CN106767815A - Weighted least-squares indoor positioning algorithms based on the range finding of phase difference Euclidean distance - Google Patents

Weighted least-squares indoor positioning algorithms based on the range finding of phase difference Euclidean distance Download PDF

Info

Publication number
CN106767815A
CN106767815A CN201611081340.7A CN201611081340A CN106767815A CN 106767815 A CN106767815 A CN 106767815A CN 201611081340 A CN201611081340 A CN 201611081340A CN 106767815 A CN106767815 A CN 106767815A
Authority
CN
China
Prior art keywords
distance
tag
phase difference
reader
weighted
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
Application number
CN201611081340.7A
Other languages
Chinese (zh)
Other versions
CN106767815B (en
Inventor
马永涛
苗新龙
高政
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tianjin University
Original Assignee
Tianjin University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tianjin University filed Critical Tianjin University
Priority to CN201611081340.7A priority Critical patent/CN106767815B/en
Publication of CN106767815A publication Critical patent/CN106767815A/en
Application granted granted Critical
Publication of CN106767815B publication Critical patent/CN106767815B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20Instruments for performing navigational calculations
    • G01C21/206Instruments for performing navigational calculations specially adapted for indoor navigation
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/06Position of source determined by co-ordinating a plurality of position lines defined by path-difference measurements

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

本发明公开一种基于相位差欧氏距离测距的加权最小二乘室内定位算法,包括:布置定位RFID阅读器和参考标签;利用阅读器接收到的相位差估计阅读器与标签之间的距离,把多径效应、高斯白噪声引起的测距误差等效为高斯分布,参考标签与各个阅读器之间的估计距离与实际距离之间偏差的均值和方差构成高斯分布参量的位置参数和尺度参数;参考标签与待定位标签距离估计;以待定位标签与阅读器、参考标签之间距离估计误差的方差的倒数作为加权因子,运用加权最小二乘算法求解定位问题。本发明具有精度较高的特点。

The invention discloses a weighted least squares indoor positioning algorithm based on phase difference Euclidean distance measurement, including: arranging and positioning RFID readers and reference tags; using the phase difference received by the readers to estimate the distance between the readers and the tags , the ranging error caused by multipath effect and Gaussian white noise is equivalent to a Gaussian distribution, and the mean and variance of the deviation between the estimated distance and the actual distance between the reference tag and each reader constitute the position parameter and scale of the Gaussian distribution parameter Parameters; distance estimation between the reference tag and the tag to be positioned; the reciprocal of the variance of the distance estimation error between the tag to be positioned and the reader and the reference tag is used as the weighting factor, and the weighted least squares algorithm is used to solve the positioning problem. The invention has the characteristics of high precision.

Description

基于相位差欧氏距离测距的加权最小二乘室内定位算法Weighted Least Squares Indoor Positioning Algorithm Based on Phase Difference Euclidean Distance Ranging

技术领域technical field

本发明涉及一种室内定位问题。The invention relates to an indoor positioning problem.

背景技术Background technique

定位技术为人们的生活带来了极大的便利,近年来随着物联网的迅猛发展,人们对定位的需求越来越高,室内定位技术的应用也更加广泛。基于卫星的定位技术和基于移动蜂窝网的定位技术受建筑物的影响很大,在学校、仓库、商场等建筑物相对集中的场景中定位精度将会大大降低,无法满足高精度的定位需求。Positioning technology has brought great convenience to people's lives. In recent years, with the rapid development of the Internet of Things, people's demand for positioning has become higher and higher, and the application of indoor positioning technology has become more extensive. Satellite-based positioning technology and mobile cellular network-based positioning technology are greatly affected by buildings. In scenes where buildings such as schools, warehouses, and shopping malls are relatively concentrated, the positioning accuracy will be greatly reduced, which cannot meet the high-precision positioning requirements.

在室内定位中,电磁波在传输过程中遇到地面、天花板、墙壁、障碍物等会发生反射而产生多径效应,多径效应导致接收机接收到的信号的能量、相位、时间等信息发生改变,从而对定位结果产生严重的干扰。In indoor positioning, electromagnetic waves will reflect when encountering the ground, ceiling, walls, obstacles, etc. during transmission, resulting in multipath effects, which lead to changes in the energy, phase, time and other information of the signals received by the receiver , which seriously interferes with the positioning results.

在当前的定位技术中,主要有红外线定位技术、超声波室内定位技术、蓝牙室内定位技术、WIFI室内定位技术、ZigBee室内定位技术、计算机视觉定位技术、超宽带室内定位技术、UHF RFID室内定位技术等。其中,基于RFID的定位技术具有成本低、精度高、实时性强的优点,并且不需要预先建立指纹库,后期维护的工作量比较小。In the current positioning technology, there are mainly infrared positioning technology, ultrasonic indoor positioning technology, Bluetooth indoor positioning technology, WIFI indoor positioning technology, ZigBee indoor positioning technology, computer vision positioning technology, ultra-wideband indoor positioning technology, UHF RFID indoor positioning technology, etc. . Among them, the RFID-based positioning technology has the advantages of low cost, high precision, and strong real-time performance, and does not need to establish a fingerprint database in advance, and the workload of later maintenance is relatively small.

发明内容Contents of the invention

本发明的目的在于提供一种维护工作量比较小,精度较高的室内定位算法。技术方案如下:The purpose of the present invention is to provide an indoor positioning algorithm with relatively small maintenance workload and high precision. The technical scheme is as follows:

一种基于相位差欧氏距离测距的加权最小二乘室内定位算法,包括下列步骤:A weighted least squares indoor positioning algorithm based on phase difference Euclidean distance ranging, comprising the following steps:

1)布置定位场景:在所需定位的场景的不同位置布置至少三个RFID阅读器,并铺设参考标签;1) Arrange the positioning scene: arrange at least three RFID readers in different positions of the scene to be positioned, and lay reference tags;

2)阅读器与待定位标签距离估计:利用阅读器接收到的相位差估计阅读器与标签之间的距离,把多径效应、高斯白噪声引起的测距误差等效为高斯分布,参考标签与各个阅读器之间的估计距离与实际距离之间偏差的均值和方差构成高斯分布参量的位置参数和尺度参数;2) Estimation of the distance between the reader and the tag to be located: the phase difference received by the reader is used to estimate the distance between the reader and the tag, and the ranging error caused by multipath effect and Gaussian white noise is equivalent to a Gaussian distribution, and the reference tag The mean and variance of the deviation between the estimated distance and the actual distance with each reader constitute the position parameter and scale parameter of the Gaussian distribution parameter;

3)参考标签与待定位标签距离估计:构造标签的相位差矩阵,对参考标签之间的实际距离与相位差欧式距离进行拟合,求解出dij=a·Eij+b的待定系数a和b,其中,dij为第i个参考标签与第j个参考标签之间的实际距离,Eij为第i个参考标签与第j个参考标签之间的相位差欧式距离;把多径效应、相位差欧氏距离拟合以及高斯白噪声引起的测距误差等效为高斯分布,任意一个参考标签与其他参考标签之间通过线性拟合的估计距离与实际距离之间的偏差的均值和方差构成高斯分布参量的位置参数和尺度参数;3) Estimation of the distance between the reference tag and the tag to be located: Construct the phase difference matrix of the tag, fit the actual distance between the reference tags and the Euclidean distance of the phase difference, and solve the undetermined coefficient a of d ij = a E ij + b and b, where d ij is the actual distance between the i-th reference label and the j-th reference label, E ij is the phase difference Euclidean distance between the i-th reference label and the j-th reference label; Effect, phase difference Euclidean distance fitting and Gaussian white noise cause the ranging error is equivalent to a Gaussian distribution, the mean value of the deviation between the estimated distance and the actual distance between any reference tag and other reference tags by linear fitting and the variance constitute the position parameter and scale parameter of the Gaussian distribution parameter;

4)以待定位标签与阅读器、参考标签之间距离估计误差的方差的倒数作为加权因子,运用加权最小二乘算法求解定位问题。4) Taking the reciprocal of the variance of the distance estimation error between the tag to be positioned and the reader and the reference tag as the weighting factor, the weighted least squares algorithm is used to solve the positioning problem.

本发明可以缓解室内定位中多径效应和高斯白噪声对定位结果的影响,不需要建立指纹库,也不需要预先了解环境的具体情况,参考标签与待定位标签之间的距离估计利用相位差欧氏距离拟合,将多径效应、高斯白噪声、相位差欧氏距离拟合引起的距离估计误差等效为高斯分布,然后运用加权最小二乘求解定位问题,提高定位的精度。The present invention can alleviate the influence of multipath effect and Gaussian white noise on the positioning results in indoor positioning, and does not need to establish a fingerprint library, nor need to know the specific conditions of the environment in advance, and the distance estimation between the reference tag and the tag to be positioned uses the phase difference Euclidean distance fitting, the distance estimation error caused by multipath effect, Gaussian white noise, and phase difference Euclidean distance fitting is equivalent to Gaussian distribution, and then the weighted least squares is used to solve the positioning problem to improve the positioning accuracy.

附图说明Description of drawings

图1示出了本发明定位场景示意图。FIG. 1 shows a schematic diagram of a positioning scenario in the present invention.

图2示出了阅读器距离估计误差曲线。Figure 2 shows the reader distance estimation error curve.

图3示出了参考标签距离估计误差曲线。Figure 3 shows the reference tag distance estimation error curve.

图4示出了定位性能对比图。Fig. 4 shows a comparison chart of positioning performance.

具体实施方式detailed description

为验证所提算法的有效性,本发明在matlab中进行了实验仿真。其中,多径信道模型采用统计型信道模型,阅读器接收到的信号的最大多径数目从3到10依次改变,定位在10×10m2的带定位区域进行,在本实施实例具体应用如下:In order to verify the effectiveness of the proposed algorithm, the present invention has carried out experimental simulation in matlab. Among them, the multipath channel model adopts a statistical channel model, and the maximum multipath number of the signal received by the reader is changed from 3 to 10 in turn, and the positioning is carried out in a 10×10m 2 belt positioning area. The specific application in this implementation example is as follows:

1.布置定位场景。在待定位区域的四个角落安置四个阅读器,地面上等距铺设9个参考标签,如图1所示。1. Arrange the positioning scene. Four readers are placed at the four corners of the area to be located, and nine reference tags are laid equidistantly on the ground, as shown in Figure 1.

2.阅读器与待定位标签距离估计。利用阅读器接收到的相位差估计阅读器与标签之间的距离,把多径效应、高斯白噪声引起的测距误差等效为高斯分布,参考标签与各个阅读器之间的估计距离与实际距离之间偏差的均值和方差构成高斯分布参量的位置参数和尺度参数。2. Estimation of the distance between the reader and the tag to be located. Using the phase difference received by the reader to estimate the distance between the reader and the tag, the ranging error caused by the multipath effect and Gaussian white noise is equivalent to a Gaussian distribution, and the estimated distance between the reference tag and each reader is the same as the actual The mean and variance of the deviation between distances constitute the location and scale parameters of the Gaussian distribution parameters.

3.参考标签与待定位标签距离估计。构造标签的相位差矩阵,标签i与标签j之间的相位差欧氏距离为对参考标签之间的实际距离与相位差欧式距离进行拟合,求解出dij=a·Eij+b的待定系数a和b。把多径效应、相位差欧氏距离拟合、高斯白噪声引起的测距误差等效为高斯分布,任意一个参考标签与其他参考标签之间通过线性拟合的估计距离与实际距离之间的偏差的均值和方差构成高斯分布参量的位置参数和尺度参数。3. Estimating the distance between the reference tag and the tag to be located. Construct the phase difference matrix of the tag, and the phase difference Euclidean distance between tag i and tag j is The actual distance between the reference tags and the Euclidean distance of the phase difference are fitted, and the undetermined coefficients a and b of d ij =a·E ij +b are obtained. The ranging error caused by multipath effect, phase difference Euclidean distance fitting, and Gaussian white noise is equivalent to a Gaussian distribution, and the estimated distance between any reference tag and other reference tags through linear fitting and the actual distance The mean and variance of the deviation constitute the location and scale parameters of the Gaussian distribution parameters.

4.验证将距离估计误差等效为高斯分布的可行性。当最大多径数目为7时,与阅读器、参考标签之间距离估计误差的概率密度曲线与利用参考标签的位置信息和相位差信息计算的高斯分布曲线接近,如图2和图3所示,将距离估计误差等效为高斯分布是可行的。4. Verify the feasibility of equating the distance estimation error to a Gaussian distribution. When the maximum number of multipaths is 7, the probability density curve of the distance estimation error between the reader and the reference tag is close to the Gaussian distribution curve calculated by using the position information and phase difference information of the reference tag, as shown in Figure 2 and Figure 3 , it is feasible to equate the distance estimation error to a Gaussian distribution.

5.将阅读器和参考标签看作参考节点,共有N个参考节点,通过步骤2和步骤3可以计算出与参考节点之间距离估计高斯分布参量的位置参数λi和尺度参数σi,与参考节点之间距离估计为di,i=1,…,N。则有5. Consider the reader and the reference tag as reference nodes, and there are N reference nodes in total. Through steps 2 and 3, the position parameter λ i and the scale parameter σ i of the Gaussian distribution parameters of the distance estimation from the reference node can be calculated, and The distance between reference nodes is estimated to be d i , i=1,...,N. then there is

公式推导可以得到下式:The formula derivation can get the following formula:

WAθ=WbWAθ=Wb

其中, in,

计算上式即可求得待定位标签的坐标θ=(ATWA)-1ATWb。By calculating the above formula, the coordinate θ=( AT WA) -1 AT Wb of the tag to be located can be obtained.

Claims (1)

1.一种基于相位差欧氏距离测距的加权最小二乘室内定位算法,包括下列步骤:1. A weighted least squares indoor positioning algorithm based on phase difference Euclidean distance ranging, comprising the following steps: 1)布置定位场景:在所需定位的场景的不同位置布置至少三个RFID阅读器,并铺设参考标签;1) Arrange the positioning scene: arrange at least three RFID readers in different positions of the scene to be positioned, and lay reference tags; 2)阅读器与待定位标签距离估计:利用阅读器接收到的相位差估计阅读器与标签之间的距离,把多径效应、高斯白噪声引起的测距误差等效为高斯分布,参考标签与各个阅读器之间的估计距离与实际距离之间偏差的均值和方差构成高斯分布参量的位置参数和尺度参数;2) Estimation of the distance between the reader and the tag to be located: the phase difference received by the reader is used to estimate the distance between the reader and the tag, and the ranging error caused by multipath effect and Gaussian white noise is equivalent to a Gaussian distribution, and the reference tag The mean and variance of the deviation between the estimated distance and the actual distance with each reader constitute the position parameter and scale parameter of the Gaussian distribution parameter; 3)参考标签与待定位标签距离估计:构造标签的相位差矩阵,对参考标签之间的实际距离与相位差欧式距离进行拟合,求解出dij=a·Eij+b的待定系数a和b,其中,dij为第i个参考标签与第j个参考标签之间的实际距离,Eij为第i个参考标签与第j个参考标签之间的相位差欧式距离;把多径效应、相位差欧氏距离拟合以及高斯白噪声引起的测距误差等效为高斯分布,任意一个参考标签与其他参考标签之间通过线性拟合的估计距离与实际距离之间的偏差的均值和方差构成高斯分布参量的位置参数和尺度参数;3) Estimation of the distance between the reference tag and the tag to be located: Construct the phase difference matrix of the tag, fit the actual distance between the reference tags and the Euclidean distance of the phase difference, and solve the undetermined coefficient a of d ij = a E ij + b and b, where d ij is the actual distance between the i-th reference label and the j-th reference label, E ij is the phase difference Euclidean distance between the i-th reference label and the j-th reference label; Effect, phase difference Euclidean distance fitting and Gaussian white noise cause the ranging error is equivalent to a Gaussian distribution, the mean value of the deviation between the estimated distance and the actual distance between any reference tag and other reference tags by linear fitting and the variance constitute the position parameter and scale parameter of the Gaussian distribution parameter; 4)以待定位标签与阅读器、参考标签之间距离估计误差的方差的倒数作为加权因子,运用加权最小二乘算法求解定位问题。4) Taking the reciprocal of the variance of the distance estimation error between the tag to be positioned and the reader and the reference tag as the weighting factor, the weighted least squares algorithm is used to solve the positioning problem.
CN201611081340.7A 2016-11-30 2016-11-30 Weighted Least Squares Indoor Positioning Method Based on Phase Difference Euclidean Distance Ranging Expired - Fee Related CN106767815B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611081340.7A CN106767815B (en) 2016-11-30 2016-11-30 Weighted Least Squares Indoor Positioning Method Based on Phase Difference Euclidean Distance Ranging

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611081340.7A CN106767815B (en) 2016-11-30 2016-11-30 Weighted Least Squares Indoor Positioning Method Based on Phase Difference Euclidean Distance Ranging

Publications (2)

Publication Number Publication Date
CN106767815A true CN106767815A (en) 2017-05-31
CN106767815B CN106767815B (en) 2019-09-03

Family

ID=58898383

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611081340.7A Expired - Fee Related CN106767815B (en) 2016-11-30 2016-11-30 Weighted Least Squares Indoor Positioning Method Based on Phase Difference Euclidean Distance Ranging

Country Status (1)

Country Link
CN (1) CN106767815B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107341424A (en) * 2017-06-28 2017-11-10 西安交通大学 A kind of precise phase computational methods based on the estimation of RFID multipaths
CN108089149A (en) * 2017-12-19 2018-05-29 成都鸿福润德科技有限公司 A kind of ultra wide band location method based on signal two-way transmission time
CN110109054A (en) * 2019-04-03 2019-08-09 佛山市顺德区中山大学研究院 A kind of RFID localization method and device based on phase difference correction
CN110207699A (en) * 2018-02-28 2019-09-06 北京京东尚科信息技术有限公司 A kind of localization method and device
CN110850401A (en) * 2019-08-27 2020-02-28 天津大学 RFID label positioning method based on motion model and synthetic aperture
CN111505572A (en) * 2020-04-07 2020-08-07 电子科技大学 RFID moving track detection method
CN114280539A (en) * 2021-12-27 2022-04-05 中国民航大学 A Location Method Based on Missing Feature Vector Estimation

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009063114A1 (en) * 2007-11-16 2009-05-22 Universidad De Malaga Rfid-based object tracking for the visually impaired
CN102111876A (en) * 2011-02-24 2011-06-29 华为技术有限公司 Method and device for selecting reference labels used for location

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009063114A1 (en) * 2007-11-16 2009-05-22 Universidad De Malaga Rfid-based object tracking for the visually impaired
CN102111876A (en) * 2011-02-24 2011-06-29 华为技术有限公司 Method and device for selecting reference labels used for location

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘熙等: "多径环境下无源超高频RFID定位算法研究", 《计算机工程》 *
马永涛等: "A Multipath Mitigation Localization Algorithm Based on MDS for Passive UHF RFID", 《IEEE COMMUNICATIONS LETTERS》 *

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107341424A (en) * 2017-06-28 2017-11-10 西安交通大学 A kind of precise phase computational methods based on the estimation of RFID multipaths
CN108089149A (en) * 2017-12-19 2018-05-29 成都鸿福润德科技有限公司 A kind of ultra wide band location method based on signal two-way transmission time
CN110207699A (en) * 2018-02-28 2019-09-06 北京京东尚科信息技术有限公司 A kind of localization method and device
CN110207699B (en) * 2018-02-28 2022-04-12 北京京东尚科信息技术有限公司 Positioning method and device
CN110109054A (en) * 2019-04-03 2019-08-09 佛山市顺德区中山大学研究院 A kind of RFID localization method and device based on phase difference correction
CN110850401A (en) * 2019-08-27 2020-02-28 天津大学 RFID label positioning method based on motion model and synthetic aperture
CN110850401B (en) * 2019-08-27 2022-06-28 天津大学 A RFID Tag Location Method Based on Motion Model and Synthetic Aperture
CN111505572A (en) * 2020-04-07 2020-08-07 电子科技大学 RFID moving track detection method
CN111505572B (en) * 2020-04-07 2023-03-10 电子科技大学 RFID (radio frequency identification) moving track detection method
CN114280539A (en) * 2021-12-27 2022-04-05 中国民航大学 A Location Method Based on Missing Feature Vector Estimation
CN114280539B (en) * 2021-12-27 2024-08-06 中国民航大学 Positioning method based on missing feature vector estimation

Also Published As

Publication number Publication date
CN106767815B (en) 2019-09-03

Similar Documents

Publication Publication Date Title
CN106767815B (en) Weighted Least Squares Indoor Positioning Method Based on Phase Difference Euclidean Distance Ranging
CN106793087B (en) Array antenna indoor positioning method based on AOA and PDOA
Alsmadi et al. An improved indoor positioning accuracy using filtered RSSI and beacon weight
Afuosi et al. Indoor positioning based on improved weighted KNN for energy management in smart buildings
CN104076327B (en) Continuous positioning method based on search space reduction
CN107727095B (en) 3D indoor localization method based on spectral clustering and weighted back-propagation neural network
CN106226732B (en) The indoor wireless positioning and tracing method filtered based on TOF and iteration without mark
CN107484123B (en) WiFi indoor positioning method based on integrated HWKNN
CN106597363A (en) Pedestrian location method in indoor WLAN environment
Zhou et al. SCaNME: location tracking system in large-scale campus Wi-Fi environment using unlabeled mobility map
Shit et al. AI-enabled fingerprinting and crowdsource-based vehicle localization for resilient and safe transportation systems
Wang et al. Deep neural network‐based Wi‐Fi/pedestrian dead reckoning indoor positioning system using adaptive robust factor graph model
Wang et al. An indoor UWB NLOS correction positioning method based on anchor LOS/NLOS map
Ding et al. OGI-SLAM2: A hybrid map SLAM framework grounded in inertial-based SLAM
CN110007269A (en) A two-stage wireless signal fingerprint location method based on Gaussian process
Munadhil et al. Distance estimation-based PSO between patient with Alzheimer’s disease and beacon node in wireless sensor networks
Kerdjidj et al. Exploiting 2-D representations for enhanced indoor localization: A transfer learning approach
CN110072192B (en) WiFi indoor positioning method for smart phone
CN113794983A (en) Multi-target indoor positioning method based on nonlinear geometric constraint optimization
Zhang et al. Precise visual positioning of agricultural mobile robots with a fiducial marker reprojection approach
CN109254264A (en) Improved UHF-RFID positioning method
Soni et al. Intelligent RFID-based localization and tracking model design using unscented Kalman filter and convolution neural network
Wang et al. A Model Stacking Algorithm for Indoor Positioning System using WiFi Fingerprinting
CN114205749B (en) Ultra-wideband iterative positioning algorithm and device suitable for through-wall scene
Mo et al. A novel technique for human traffic based radio map updating in Wi-Fi indoor positioning systems

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

Granted publication date: 20190903

CF01 Termination of patent right due to non-payment of annual fee