior probability, the merging posterior probability is Gaussian Profile, and the mean value vector for merging posterior probability is to meet pattra leaves
Maximum posteriori criterion as a result, determining the front two element of the mean value vector as the target device under this frame
Position.
Fusion center is based on soft merging formula to the multiple approximation posterior probability q (xk|zm 1:k) carry out soft merging, soft conjunction
And the merging posterior probability obtained is Gaussian Profile and mean value vector isCovariance square
Battle array beThe mean value vectorAs meet maximum posteriori criterion under Bayesian frame as a result,
q(xk|zm 1:k) in m value do not indicate in wireless sensor network that number is the approximate posteriority that different sensors are calculated simultaneously
Probability, the soft merging formula include:Wherein, m is sensor volume
Number, A is normaliztion constant, and M is number of sensors, and 1≤m≤M, q are the approximate solution of posterior probability function.
It is Gaussian system due to merging posterior probability, and since gaussian probability distribution function is maximum in its average value
Value, therefore the value for meeting maximum a posteriori probability is its mean value vector
In the above-described embodiments, Bayes's frame is carried out by multiple approximate posterior probability of the fusion center to multiple sensors
Soft merging under frame, thus avoid in massive wireless sensor by fusion center to all the sensors transmission Lai letter
Number intensity carries out Predetermined filter processing, enhances the reliability and robustness of entire positioning system；Soft merging is than tradition simultaneously
Hard merging mode is more applicable for information judgement, and the numerical procedure of soft merging can be subtracted significantly by the inverse operation of introducing covariance
Unreliable calculating (unreliable to mean that covariance matrix is larger) the bring negative effect that lower part local sensor uploads, tool
There is better setting accuracy.
Second embodiment
In order to cooperate the Data Fusion of Sensor method of the embodiment of the present application, the application second embodiment additionally provides one kind
Data Fusion of Sensor device 20.
Referring to FIG. 3, Fig. 3 is a kind of structural block diagram of Data Fusion of Sensor device provided by the embodiments of the present application.
Data Fusion of Sensor device 30 includes signal strength determining module 31, approximate posterior probability computing module 32, closes
And module 33.
Signal strength determining module 31 obtains the wireless signal that target device is sent for controlling sensor, determines institute
State the signal strength of wireless signal；
Approximate posterior probability computing module 32 is based on Predetermined filter to signal strength progress for controlling sensor
Approximate posterior probability is obtained after calculation process, and the approximate posterior probability is sent to fusion center；
Merging module 33 receives the corresponding with target device more of the multiple sensor transmission for controlling fusion center
The multiple approximate posterior probability is carried out under Bayesian frame soft merging, determines that the target is set by a approximation posterior probability
Standby position.
Further, the signal strength determining module 31 is specifically used for: determining wireless communication based on nonlinear state model
Number signal strength, the nonlinear state model includes:Wherein, xk=f (xk-1)+vk-1It retouches
State state vector xkVariation, xk=[xk,yk,θk]T, xk,ykCoordinate value for the target device at the k moment, θkFor for retouching
The parameter of state change is stated, k is discrete time, vk-1And wkFor Gaussian noise；zk=h (xk)+wkSensor measurement signal is described
Intensity zk=[z1 k,…,zM k]TMensuration mode, zm kIt indicates to number the measuring signal intensity for the sensor for being m, 1≤m at the k moment
≤M。
The approximation posterior probability computing module 32 is specifically used for: setting lossless Kalman for the Predetermined filter and filters
Wave device is strong to the signal based on the lossless Kalman filter using the maximum posteriori criterion under Bayesian frame
Degree is filtered, to obtain the approximate posterior probability of state variable；It is based on default sending cycle that the approximate posteriority is general
Rate, which synchronizes, is sent to fusion center；The maximum posteriori criterion includes:Its
In,To make the maximum parameter value of posterior probability function value, z1:k=z1 1:k,…,zm 1:k。
The merging module 33 is specifically used for: it is general to receive the approximate posteriority corresponding with target device that multiple sensors transmit
Rate, based on soft merging formula to the multiple approximation posterior probability q (xk|zm 1:k) soft merging is carried out, after the merging that soft merging obtains
Test that probability is Gaussian Profile and mean value vector isCovariance matrix isThe mean value vectorAs meet maximum posteriori criterion under Bayesian frame as a result, determining
The mean value vectorPosition of the front two element as the target device；The soft merging formula includes:Wherein, m is sensor number, and A is normaliztion constant, and M is sensing
Device quantity, 1≤m≤M, q are the approximate solution of posterior probability function.
3rd embodiment
Referring to FIG. 4, Fig. 4 is a kind of electronics that can be applied to Data Fusion of Sensor method provided by the embodiments of the present application
The structural block diagram of equipment.
Electronic equipment 40 provided in this embodiment may include Data Fusion of Sensor device 30, memory 41, storage control
Device 42 processed, processor 43.
The memory 41, storage control 42, each element of processor 43 are directly or indirectly electrically connected between each other,
To realize the transmission or interaction of data.For example, these elements can pass through one or more communication bus or signal wire between each other
It realizes and is electrically connected.The Data Fusion of Sensor device 30 includes at least one can be with the shape of software or firmware (firmware)
Formula is stored in the memory 41 or is solidificated in soft in the operating system (operating system, OS) of electronic equipment 40
Part functional module.The processor 43 is for executing the executable module stored in memory 41, such as Data Fusion of Sensor
The software function module or computer program that device 30 includes.
Wherein, memory 41 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only
Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM),
Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc..
Wherein, memory 41 is for storing program, and the processor 43 executes described program after receiving and executing instruction, and aforementioned
Method performed by the server that the stream process that inventive embodiments any embodiment discloses defines can be applied in processor 43,
Or it is realized by processor 43.
Processor 43 can be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 43 can be with
It is general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit
(Network Processor, abbreviation NP) etc.；Can also be digital signal processor (DSP), specific integrated circuit (ASIC),
Ready-made programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hard
Part component.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor
It can be microprocessor or the processor 43 be also possible to any conventional processor etc..
In conclusion the embodiment of the present application provides a kind of Data Fusion of Sensor method, apparatus, electronic equipment and storage
Medium, the Data Fusion of Sensor method include: the wireless signal for obtaining target device and sending, and determine the wireless signal
Signal strength；Approximate posterior probability is obtained after carrying out calculation process to the signal strength based on Predetermined filter；It will be described
Approximate posterior probability is sent to fusion center, so that the fusion center determines that the target is set based on the approximate posterior probability
Standby position.
During above-mentioned realization, in the letter for the wireless signal that sensor side sends target device based on Predetermined filter
Number intensity obtains approximate posterior probability after carrying out calculation process, then by approximate posterior probability be sent to fusion center carry out it is subsequent
Target device positioning, thus avoid in massive wireless sensor by fusion center to all the sensors transmission Lai
Signal strength carries out Predetermined filter processing, enhances the reliability and robustness of entire positioning system.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing
Show the device of multiple embodiments according to the application, the architectural framework in the cards of method and computer program product,
Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code
Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held
Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart
The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement
It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the application can integrate one independent portion of formation together
Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of the steps.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
The above description is only an example of the present application, the protection scope being not intended to limit this application, for ability
For the technical staff in domain, various changes and changes are possible in this application.Within the spirit and principles of this application, made
Any modification, equivalent substitution, improvement and etc. should be included within the scope of protection of this application.It should also be noted that similar label and
Letter indicates similar terms in following attached drawing, therefore, once it is defined in a certain Xiang Yi attached drawing, then in subsequent attached drawing
In do not need that it is further defined and explained.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain
Lid is within the scope of protection of this application.
It should be noted that, in this document, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also including other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Claims (10)
1. a kind of Data Fusion of Sensor method, which is characterized in that the described method includes:
The wireless signal that target device is sent is obtained, determines the signal strength of the wireless signal；
Approximate posterior probability is obtained after carrying out calculation process to the signal strength based on Predetermined filter；
The approximate posterior probability is sent to fusion center, so that the fusion center is determined based on the approximate posterior probability
The position of the target device.
2. Data Fusion of Sensor method according to claim 1, which is characterized in that determine the signal of the wireless signal
Intensity, comprising:
The signal strength of wireless signal is determined based on nonlinear state model；
The nonlinear state model includes:
Wherein, xk=f (xk-1)+vk-1State vector x is describedkVariation, xk=[xk,yk,θk]T, xk,ykFor the target device
In the coordinate value at k moment, θkFor the parameter for describing state change, k is discrete time, vk-1And wkFor Gaussian noise；zk=h
(xk)+wkSensor measurement signal intensity z is describedk=[z1 k,…,zM k]TMensuration mode, zm kIt is m's that expression is numbered at the k moment
The measuring signal intensity of sensor, 1≤m≤M.
3. Data Fusion of Sensor method according to claim 2, which is characterized in that based on Predetermined filter to the letter
Number intensity obtains approximate posterior probability after carrying out calculation process, comprising:
Lossless Kalman filter is set by the Predetermined filter, it is quasi- using the maximum a posteriori probability under Bayesian frame
Then, the signal strength is filtered based on the lossless Kalman filter, to obtain approximate posterior probability；
The maximum posteriori criterion includes:Wherein,To make posteriority
The maximum parameter value of probability function value, z1:k=z1 1:k,…,zm 1:k。
4. Data Fusion of Sensor method described in any claim in -3 according to claim 1, which is characterized in that by the approximation
Posterior probability is sent to fusion center, comprising:
The approximate posterior probability is synchronized based on default sending cycle and is sent to fusion center.
5. a kind of Data Fusion of Sensor method, which is characterized in that the described method includes:
Receive multiple approximate posterior probability corresponding with target device that multiple sensors are sent, the multiple approximation posterior probability
It is to be obtained after the multiple sensor carries out Predetermined filter calculation process to the signal strength of wireless signal；
The multiple approximate posterior probability is subjected to soft merging under Bayesian frame, determines the position of the target device.
6. Data Fusion of Sensor method according to claim 5, which is characterized in that by the multiple approximate posterior probability
Soft merging is carried out under Bayesian frame, determines the position of the target device, comprising: based on soft merging formula to the multiple
Approximate posterior probability carries out soft merging, and to obtain merging posterior probability, the merging posterior probability is Gaussian Profile, the merging
The mean value vector of posterior probability is to meet the result of maximum posteriori criterion under Bayesian frame；
Determine position of the front two element of the mean value vector as the target device；
The mean value vector isWhereinThe sensor for indicating that number is m calculates
The covariance of the approximate posterior probability arrived；The soft merging formula includes:Wherein, m is sensor number, and A is normaliztion constant, and M is sensing
Device quantity, 1≤m≤M, q are the approximate solution of posterior probability function.
7. a kind of Data Fusion of Sensor device, which is characterized in that described device includes:
Signal strength determining module sends out the wireless signal transmitted for obtaining target device, determines the signal of the wireless signal
Intensity；
Approximate posterior probability computing module, for being obtained after carrying out calculation process to the signal strength based on lossless Predetermined filter
Obtain approximate posterior probability；
Sending module, for the approximate posterior probability to be sent to fusion center, so that the fusion center is based on described close
The position of the target device is determined like posterior probability.
8. a kind of Data Fusion of Sensor device, which is characterized in that described device includes:
Receiving module, the multiple approximate posterior probability corresponding with target device transmitted for receiving multiple sensors are described more
A approximation posterior probability is obtained after the multiple sensor carries out Predetermined filter calculation process to the signal strength of wireless signal
?；
Merging module determines the target device for the approximate posterior probability to be carried out soft merging under Bayesian frame
Position.
9. a kind of electronic equipment, which is characterized in that the electronic equipment includes memory and processor, is stored in the memory
There is program instruction, when the processor reads and runs described program instruction, perform claim is required in any one of 1-6 the method
The step of.
10. a kind of read/write memory medium, which is characterized in that be stored with computer program in the read/write memory medium and refer to
It enables, when the computer program instructions are read and run by a processor, perform claim is required in any one of 1-6 the method
Step.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910292114.0A CN109996205B (en) | 2019-04-12 | 2019-04-12 | Sensor data fusion method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910292114.0A CN109996205B (en) | 2019-04-12 | 2019-04-12 | Sensor data fusion method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109996205A true CN109996205A (en) | 2019-07-09 |
| CN109996205B CN109996205B (en) | 2021-12-07 |
Family
ID=67133492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910292114.0A Expired - Fee Related CN109996205B (en) | 2019-04-12 | 2019-04-12 | Sensor data fusion method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109996205B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111132026A (en) * | 2019-11-25 | 2020-05-08 | 成都工业学院 | Target detection method, device, network system and readable storage medium |
| CN112313536A (en) * | 2019-11-26 | 2021-02-02 | 深圳市大疆创新科技有限公司 | Object state acquisition method, movable platform and storage medium |
| CN113114138A (en) * | 2021-04-22 | 2021-07-13 | 成都工业学院 | DPD parameter extraction method and device applied to 5G, electronic equipment and medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147468A (en) * | 2011-01-07 | 2011-08-10 | 西安电子科技大学 | Bayesian theory-based multi-sensor detecting and tracking combined processing method |
| CN103002480A (en) * | 2011-09-09 | 2013-03-27 | 上海贝尔股份有限公司 | Distributed type collaborative detecting method and distributed type collaborative detecting equipment for uplink baseband signals |
| CN103105611A (en) * | 2013-01-16 | 2013-05-15 | 广东工业大学 | Intelligent information fusion method of distributed multi-sensor |
| CN104185270A (en) * | 2013-05-28 | 2014-12-03 | 中国电信股份有限公司 | Indoor positioning method, system and positioning platform |
| CN105424030A (en) * | 2015-11-24 | 2016-03-23 | 东南大学 | Fusion navigation device and method based on wireless fingerprints and MEMS sensor |
| CN105717505A (en) * | 2016-02-17 | 2016-06-29 | 国家电网公司 | Data association method for utilizing sensing network to carry out multi-target tracking |
| CN106412826A (en) * | 2016-09-07 | 2017-02-15 | 清华大学 | Indoor positioning method and positioning device based on multi-source information fusion |
| WO2017052951A1 (en) * | 2015-09-25 | 2017-03-30 | Intel Corporation | Vision and radio fusion based precise indoor localization |
| CN108398704A (en) * | 2018-02-06 | 2018-08-14 | 北京科技大学 | A kind of more vehicle cooperative localization methods of Bayesian filter |
-
2019
- 2019-04-12 CN CN201910292114.0A patent/CN109996205B/en not_active Expired - Fee Related
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147468A (en) * | 2011-01-07 | 2011-08-10 | 西安电子科技大学 | Bayesian theory-based multi-sensor detecting and tracking combined processing method |
| CN103002480A (en) * | 2011-09-09 | 2013-03-27 | 上海贝尔股份有限公司 | Distributed type collaborative detecting method and distributed type collaborative detecting equipment for uplink baseband signals |
| CN103105611A (en) * | 2013-01-16 | 2013-05-15 | 广东工业大学 | Intelligent information fusion method of distributed multi-sensor |
| CN104185270A (en) * | 2013-05-28 | 2014-12-03 | 中国电信股份有限公司 | Indoor positioning method, system and positioning platform |
| WO2017052951A1 (en) * | 2015-09-25 | 2017-03-30 | Intel Corporation | Vision and radio fusion based precise indoor localization |
| CN105424030A (en) * | 2015-11-24 | 2016-03-23 | 东南大学 | Fusion navigation device and method based on wireless fingerprints and MEMS sensor |
| WO2017088196A1 (en) * | 2015-11-24 | 2017-06-01 | 东南大学 | Fusion navigation device and method based on wireless fingerprints and mems sensor |
| CN105717505A (en) * | 2016-02-17 | 2016-06-29 | 国家电网公司 | Data association method for utilizing sensing network to carry out multi-target tracking |
| CN106412826A (en) * | 2016-09-07 | 2017-02-15 | 清华大学 | Indoor positioning method and positioning device based on multi-source information fusion |
| CN108398704A (en) * | 2018-02-06 | 2018-08-14 | 北京科技大学 | A kind of more vehicle cooperative localization methods of Bayesian filter |
Non-Patent Citations (2)
| Title |
|---|
| ANINDYA S.PAUL: "RSSI-Based Indoor Localization and Tracking Using Sigma-Point Kalman Smoothers", 《IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING》 * |
| 高祺: "多传感器多目标跟踪的数据关联算法研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111132026A (en) * | 2019-11-25 | 2020-05-08 | 成都工业学院 | Target detection method, device, network system and readable storage medium |
| CN112313536A (en) * | 2019-11-26 | 2021-02-02 | 深圳市大疆创新科技有限公司 | Object state acquisition method, movable platform and storage medium |
| CN112313536B (en) * | 2019-11-26 | 2024-04-05 | 深圳市大疆创新科技有限公司 | Object state acquisition method, movable platform and storage medium |
| CN113114138A (en) * | 2021-04-22 | 2021-07-13 | 成都工业学院 | DPD parameter extraction method and device applied to 5G, electronic equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109996205B (en) | 2021-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6956746B2 (en) | Systems and methods for accurate radio frequency position estimation in the presence of multiple communication paths | |
| CN109996205A (en) | Data Fusion of Sensor method, apparatus, electronic equipment and storage medium | |
| EP2769233B1 (en) | Time of arrival based wireless positioning system | |
| US20160131750A1 (en) | Distance estimation method and device as well as node localization method and apparatus | |
| Geng et al. | Indoor tracking with RFID systems | |
| US9995564B2 (en) | Terminal and server for modifying magnetic field and method thereof | |
| WO2013086393A1 (en) | Positioning technique for wireless communication system | |
| CN110427104B (en) | System and method for calibrating motion trail of finger | |
| Wang et al. | Research on APIT and Monte Carlo method of localization algorithm for wireless sensor networks | |
| Martin et al. | Accuracy vs. resolution in radio tomography | |
| WO2023005789A1 (en) | Temperature treatment method and apparatus | |
| CN108200534B (en) | Method and equipment for positioning terminal | |
| Cao et al. | Localization with imprecise distance information in sensor networks | |
| CN108566677A (en) | A kind of fingerprint positioning method and device | |
| US20190302221A1 (en) | Fog-based internet of things (iot) platform for real time locating systems (rtls) | |
| Li et al. | A self-adaptive bluetooth indoor localization system using LSTM-based distance estimator | |
| CN108919182B (en) | Target positioning method based on support set and expectation maximization in WIFI environment | |
| CN105407496B (en) | A kind of method of erroneous measurements in identification wireless sensor network | |
| Elmenreich | Fusion of continuous-valued sensor measurements using confidence-weighted averaging | |
| Fahama et al. | An experimental comparison of RSSI-based indoor localization techniques using ZigBee technology | |
| US20200068344A1 (en) | Method and system for wireless localization data acquisition and calibration with image localization | |
| CN109889977B (en) | Bluetooth positioning method, device, equipment and system based on Gaussian regression | |
| CN111654843B (en) | Method and system for automatically updating fingerprint database, wifi positioning method and system | |
| Berkvens et al. | Asynchronous, electromagnetic sensor fusion in RatSLAM | |
| CN110035405A (en) | A kind of efficient fusion method of Multisensor Distributed based on random set theory |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20211207 |