CN112261718B - Indoor positioning method - Google Patents
Indoor positioning method Download PDFInfo
- Publication number
- CN112261718B CN112261718B CN202011024537.3A CN202011024537A CN112261718B CN 112261718 B CN112261718 B CN 112261718B CN 202011024537 A CN202011024537 A CN 202011024537A CN 112261718 B CN112261718 B CN 112261718B
- Authority
- CN
- China
- Prior art keywords
- indoor
- node
- electronic map
- signal intensity
- positioning method
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses an indoor positioning method, which comprises the following steps: acquiring indoor environment information; analyzing distribution interval characteristics of the received signal strength indication based on the indoor environment information; constructing a wireless sensor network and an indoor plane electronic map; the wireless sensor network carries out positioning detection and transmits the positioning detection result to the upper computer; dividing an indoor environment into a plurality of areas, collecting signal intensity indicating data of the area where a detected person is located and position coordinates of an indoor plane electronic map, and transmitting the signal intensity indicating data and the position coordinates into a neural network system; the neural network system carries out perception prediction based on the signal intensity indicating data of the area where the detected person is located and the position coordinate of the indoor plane electronic map, and outputs the target position.
Description
Technical Field
The invention relates to the technical field of personnel positioning, in particular to an indoor positioning method.
Background
Currently, due to the extensive research and application of GPS positioning technology, outdoor positioning systems have well met the needs of outdoor positioning. However, in the research of indoor positioning technology, because there are many indoor obstacles and the environment is complicated and changeable, some existing indoor sensing positioning methods cannot well meet the needs of a large number of users. Common indoor positioning technologies include infrared positioning technology, ultrasonic positioning technology, radio frequency identification technology, and the like, which have the disadvantages. Therefore, it is an urgent need to find a sensing and positioning method that can break through environmental interference and is not affected by obstacles, room temperature, illumination and other factors.
Disclosure of Invention
The present invention is directed to an indoor positioning method to solve the problems set forth in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: an indoor positioning method, comprising:
acquiring indoor environment information;
analyzing distribution interval characteristics of received signal strength indications based on the indoor environment information;
constructing a wireless sensor network and an indoor plane electronic map;
the wireless sensor network carries out positioning detection and transmits the positioning detection result to an upper computer;
dividing an indoor environment into a plurality of areas, collecting signal intensity indication data of the areas where detected people are located and position coordinates of an indoor plane electronic map, and transmitting the signal intensity indication data and the position coordinates into a neural network system;
and the neural network system carries out perception prediction based on the signal intensity indication data of the area where the detected person is located and the position coordinates of the indoor plane electronic map, and outputs the target position.
Preferably, the analysis mode of the distribution interval characteristic of the received signal strength indication is point-to-point communication analysis.
Preferably, the peer-to-peer communication analysis is to obtain two nodes on the same horizontal plane, where one node is a fixed node and the other node is a mobile node, the mobile node moves in a direction away from the fixed node, and records communication data between the fixed node and the mobile node every unit distance.
Preferably, the wireless sensor network comprises a plurality of sensor nodes, and 2 communication links are arranged between every two sensor nodes.
Preferably, the position coordinate of the indoor plane electronic map is a two-dimensional plane coordinate.
Preferably, the number of sensor nodes is not less than 13.
Preferably, the sensor node transmits the positioning detection result to an upper computer through a gateway.
Compared with the prior art, the invention has the beneficial effects that: the indoor positioning method can quickly and accurately position indoor personnel, and can break through interference in the positioning process, so that the positioning is more accurate, and the positioning effect is better.
Drawings
Fig. 1 is a flowchart of an indoor positioning method according to an embodiment of the present invention;
FIG. 2 is a static object location graph of an indoor location method according to an embodiment of the present invention;
FIG. 3 is a dynamic target location diagram of an indoor location method according to an embodiment of the present invention;
fig. 4 is a dynamic target positioning trajectory diagram of an indoor positioning method according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the present invention provides a technical solution: an indoor positioning method, comprising:
acquiring indoor environment information;
analyzing distribution interval characteristics of received signal strength indication based on indoor environment information, and analyzing the distribution interval characteristic distribution characteristics of the signal strength indication so as to determine the maximum distance that the data can not be seriously jittered to influence positioning in a region with larger interference, thereby determining the distribution of the sensors;
the wireless sensor network and the indoor plane electronic map are constructed, the wireless sensor network carries out data transmission through radio frequency signals, the radio frequency signals are used as electromagnetic waves, the wavelengths of the electromagnetic waves can be adjusted to carry out non-line-of-sight transmission, and the electromagnetic waves pass through non-metal walls, shelters, trees, indoor other barriers and the like through reflection, diffraction and scattering effects. Compared with traditional sensors such as a camera, infrared rays and ultrasonic waves, the radio frequency signal is insensitive to environmental changes, external illumination changes, temperature and humidity changes, smoke and the like hardly affect the transmission of the radio frequency signal, and the anti-interference performance is obviously superior to that of a traditional positioning system;
the wireless sensor network carries out positioning detection and transmits the positioning detection result to the upper computer;
dividing an indoor environment into a plurality of areas, collecting signal intensity indicating data of an area where a detected person is located and position coordinates of an indoor plane electronic map, and transmitting the signal intensity indicating data and the position coordinates into a neural network system, wherein the neural network is an artificial neural network, the artificial neural network is an artificial neuron mathematical model which is currently nonlinear science and computational intelligence and utilizes a large amount of abstractions, and simulates the biological process of human brain, the artificial neural network finds internal rules in a large amount of sample data based on learning and memory, does not need any prior formula, has strong nonlinear mapping capability, can automatically give correct output when similar input appears again, and distribution interval characteristic fingerprint data indicated by the signal intensity of each position needs to be collected for many times in the actual use process, and the fingerprint data comprises: and the distribution interval characteristic data of the signal intensity indication of each node at the moment and the two-dimensional coordinates of the indoor plane electronic map of the collection personnel. The distribution interval characteristics of the signal strength indications acquired by each node for multiple times can be averaged to be used as final data. The neural network requires a portion of the fingerprint data to be trained and another portion to test its performance. When the precision of the neural network training and testing is high enough, the method can be used;
the neural network system carries out perception prediction based on signal intensity indicating data of an area where a detected person is located and position coordinates of an indoor plane electronic map, outputs a target position, and takes one part of the measured data and coordinates as a training sample and the other part as a testing sample; the method comprises the steps of carrying out perception prediction on data measured in real time by using a trained neural network, outputting the position of a target, displaying the moving track of the target by an upper computer if the target moves, carrying out perception prediction on the distribution interval characteristic of the neural network based on signal intensity indication received by a sensor in the operation process, namely the distribution interval characteristic data of the signal intensity indication uploaded to the upper computer by a gateway, and outputting the position of an indoor plane electronic map where the target is located.
The programs of the upper computer are all operated by Matlab and are mainly responsible for the functions of signal strength indication data acquisition, index sample acquisition, neural network training, real-time perception and the like. The upper computer receives the signal strength indication data of the sink node through the USB virtual serial port, a serial port object needs to be generated in Matlab to operate the serial port, and the operation comprises configuration of parameters such as baud rate, effective bit length of data, parity check and the like, configuration of a receiving mode, callback function and the like. And training the network by using a common function and sample data of neural network training provided in Matlab, and performing perception prediction on a new index measured in real time by using the trained neural network. And if the detected target is dynamically moved, displaying the moving track on the upper computer.
Specifically, the analysis method of the distribution interval characteristic of the received signal strength indication is point-to-point communication analysis.
Specifically, the point-to-point communication analysis is to obtain two nodes on the same horizontal plane, where one node is a fixed node and the other node is a mobile node, the mobile node moves away from the fixed node, and records communication data between the fixed node and the mobile node every unit distance, and the multiple measurements of each unit distance are averaged to fit the measured data into a curve, and a value with a small fluctuation and a long distance is selected from the data indicated by the received signal strength relative to the curve value. Thus, the received signal strength indication value can be effectively obtained and the cost can be reduced.
Specifically, the wireless sensor network comprises a plurality of sensor nodes, wherein the sensor nodes are responsible for receiving and sending data to each other, storing and sending signal strength indicating data generated by communication between other nodes and the sensor nodes to the sink node. And the sensor node is in a receiving state most of the time, the received signal strength is analyzed to indicate that the source node number of the data packet is compared with the node number of the sensor node, a token is obtained when the sensor node turns to the sensor node, the token is sent, and if the token transmission is stopped unexpectedly, the sink node is responsible for starting a new round of ring coordination. Therefore, all the sensor node programs are consistent, and 2 communication links can be arranged between every two sensor nodes only by configuring different node numbers for the sensor nodes.
Specifically, the position coordinates of the indoor planar electronic map are two-dimensional planar coordinates.
Specifically, the number of the sensor nodes is not less than 13, and the CC2530 is used as a main control chip to construct the network nodes in the method. The CC2530 is a radio frequency SoC which is proposed by TI and conforms to the IEEE802.15.4 communication standard, is widely applied to the construction of an indoor wireless sensor network with short distance, low speed, low cost and low power consumption, and conforms to the design requirement of an indoor passive sensing model.
The sensor nodes comprise a sink node, the sink node is responsible for starting each signal strength indication acquisition period and receiving signal strength indication data sent by each sensor node, and after one acquisition period is finished, all the signal strength indication data are collected and transmitted to the upper computer. Under normal conditions, the sink node sends a ring coordination starting command to the sensor node No. 1 at the beginning of a period, ring coordination tokens are sequentially transmitted in the sensor nodes, and only the sensor node obtaining the token can send a signal strength indication to the sink node, so that in the whole period, the sink node sends the starting command for 1 time, receives 12 groups of 11 signal strength indications in each group, and the cycle is repeated.
Specifically, the sensor node transmits the positioning detection result to the upper computer through the gateway.
As shown in fig. 2 and table 1, when the positioning positions of 8 static objects are detected, the static object positioning data is shown in table 1:
TABLE 1
As shown in fig. 3 and table 2, when detecting a dynamic object, the dynamic object perceived location is as shown in table 2,
TABLE 2
The position change of the dynamic object is shown in fig. 4, in which the dotted line part represents the motion trajectory.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. An indoor positioning method, comprising:
acquiring indoor environment information;
analyzing distribution interval characteristics of received signal strength indications based on the indoor environment information;
constructing a wireless sensor network and an indoor plane electronic map;
the wireless sensor network carries out positioning detection and transmits the positioning detection result to an upper computer;
dividing an indoor environment into a plurality of areas, collecting signal intensity indicating data of the area where a detected person is located and position coordinates of an indoor plane electronic map, and transmitting the signal intensity indicating data and the position coordinates into a neural network system;
the neural network system carries out perception prediction based on signal intensity indication data of the area where the detected person is located and the position coordinates of the indoor plane electronic map, and outputs the position of the target in the indoor plane electronic map;
the analysis mode of the distribution interval characteristic of the received signal strength indication is point-to-point communication analysis;
the point-to-point communication analysis is to obtain two nodes on the same horizontal plane, wherein one node is a fixed node, the other node is a mobile node, the mobile node moves towards the direction far away from the fixed node, communication data between the fixed node and the mobile node are recorded at intervals of unit distance, the average value of multiple measurements of each unit distance is taken, and the measurement data are fitted into a curve.
2. The indoor positioning method according to claim 1, characterized in that: the wireless sensor network comprises a plurality of sensor nodes, and 2 communication links are arranged between every two sensor nodes.
3. The indoor positioning method according to claim 1, wherein: and the position coordinate of the indoor plane electronic map is a two-dimensional plane coordinate.
4. The indoor positioning method according to claim 1, wherein: the number of the sensor nodes is not less than 13.
5. The indoor positioning method according to claim 4, characterized in that: and the sensor node transmits the distribution interval characteristics indicated by the signal intensity to an upper computer through a gateway.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011024537.3A CN112261718B (en) | 2020-09-25 | 2020-09-25 | Indoor positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011024537.3A CN112261718B (en) | 2020-09-25 | 2020-09-25 | Indoor positioning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112261718A CN112261718A (en) | 2021-01-22 |
| CN112261718B true CN112261718B (en) | 2022-09-27 |
Family
ID=74233598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011024537.3A Active CN112261718B (en) | 2020-09-25 | 2020-09-25 | Indoor positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112261718B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112947451B (en) * | 2021-02-22 | 2022-09-27 | 浙江纳特智能网络工程有限公司 | Intelligent community personnel supervision system based on wireless communication positioning |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103228040A (en) * | 2012-01-31 | 2013-07-31 | 国际商业机器公司 | Indoor electronic map generating method and system, and indoor target positioning method and system |
| KR102158029B1 (en) * | 2014-01-03 | 2020-09-21 | 한국전자통신연구원 | Method and apparatus for recognizing indoor location using field intensity map |
| CN105872981B (en) * | 2016-03-30 | 2018-12-25 | 河海大学常州校区 | Indoor orientation method based on signal synthesis and artificial neural network |
| CN107064913A (en) * | 2017-03-10 | 2017-08-18 | 上海斐讯数据通信技术有限公司 | A kind of wireless location method and system based on deep learning |
| US10620290B1 (en) * | 2019-02-19 | 2020-04-14 | Ideal Industries Lighting Llc | Indoor positioning system |
| CN110082716B (en) * | 2019-04-29 | 2023-07-11 | 徐州医科大学 | Indoor positioning system and positioning method for complex environment of hospital |
-
2020
- 2020-09-25 CN CN202011024537.3A patent/CN112261718B/en active Active
Non-Patent Citations (3)
| Title |
|---|
| 一种基于RBF神经网络的无线传感器网络定位模型;于涛等;《山东科学》;20101215(第06期);全文 * |
| 一种基于分段拟合估计的WSN定位算法;张会清等;《计算机测量与控制》;20090125(第01期);全文 * |
| 基于BP神经网络的ZigBee无线定位技术;杨筱宇;《现代计算机(专业版)》;20120405(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112261718A (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109444813B (en) | RFID indoor positioning method based on BP and DNN double neural networks | |
| CN111919476B (en) | Indoor positioning method, server and positioning system | |
| Kaltiokallio et al. | Follow@ grandma: Long-term device-free localization for residential monitoring | |
| CN102638889B (en) | Indoor wireless terminal positioning method based on Bayes compression sensing | |
| CN106559749B (en) | Multi-target passive positioning method based on radio frequency tomography | |
| CN102589504B (en) | Online measuring device for diameter of tree in growth | |
| CN108871332A (en) | A kind of RFID indoor locating system and method based on XGBoost | |
| CN110046834A (en) | Workplace pernicious gas health risk quantitative evaluating system and its appraisal procedure | |
| CN111601270A (en) | Internet of things power monitoring system and method of wireless sensor network topological structure | |
| CN103338516A (en) | Two-step positioning method of wireless sensor network based on total least squares | |
| CN104053129A (en) | Wireless sensor network indoor positioning method and device based on sparse RF fingerprint interpolations | |
| CN110456320A (en) | A kind of ULTRA-WIDEBAND RADAR personal identification method based on free space gait temporal aspect | |
| CN105243285A (en) | Big data health forecast system | |
| CN114038012A (en) | Fall detection method and system based on millimeter wave radar and machine learning | |
| CN103702282B (en) | A kind of multiple types multiple target passive type localization method based on migration compressed sensing | |
| CN112261718B (en) | Indoor positioning method | |
| CN110781961B (en) | Accurate behavior recognition method based on decision tree classification algorithm | |
| CN111141284A (en) | Intelligent building personnel thermal comfort level and thermal environment management system and method | |
| Santiprapan et al. | Development of an adaptive device-free human detection system for residential lighting load control | |
| CN113591760A (en) | Far-field multi-human-body gait monitoring method based on millimeter waves | |
| CN204085569U (en) | A kind of hot comfort instrument for measuring index based on Internet of Things and neural network | |
| CN110084986A (en) | A kind of circumference safety protection method and device | |
| CN113781728A (en) | Vibration sensing system and method based on group intelligent optimization | |
| Zheng et al. | Design of a Precision Agriculture Leakage Seeding System Based on Wireless Sensors. | |
| Li et al. | Device-free localization using enhanced channel selection and a distance-based elliptical model |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 510, No. 353, Tianmu Middle Road, Jing'an District, Shanghai, 200070 Applicant after: SHANGHAI HANYOU ELECTRONIC TECHNOLOGY Co.,Ltd. Applicant after: HUNAN INSTITUTE OF SCIENCE AND TECHNOLOGY Address before: 414000 Xueyuan Road, Jine East Road, Yueyang City, Hunan Province Applicant before: HUNAN INSTITUTE OF SCIENCE AND TECHNOLOGY Applicant before: SHANGHAI HANYOU ELECTRONIC TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |