CN114222240A - Multi-source fusion positioning method based on particle filtering - Google Patents
Multi-source fusion positioning method based on particle filtering Download PDFInfo
- Publication number
- CN114222240A CN114222240A CN202111274141.9A CN202111274141A CN114222240A CN 114222240 A CN114222240 A CN 114222240A CN 202111274141 A CN202111274141 A CN 202111274141A CN 114222240 A CN114222240 A CN 114222240A
- Authority
- CN
- China
- Prior art keywords
- positioning
- particle
- fusion
- precision
- uwb
- 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
- 239000002245 particle Substances 0.000 title claims abstract description 54
- 230000004927 fusion Effects 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001914 filtration Methods 0.000 title claims abstract description 24
- 230000033001 locomotion Effects 0.000 claims abstract description 17
- 238000010276 construction Methods 0.000 claims abstract description 7
- 238000012937 correction Methods 0.000 claims abstract description 7
- 230000000007 visual effect Effects 0.000 claims abstract description 4
- 230000001360 synchronised effect Effects 0.000 claims abstract 2
- 238000005516 engineering process Methods 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 5
- 238000007499 fusion processing Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000012952 Resampling Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000012805 post-processing Methods 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 2
- 230000015556 catabolic process Effects 0.000 claims 1
- 238000006731 degradation reaction Methods 0.000 claims 1
- 238000004891 communication Methods 0.000 abstract description 6
- 230000005540 biological transmission Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Navigation (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention belongs to the technical field of wireless communication, and relates to a particle filter-based multi-source fusion positioning method. The method mainly comprises the steps that a particle filter is adopted in a main filter to perform short-distance high-precision wireless positioning information based on UWB (Ultra Wide Band ), DR (Dead Reckoning) And VSLAM (Visual synchronous positioning And map construction) motion smooth fusion positioning based on extended Kalman filtering, geomagnetic signal fingerprint positioning based on a depth confidence network, various different signal source positioning data are fused continuously And refined step by step, And a positioning result is subjected to feedback correction, so that high-precision And continuous positioning under LOS (Line Of Sigh) And NLOS (Non-Line Of Sigh) environments is realized. The invention can be suitable for non-line-of-sight, complex electromagnetic environments and indoor layout variable environments, realizes high-precision, continuous and stable positioning, and provides technical support for indoor positioning of smart cities.
Description
Technical Field
The invention belongs to the technical field of wireless communication, and relates to a particle filter-based multi-source fusion positioning method.
Background
With the deep progress of the information revolution, new technologies such as the internet of things and artificial intelligence are gradually changing our lives. Location services are an essential link, and have been widely applied to aspects such as public safety, emergency rescue, intelligent transportation, location tracking and monitoring, big data analysis, and the like. The location service has great commercial value in a plurality of fields such as intelligent city construction, commodity information popularization and the like, is one of the most basic elements of the next generation mobile internet, and the development of the location service needs high-precision and high-reliability location information to provide support. In recent years, high-precision indoor positioning has been increasingly researched and paid attention to, the market is vigorously developed, the demand is continuously increased, and indoor wireless positioning research with higher precision, continuity and stability for moving targets becomes a key problem which needs to be solved urgently in many application researches.
GNSS (Global Navigation Satellite System) is the most competitive positioning and Navigation technology, and provides efficient and reliable positioning and Navigation services for Global users. However, in application scenes such as complex indoor environments, between urban buildings, high mountain canyons and underwater, and the like, due to the fact that technical obstacles such as NLOS (Non Line of Sight), complex electromagnetic environments, variable indoor layouts and the like are difficult to break through and are few, so far, any dominant high-precision indoor positioning service is not available. The multi-source fusion positioning technology can make up the defects of a single signal source positioning method and can provide positioning and navigation services in areas where GNSS cannot work. The multi-source fusion positioning is a technology based on an information fusion strategy, information in different subsystems can be comprehensively processed by utilizing a particle filter, and some defects of a single subsystem are avoided, so that an optimal fusion positioning result is obtained.
Currently, the indoor positioning technologies mainly include the following 5 types: radio Frequency Identification (RFID) location: the RFID realizes the identification of a target through electromagnetic induction between the tag and the reader-writer, only has simple data transmission capacity, has short RFID action distance due to power limitation and poor anti-electromagnetic interference capacity, and is only suitable for judging the existence or the access performance in a short distance range. WiFi positioning: WiFi positioning technology divide into trilateral location and fixes a position based on signal strength, and WiFi positioning can realize location, monitoring on a large scale, and its positioning accuracy depends on the data volume of reference point signal strength collection in earlier stage, if the quality of WiFi basic station or AP is unstable, can lead to the quality of location to obtain effectual assurance. Thirdly, positioning by Bluetooth: the bluetooth positioning is that a proper bluetooth local area network access point is installed indoors, and when a user starts the bluetooth function of the mobile terminal, the position information of the user is obtained through signal strength detection. The Bluetooth equipment is small in size, easy to integrate and low in power consumption, but the communication distance is limited to be only suitable for small-range positioning, the working range is 45m furthest, the positioning accuracy is within the range of 3m-15m, and the Bluetooth equipment is not suitable for indoor high-accuracy positioning. Fourthly, infrared positioning: the infrared positioning can realize relatively high positioning accuracy, but because infrared rays can not pass through a shielding object, the infrared emitter can not normally work when being shielded by the shielding object such as a human body or a wall, and the cost is high because an infrared receiver is installed in each positioning area, and the factors limit that the infrared positioning can only be suitable for positioning under sight distance transmission and close-range scenes. UWB (Ultra-Wide Band ) positioning: the UWB technology is a new wireless communication technology, different from the principle that high-frequency carrier waves are adopted for transmission in the traditional wireless communication technology, and nanosecond non-sinusoidal narrow pulses are utilized to transmit data at extremely low power in a short time. The unique communication mechanism has the advantages of strong multipath resolution capability, strong anti-interference capability, low system complexity, strong penetration capability and the like, thereby being widely concerned in the global scope. But many problems also arise in practical applications. On one hand, because the indoor environment is generally complex, the existence of shelters and the problems of environmental interference caused by other electronic equipment and the like cause that UWB signals are influenced by multipath interference and system errors in the transmission process, the signals received by a signal receiver have larger deviation, and the position calculation of subsequent labels is difficult; on the other hand, the contradiction between the continuous increase of the number of tags in the area and the continuous expansion of the system function types and the gradual increase of the serial processing chip adopted by the existing base station mostly causes low working efficiency, and the requirement of tag real-time positioning under the high-density condition cannot be met.
Therefore, any single positioning system has respective limitations, and cannot meet the requirements of high precision and seamless positioning in a complex scene. Therefore, the search for high-precision positioning technology is always a main target of research in the field of indoor positioning. The invention provides a method for positioning based on multi-source information fusion such as UWB (ultra wide band), geomagnetic signals, inertial navigation and images, so as to meet the use requirements in different application scenes and realize high-precision positioning of indoor multi-information fusion.
Disclosure of Invention
In view of the fact that any single positioning system has respective limitation and cannot meet the requirements of high-precision and seamless positioning in a complex scene, the invention provides the particle filter-based multi-source fusion positioning method, which can correct positioning errors caused by factors such as non-line-of-sight, complex electromagnetic environment and indoor layout diversity and provide high-precision indoor position information.
The technical scheme of the invention is as follows:
a multi-source fusion positioning method based on particle filtering comprises the following steps:
1. in the main filter, a particle filter is adopted to perform short-distance high-precision wireless positioning information based on UWB, DR (Dead Reckoning) And VSLAM (Visual Simultaneous Localization And Mapping) motion smooth fusion positioning based on extended Kalman filtering, geomagnetic signal fingerprint positioning based on a depth confidence network is fused, positioning data Of various different signal sources are continuously fused And gradually refined, And a positioning result is subjected to feedback correction, so that high-precision And continuous positioning under LOS (Line Of Sigh) And NLOS (Line Of Sigh) environments is realized, And positioning methods adopted by the signal sources are respectively as follows:
1) UWB-based geometric positioning
Measuring the Time Difference of the propagation of radio signals of the positioning tag relative to a plurality of different positioning base stations by using a UWB technology in an LOS environment so as to obtain the distance Difference of the positioning tag relative to the positioning base stations, and performing TDOA (Time Difference of Arrival) geometric positioning on the positioning tag so as to obtain position information;
2) geomagnetic signal fingerprint positioning based on depth confidence network
Entering a signal fingerprint positioning module based on Deep learning in an NLOS environment, acquiring UWB and geomagnetic signal fingerprints to form a multidimensional vector in an off-line stage, and inputting a DBN (Deep Boltzmann Machine) network for training; in the on-line positioning stage, firstly, calculating Euclidean distances between the preprocessed signal fingerprint data vectors and each clustering center, judging the cluster to which the preprocessed signal fingerprint data vectors belong, and then estimating the position of a current target by using a trained DBN network model of a corresponding class;
3) DR and VSLAM motion smooth fusion positioning based on extended Kalman filtering
Under the premise of acquiring the coordinate position of the carrier at the current moment, the angular velocity is acquired through the gyroscope, the acceleration is acquired through the accelerometer, so that the moving steering angle and the moving distance of the carrier in a unit sampling period are acquired, the coordinate position of the carrier at the next moment can be calculated, and the extended Kalman filtering is combined with dead reckoning and video SLAM map construction, so that high-precision positioning under the environment with NLOS shielding is realized.
2. Further, the method for realizing the multi-source information fusion indoor positioning by the particle filter comprises the following steps:
using particle filtering to correct position information and velocity (L)1、V1)、(L2、V2)、(L3、V3) The three positioning information are fused and positioned, the working process of the particle filter is mainly divided into the steps of initialization and selection of particles, a motion model and system state equation, particle weight updating and resampling, system state estimation and the like, wherein the state equation is as follows:
liand thetaiThe step size and the direction angle in the motion smooth estimation after particle weighting are represented, and the delta l and the delta theta represent corresponding random errors and are distributed according to Gaussian distribution. The method canThe method comprises the steps of abandoning particles with small weight, copying the particles with large weight for multiple times to obtain new particles, replacing the abandoned particles with the new particles, and determining the copying times by the weight.
The particle filter is adopted in the main filter to perform fusion processing on the positioning data of various different signal sources, a feedback correction mode is adopted to perform error correction on the sub-filter of the previous stage, accurate and continuous positioning in the motion process is achieved, when fusion processing is performed, based on the idea of dispersing and then concentrating post-processing, filtering results of three subsystems are subjected to unified registration of space-time reference, then global optimal estimation is obtained through fusion of the main filter, and when a certain subsystem fails and cannot work, positioning can be performed through the remaining subsystems through reliability distribution adjustment, and therefore high-precision seamless positioning is achieved.
Drawings
FIG. 1 is a flow chart of a particle filter based multi-source fusion positioning method;
fig. 2 is a flow chart of a particle filtering algorithm.
Detailed Description
The present invention will be described in detail with reference to the drawings.
As shown in fig. 1, the main steps of the present invention are as follows:
1) UWB-based geometric positioning in LOS environment
In a LOS environment, UWB-based high-precision geometric positioning is performed: through a positioning base station with known coordinates arranged indoors, a person to be positioned carries a positioning tag, the tag emits pulses according to a certain frequency, the distance measurement is continuously carried out with the base station with the known position, and the position of the tag is calculated through TDOA geometric positioning;
2) geomagnetic signal fingerprint positioning based on deep confidence network under NLOS environment
The deep learning-based fingerprint positioning is realized by adopting DBN (DBN under NLOS (non-linear regression) environment, and the structure of the deep learning-based fingerprint positioning system is composed of a plurality of layers of RBMs (Restricted Boltzmann machines) and a layer of BP (Back propagation, Back propagation neural network). In the off-line stage, UWB and geomagnetic signal fingerprints are collected to form a multidimensional vector, and the multidimensional vector is input into a DBN (digital broadcast network) to be trained; in the on-line positioning stage, firstly, calculating Euclidean distances between the preprocessed signal fingerprint data vectors and each clustering center, judging the cluster to which the preprocessed signal fingerprint data vectors belong, and then estimating the position of a current target by using a trained DBN network model of a corresponding class;
3) DR and VSLAM motion smooth fusion positioning based on extended Kalman filtering
And acquiring angular velocity and acceleration by using a gyroscope and an accelerometer so as to obtain the steering angle and the distance of the movement of the carrier in a unit sampling period, carrying out dead reckoning on the basis of the established mathematical model, and calculating the coordinate position of the carrier at the next moment. And transmitting the data to a camera SLAM positioning module, acquiring the data by using the camera, and realizing visual positioning based on the established SLAM model. Then, integrating dead reckoning and video SLAM map construction by extended Kalman filtering, thereby realizing higher-precision positioning in an NLOS shielded environment;
4) particle filtering for realizing multi-source information fusion indoor positioning
A particle filter is adopted in a main filter to fuse UWB positioning information, VSLAM map construction based on Kalman filtering fusion with a gyroscope, accelerometer dead reckoning position information and geomagnetic signal fingerprint positioning information based on a depth confidence network, and various different signal source positioning data, and meanwhile, a feedback correction mode is adopted to correct errors of a sub-filter of the previous stage, so that accurate and continuous positioning in the motion process is achieved. During fusion processing, based on the idea of first dispersion and then concentration post-processing, the filtering results of the three subsystems are subjected to unified registration of space-time reference, and then are fused by a main filter to obtain global optimal estimation, so that the positioning accuracy is improved with lower complexity, as shown in fig. 1. When a certain subsystem has a problem or cannot work, the positioning can be carried out through the residual systems through the reliability distribution adjustment, so that the seamless positioning is realized.
The multisource fusion positioning algorithm based on particle filtering comprises the following steps:
the method comprises the following steps: initialization, from the beginningGenerating particle sets in test distributions
The weight of each particle is 1/N, the initial position obtained by positioning each subsystem is input, and the unit distance of target movement is used as prior information;
step two: sampling importance, constructing a target motion equation by using target motion information measured by a gyroscope, an accelerometer and a camera, predicting a new position by a particle set according to the motion equation, predicting the state of all particles, and calculating the observation estimated value of the particles;
taking a geometric positioning result based on UWB under an LOS environment as an observed value, taking a fingerprint positioning result obtained by a deep belief network under an NLOS environment as an observed value, calculating a weight corresponding to each particle according to the distance between a particle set and the observed value, and updating the particle weight;
normalization
Step three: resampling based on
The sample is copied or discarded to obtain a new particle set, and the total number of particles is unchanged after resampling. Order to
Step four: state estimation, namely calculating to obtain target state estimation according to the weights and states of all the particles;
step five: returning to the step two to continue to execute the filtering until the filtering is finished.
The position information of the target at the current moment can be obtained through the steps. And fusing the information of each sub-positioning system by using a particle filter to realize the co-positioning. The method has good fault-tolerant capability and high positioning precision, and realizes seamless and high-precision positioning.
Claims (1)
1. A multisource fusion positioning method based on particle filtering is characterized in that a particle filter is adopted in a main filter to fuse short-distance high-precision wireless positioning information based on UWB (Ultra Wide Band ), DR (Dead Reckoning) And VSLAM (Visual synchronous positioning And map construction) motion smooth fusion positioning based on extended Kalman filtering, And geomagnetic signal fingerprint positioning based on a depth confidence network, various signal source positioning data are continuously fused And gradually refined, positioning results are fed back And corrected, high-precision And seamless continuous positioning under LOS (Line Of Sigh) And NLOS (Non-Line Of Sight) environments is realized, And the positioning methods adopted by several signal sources are respectively as follows:
1) UWB-based geometric positioning
Measuring the Time Difference Of the propagation Of radio signals Of the positioning tag relative to a plurality Of different positioning base stations by using a UWB technology in an LOS environment so as to obtain the distance Difference Of the positioning tag relative to the positioning base stations, and performing TDOA (Time Difference Of Arrival) geometric positioning on the positioning tag so as to obtain position information;
2) geomagnetic signal fingerprint positioning based on depth confidence network
Entering a signal fingerprint positioning module based on Deep learning in an NLOS environment, acquiring UWB and geomagnetic signal fingerprints to form a multidimensional vector in an off-line stage, and inputting a DBN (Deep Boltzmann Machine) network for training; in the on-line positioning stage, firstly, calculating Euclidean distances between the preprocessed signal fingerprint data vectors and each clustering center, judging the cluster to which the preprocessed signal fingerprint data vectors belong, and then estimating the position of a current target by using a trained DBN network model of a corresponding class;
3) DR and VSLAM motion smooth fusion positioning based on extended Kalman filtering
On the premise of acquiring the coordinate position of the carrier at the current moment, acquiring the angular velocity through a gyroscope and acquiring the acceleration through an accelerometer so as to acquire the moving steering angle and the moving distance of the carrier in a unit sampling period, further calculating the coordinate position of the carrier at the next moment, and then fusing dead reckoning and video SLAM map construction through extended Kalman filtering, thereby realizing higher-precision positioning in an NLOS shielded environment;
further, the method for realizing the multi-source information fusion indoor positioning by the particle filter comprises the following steps:
using particle filtering to correct position information and velocity (L)1、V1)、(L2、V2)、(L3、V3) The three positioning information are fused and positioned, the working process of the particle filter is mainly divided into the steps of initialization and selection of particles, a motion model and system state equation, particle weight updating and resampling, system state estimation and the like, wherein the state equation is as follows:
liand thetaiThe method can effectively solve the problem of particle degradation, when the number of effective particles is less than a certain threshold value, the particles are resampled, the method is to abandon the particles with small weight and copy the particles with large weight for multiple times to obtain the productWhen the new particle is arrived, the abandoned particle is replaced by the new particle, and the copying times are determined by the weight;
the particle filter is adopted in the main filter to perform fusion processing on the positioning data of various different signal sources, a feedback correction mode is adopted to perform error correction on the sub-filter of the previous stage, accurate and continuous positioning in the motion process is achieved, when fusion processing is performed, based on the idea of dispersing and then concentrating post-processing, filtering results of three subsystems are subjected to unified registration of space-time reference, then global optimal estimation is obtained through fusion of the main filter, and when a certain subsystem fails and cannot work, positioning can be performed through the remaining subsystems through reliability distribution adjustment, and therefore high-precision seamless positioning is achieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111274141.9A CN114222240A (en) | 2021-10-29 | 2021-10-29 | Multi-source fusion positioning method based on particle filtering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111274141.9A CN114222240A (en) | 2021-10-29 | 2021-10-29 | Multi-source fusion positioning method based on particle filtering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114222240A true CN114222240A (en) | 2022-03-22 |
Family
ID=80696360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111274141.9A Pending CN114222240A (en) | 2021-10-29 | 2021-10-29 | Multi-source fusion positioning method based on particle filtering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114222240A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115103299A (en) * | 2022-06-15 | 2022-09-23 | 河南工程学院 | Multi-sensor fusion positioning method based on RFID |
| CN115187792A (en) * | 2022-09-09 | 2022-10-14 | 武汉中仪物联技术股份有限公司 | Pipeline crack extraction method and device, electronic equipment and storage medium |
| CN115426401A (en) * | 2022-08-31 | 2022-12-02 | 国家开放大学 | Information pushing method and device based on teaching space |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017088196A1 (en) * | 2015-11-24 | 2017-06-01 | 东南大学 | Fusion navigation device and method based on wireless fingerprints and mems sensor |
| JP2017173001A (en) * | 2016-03-18 | 2017-09-28 | 国立大学法人東北大学 | Information terminal, position estimation method, and position estimation program |
| US20170289951A1 (en) * | 2016-04-01 | 2017-10-05 | Saikat Dey | Geo-Localization Assembly and Methodology |
| CN107421546A (en) * | 2017-08-25 | 2017-12-01 | 北京麦钉艾特科技有限公司 | A kind of passive combined positioning method based on space environment magnetic signature |
| CN108089180A (en) * | 2017-12-18 | 2018-05-29 | 江苏添仂智能科技有限公司 | Based on UWB sensors as back indicator to the localization method of GPS and inertial navigation system the suspension type rail vehicle corrected |
| CN109298389A (en) * | 2018-08-29 | 2019-02-01 | 东南大学 | Indoor pedestrian based on multiparticle group optimization combines position and orientation estimation method |
| JP2019212291A (en) * | 2018-06-07 | 2019-12-12 | 光禾感知科技股▲ふん▼有限公司Ｏｓｅｎｓｅ Ｔｅｃｈｎｏｌｏｇｙ Ｃｏ．， Ｌｔｄ． | Indoor positioning system and method based on geomagnetic signals in combination with computer vision |
| CN111698774A (en) * | 2020-06-23 | 2020-09-22 | 北京麦钉艾特科技有限公司 | Indoor positioning method and device based on multi-source information fusion |
| CN112261719A (en) * | 2020-07-24 | 2021-01-22 | 大连理智科技有限公司 | Area positioning method combining SLAM technology with deep learning |
| CN112923919A (en) * | 2021-01-21 | 2021-06-08 | 湖南格纳微信息科技有限公司 | Pedestrian positioning method and system based on graph optimization |
| CN113074732A (en) * | 2021-03-22 | 2021-07-06 | 东南大学 | Indoor and outdoor seamless positioning system and positioning method thereof |
| CN113074739A (en) * | 2021-04-09 | 2021-07-06 | 重庆邮电大学 | UWB/INS fusion positioning method based on dynamic robust volume Kalman |
-
2021
- 2021-10-29 CN CN202111274141.9A patent/CN114222240A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017088196A1 (en) * | 2015-11-24 | 2017-06-01 | 东南大学 | Fusion navigation device and method based on wireless fingerprints and mems sensor |
| JP2017173001A (en) * | 2016-03-18 | 2017-09-28 | 国立大学法人東北大学 | Information terminal, position estimation method, and position estimation program |
| US20170289951A1 (en) * | 2016-04-01 | 2017-10-05 | Saikat Dey | Geo-Localization Assembly and Methodology |
| CN107421546A (en) * | 2017-08-25 | 2017-12-01 | 北京麦钉艾特科技有限公司 | A kind of passive combined positioning method based on space environment magnetic signature |
| CN108089180A (en) * | 2017-12-18 | 2018-05-29 | 江苏添仂智能科技有限公司 | Based on UWB sensors as back indicator to the localization method of GPS and inertial navigation system the suspension type rail vehicle corrected |
| JP2019212291A (en) * | 2018-06-07 | 2019-12-12 | 光禾感知科技股▲ふん▼有限公司Ｏｓｅｎｓｅ Ｔｅｃｈｎｏｌｏｇｙ Ｃｏ．， Ｌｔｄ． | Indoor positioning system and method based on geomagnetic signals in combination with computer vision |
| CN109298389A (en) * | 2018-08-29 | 2019-02-01 | 东南大学 | Indoor pedestrian based on multiparticle group optimization combines position and orientation estimation method |
| CN111698774A (en) * | 2020-06-23 | 2020-09-22 | 北京麦钉艾特科技有限公司 | Indoor positioning method and device based on multi-source information fusion |
| CN112261719A (en) * | 2020-07-24 | 2021-01-22 | 大连理智科技有限公司 | Area positioning method combining SLAM technology with deep learning |
| CN112923919A (en) * | 2021-01-21 | 2021-06-08 | 湖南格纳微信息科技有限公司 | Pedestrian positioning method and system based on graph optimization |
| CN113074732A (en) * | 2021-03-22 | 2021-07-06 | 东南大学 | Indoor and outdoor seamless positioning system and positioning method thereof |
| CN113074739A (en) * | 2021-04-09 | 2021-07-06 | 重庆邮电大学 | UWB/INS fusion positioning method based on dynamic robust volume Kalman |
Non-Patent Citations (5)
| Title |
|---|
| JISHI CUI: "Multi-Source Data Fusion Method for Indoor Localization System", 《2020 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA (ICCC)》 * |
| MICHAEL HEUER: "Multi-modal fusion with particle filter for speaker localization and tracking", 《2011 INTERNATIONAL CONFERENCE ON MULTIMEDIA TECHNOLOGY》 * |
| YUAN WU: "Indoor Positioning Based on Walking-Surveyed Wi-Fi Fingerprint and Corner Reference Trajectory-Geomagnetic Database", 《IEEE SENSORS JOURNAL 》 * |
| 王照远;高井祥;李增科;常梦阳;: "一种融合WiFi/地磁/PDR的室内定位方法", 测绘通报, no. 06 * |
| 陆妍玲;韦俊伶;刘采玮;李景文;姜建武;: "融合地磁/WiFi/PDR的自适应粒子滤波室内定位", 测绘通报, no. 06 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115103299A (en) * | 2022-06-15 | 2022-09-23 | 河南工程学院 | Multi-sensor fusion positioning method based on RFID |
| CN115103299B (en) * | 2022-06-15 | 2024-04-09 | 河南工程学院 | Multi-sensor fusion positioning method based on RFID |
| CN115426401A (en) * | 2022-08-31 | 2022-12-02 | 国家开放大学 | Information pushing method and device based on teaching space |
| CN115187792A (en) * | 2022-09-09 | 2022-10-14 | 武汉中仪物联技术股份有限公司 | Pipeline crack extraction method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Toward location-enabled IoT (LE-IoT): IoT positioning techniques, error sources, and error mitigation | |
| Asaad et al. | A comprehensive review of indoor/outdoor localization solutions in IoT era: Research challenges and future perspectives | |
| Guo et al. | A survey on fusion-based indoor positioning | |
| El-Sheimy et al. | Indoor navigation: State of the art and future trends | |
| CN114222240A (en) | Multi-source fusion positioning method based on particle filtering | |
| CN113706612B (en) | Underground coal mine vehicle positioning method fusing UWB and monocular vision SLAM | |
| LaMarca et al. | Location systems: An introduction to the technology behind location awareness | |
| CN105424030A (en) | Fusion navigation device and method based on wireless fingerprints and MEMS sensor | |
| CN106248107A (en) | A kind of flight path based on indoor earth magnetism path matching infers calibration steps and device | |
| Ren et al. | Movement pattern recognition assisted map matching for pedestrian/wheelchair navigation | |
| Liu et al. | Research and development of indoor positioning | |
| Shin et al. | Received signal strength-based robust positioning system in corridor environment | |
| Wang et al. | Indoor PDR Positioning Assisted by Acoustic Source Localization, and Pedestrian Movement Behavior Recognition, Using a Dual‐Microphone Smartphone | |
| Wang et al. | Recent advances in floor positioning based on smartphone | |
| Le et al. | Indoor navigation system for handheld devices | |
| Jia et al. | An indoor and outdoor seamless positioning system based on android platform | |
| CN112556689B (en) | Positioning method integrating accelerometer and ultra-wideband ranging | |
| Mikhalev et al. | Passive emitter geolocation using agent-based data fusion of AOA, TDOA and FDOA measurements | |
| Wang et al. | Sky-view images aided NLOS detection and suppression for tightly coupled GNSS/INS system in urban canyon areas | |
| Gao | Investigation of Context Determination for Advanced Navigation Using Smartphone Sensors | |
| Li et al. | Wireless Positioning: Technologies, Applications, Challenges, and Future Development Trends | |
| Jahagirdar et al. | WiFi based Indoor Positioning System using Machine Learning and Multi-Node Triangulation Algorithms | |
| Wang et al. | [Retracted] Personnel Positioning System Method in Building Based on Inertial Sensor | |
| CN114513746A (en) | Indoor positioning method integrating triple visual matching model and multi-base-station regression model | |
| Luo et al. | A GNSS UWB tight coupling and IMU ESKF algorithm for indoor and outdoor mixed scenario |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220322 |
|
| WD01 | Invention patent application deemed withdrawn after publication |