CN109116298B - Positioning method, storage medium and positioning system - Google Patents
Positioning method, storage medium and positioning system Download PDFInfo
- Publication number
- CN109116298B CN109116298B CN201710481197.9A CN201710481197A CN109116298B CN 109116298 B CN109116298 B CN 109116298B CN 201710481197 A CN201710481197 A CN 201710481197A CN 109116298 B CN109116298 B CN 109116298B
- Authority
- CN
- China
- Prior art keywords
- positioning
- led
- wifi
- terminal
- grid point
- 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
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000012545 processing Methods 0.000 claims description 33
- 238000012549 training Methods 0.000 claims description 25
- 230000008569 process Effects 0.000 claims description 13
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000012706 support-vector machine Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 10
- 229910052704 radon Inorganic materials 0.000 claims description 6
- SYUHGPGVQRZVTB-UHFFFAOYSA-N radon atom Chemical compound [Rn] SYUHGPGVQRZVTB-UHFFFAOYSA-N 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000008901 benefit Effects 0.000 abstract description 10
- 230000004927 fusion Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000004807 localization Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 241000282994 Cervidae Species 0.000 description 1
- 206010052143 Ocular discomfort Diseases 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/0252—Radio frequency fingerprinting
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/12—Systems for determining distance or velocity not using reflection or reradiation using electromagnetic waves other than radio waves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S2205/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S2205/01—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations specially adapted for specific applications
- G01S2205/02—Indoor
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a positioning method, a storage medium and a positioning system. The positioning method comprises the following steps: according to a wireless local area network WiFi positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain the WiFi positioning position of the positioning terminal; according to a Light Emitting Diode (LED) positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain an LED positioning position of the positioning terminal; respectively acquiring weight values corresponding to the WiFi positioning position and the LED positioning position according to the WiFi positioning position and the LED positioning position; and obtaining the final positioning position of the positioning terminal according to the WiFi positioning position, the LED positioning position and the weight values corresponding to the two positioning positions. The invention combines the advantages of the two positioning methods, realizes the advantage complementation of different positioning methods, effectively combines WiFi positioning and visible light positioning, and improves the positioning precision and stability.
Description
Technical Field
The present invention relates to the field of positioning, and in particular, to a positioning method, a storage medium, and a positioning system.
Background
In recent years, indoor location services with more and more urgent demands are oriented, the development of indoor location technology is rapid, the indoor location service is a research hotspot in the mobile interconnection era, the indoor location service is gradually exerted in various industries, and certain influence is brought to daily life of people. However, compared with the outdoor environment, the indoor environment is limited by the positioning time, the positioning precision, the indoor complex environment and other conditions, and the positioning effect is not ideal in practical application.
At present, the common indoor positioning methods mainly comprise the following steps:
1. infrared positioning
The Infrared positioning is performed after specific Infrared rays (Infrared rays) emitted by an Infrared emitter received by an indoor optical sensor are positioned. The infrared outdoor positioning system Active Badge System developed by Cambridge university AT & T laboratories is referred to as a first generation indoor positioning system. The Ambiplex proposes in 2011 that the IR.Loc system performs positioning by measuring heat radiation, and the positioning accuracy in the range of 10m reaches 20-30 cm.
The implementation of the infrared indoor positioning system comprises two parts: an infrared transmitter and an infrared receiver. Typically, the infrared transmitter is a fixed node of the network and the infrared receiver is mounted on the object to be located as a mobile terminal. The infrared indoor positioning has the advantages of high positioning precision, sensitive response and low cost of a single device.
2. Bluetooth indoor positioning
And the Bluetooth indoor positioning is performed according to the signal intensity of the measurement terminal equipment through a fingerprint positioning algorithm. The iBeacon is a protocol technology specially used for Bluetooth positioning and formulated by apple corporation, the positioning precision is 2-3 m, shopping application Shopkick is used for distributing iBeacon in a market and is applied in actual life, and APP such as "deer seeking" and "widely-distributed easy go" in China also adopts the mode for positioning. The Bluetooth positioning technology has the advantages of high safety, low cost, low power consumption and small equipment volume, most mobile phone terminals are provided with Bluetooth modules at present, and the wide-range popularization and deployment implementation are easy.
3. Radio frequency identification positioning
Radio frequency identification (Radio Frequency Identification, RFID for short) positioning technology uses radio frequency signals to perform contactless two-way communication exchange data to achieve the purposes of identification and positioning. At present, typical RFID positioning systems are Cricket system developed by MIT Oxygen project, spoton system of Washington university, RADAR system of Microsoft corporation, etc. The RFID technology has large transmission range and low cost.
Although there are many mature positioning methods at present, each positioning method has significant unavoidable drawbacks, for example, the infrared positioning method is limited to line-of-sight positioning, attenuation of infrared information in air is large, and the infrared positioning method can only be used for short-distance positioning, and positioning accuracy is easily affected by other light sources; the Bluetooth indoor positioning method is easy to be interfered by external noise signals, has poor signal stability and has a small communication range; the radio frequency indoor positioning method has short acting distance, which is only tens of meters at most, and the radio frequency signal has no communication capability, and can not be used for indoor positioning only by using the radio frequency identification technology, and can be completed by combining with other auxiliary technologies.
Disclosure of Invention
The invention aims to solve the technical problem of providing a positioning method, a storage medium and a positioning system, which are used for solving the problem of low indoor positioning precision in the prior art.
In order to solve the above technical problems, in one aspect, the present invention provides a positioning method, including:
according to a wireless local area network WiFi positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain the WiFi positioning position of the positioning terminal;
according to a Light Emitting Diode (LED) positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain an LED positioning position of the positioning terminal;
respectively acquiring weight values corresponding to the WiFi positioning position and the LED positioning position according to the WiFi positioning position and the LED positioning position;
and obtaining the final positioning position of the positioning terminal according to the WiFi positioning position, the LED positioning position and the weight values corresponding to the two positioning positions.
Further, before positioning, dividing a positioning area into a plurality of grid points in advance, acquiring a WiFi weight value corresponding to each grid point based on WiFi positioning, and acquiring an LED weight value corresponding to each grid point based on LED positioning;
in the positioning process, taking a WiFi weight value corresponding to a lattice point closest to the WiFi positioning position as a weight value corresponding to the WiFi positioning position; and taking the LED weight value corresponding to the lattice point closest to the LED positioning position as the weight value corresponding to the LED positioning position.
Further, acquiring the corresponding WiFi weight value based on WiFi positioning at each lattice point specifically includes:
acquiring a WiFi fingerprint library according to the received signal strength indication RSSI data of set times acquired at each grid point;
acquiring a WiFi classifier for performing position prediction and positioning by using RSSI data according to the WiFi fingerprint library;
calculating a WiFi weight value w corresponding to each grid point based on WiFi positioning by using formulas (2) and (3) r1 ;
ε(x r (i))=||x r (i)-x r || 2 Formula (3)
Wherein argmin represents w obtained by the minimum of equation (2) r1 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at grid point R, R representing the grid point number, r=1.
Further, the method further comprises:
after the WiFi fingerprint library is obtained, dividing the WiFi fingerprint library into a training set and a verification set according to a set proportion;
and selecting a support vector machine algorithm SVM nonlinear classifier, and training by using a Python language to obtain the WiFi classifier.
Further, according to the WiFi classifier, the positioning terminal is subjected to prediction positioning, and the WiFi positioning position of the positioning terminal is obtained.
Further, obtaining the LED weight value corresponding to each grid point based on the LED positioning specifically includes:
According to the LED positioning data collected on each grid point, an LED fingerprint library is obtained;
according to the LED fingerprint library, an LED classifier for performing position prediction and positioning by utilizing LED positioning data is obtained;
calculating the corresponding LED weight value w based on LED positioning on each grid point by using the formula (3) (4) r2 ;
ε(x r (i))=||x r (i)-x r || 2 Formula (3)
Wherein argmin represents w obtained by the minimum of equation (2) r2 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at grid point R, R representing the grid point number, r=1.
Further, the method further comprises:
after the LED fingerprint library is obtained, dividing the LED fingerprint library into a training set and a verification set according to a set proportion;
and selecting a support vector machine algorithm SVM nonlinear classifier, and training by using Python language to obtain the LED classifier.
Further, the LED positioning data includes: and acquiring the course angle, the pitch angle and the roll angle of the LED positioning data and the position coordinates of one or more LED lamps shot by the equipment on an image.
Further, according to the LED classifier, the positioning terminal is subjected to prediction positioning, and the LED positioning position of the positioning terminal is obtained.
Further, the final positioning position of the positioning terminal is obtained by the formula (1):
wherein p represents the final positioning position of the positioning terminal; j=1, 2; f (f) 1 (x) Representing a predicted positioning position obtained based on WiFi positioning at a lattice point r; f (f) 2 (x) Representing a predicted positioning position obtained based on LED positioning at a grid point r; w (w) r1 Representing a weight value corresponding to the grid point r based on WiFi positioning; w (w) r2 The corresponding weight values are located based on the LEDs at the representing grid point r.
On the other hand, the invention also provides a method for acquiring the LED positioning signal, which comprises the following steps of
Shooting an image comprising the LED lamp by using the positioning terminal;
performing image processing, obtaining flicker frequency of each LED lamp in an image, and identifying the shot LED lamps according to the flicker frequency;
acquiring coordinates of the identified LED lamp in the image, and acquiring a course angle, a pitch angle and a roll angle of the positioning terminal;
and forming a positioning signal at the position grid point of the positioning terminal by the course angle, the pitch angle and the roll angle of the positioning terminal and the coordinates of the identified LED lamp in the image.
Further, image processing is performed to obtain flicker frequencies of each LED lamp in an image, and the method specifically comprises the following steps:
converting the color image into a gray scale image;
Sequentially performing image blurring processing and binarization processing;
separating out the graph corresponding to each LED lamp in the image, extracting the outline information of each graph, and finding out the center position;
and counting the interval between black and white stripes in each pattern contour through radon transformation, and calculating the flicker frequency of the LED corresponding to the pattern contour according to the interval.
In another aspect, the present invention also provides a storage medium storing a positioning program for performing positioning, the program including:
according to a wireless local area network WiFi positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain the WiFi positioning position of the positioning terminal;
according to a Light Emitting Diode (LED) positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain an LED positioning position of the positioning terminal;
respectively acquiring weight values corresponding to the WiFi positioning position and the LED positioning position according to the WiFi positioning position and the LED positioning position;
and obtaining the final positioning position of the positioning terminal according to the WiFi positioning position, the LED positioning position and the weight values corresponding to the two positioning positions.
Further, before positioning, dividing a positioning area into a plurality of grid points in advance, acquiring a WiFi weight value corresponding to each grid point based on WiFi positioning, and acquiring an LED weight value corresponding to each grid point based on LED positioning;
In the positioning process, taking a WiFi weight value corresponding to a lattice point closest to the WiFi positioning position as a weight value corresponding to the WiFi positioning position; and taking the LED weight value corresponding to the lattice point closest to the LED positioning position as the weight value corresponding to the LED positioning position.
Further, acquiring the corresponding WiFi weight value based on WiFi positioning at each lattice point specifically includes:
acquiring a WiFi fingerprint library according to the received signal strength indication RSSI data of set times acquired at each grid point;
acquiring a WiFi classifier for performing position prediction and positioning by using RSSI data according to the WiFi fingerprint library;
calculating a WiFi weight value w corresponding to each grid point based on WiFi positioning by using formulas (2) and (3) r1 ;
ε(x r (i))=||x r (i)-x r || 2 Formula (3)
Wherein argmin represents w obtained by the minimum of equation (2) r1 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at grid point R, R representing the grid point number, r=1.
Further, the program includes:
after the WiFi fingerprint library is obtained, dividing the WiFi fingerprint library into a training set and a verification set according to a set proportion;
and selecting a support vector machine algorithm SVM nonlinear classifier, and training by using a Python language to obtain the WiFi classifier.
Further, according to the WiFi classifier, the positioning terminal is subjected to prediction positioning, and the WiFi positioning position of the positioning terminal is obtained.
Further, obtaining the LED weight value corresponding to each grid point based on the LED positioning specifically includes:
according to the LED positioning data collected on each grid point, an LED fingerprint library is obtained;
according to the LED fingerprint library, an LED classifier for performing position prediction and positioning by utilizing LED positioning data is obtained;
calculating the corresponding LED weight value w based on LED positioning on each grid point by using the formula (3) (4) r2 ;
ε(x r (i))=||x r (i)-x r || 2 Formula (3)
Wherein argmin represents w obtained by the minimum of equation (2) r2 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at grid point R, R representing the grid point number, r=1.
Further, the program further includes:
after the LED fingerprint library is obtained, dividing the LED fingerprint library into a training set and a verification set according to a set proportion;
and selecting a support vector machine algorithm SVM nonlinear classifier, and training by using Python language to obtain the LED classifier.
Further, the LED positioning data includes: and acquiring the course angle, the pitch angle and the roll angle of the LED positioning data and the position coordinates of one or more LED lamps shot by the equipment on an image.
Further, according to the LED classifier, the positioning terminal is subjected to prediction positioning, and the LED positioning position of the positioning terminal is obtained.
Further, the final positioning position of the positioning terminal is obtained by the formula (1):
wherein p represents the final positioning position of the positioning terminal; j=1, 2; f (f) 1 (x) Representing a predicted positioning position obtained based on WiFi positioning at a lattice point r; f (f) 2 (x) Representing a predicted positioning position obtained based on LED positioning at a grid point r; w (w) r1 Representing a weight value corresponding to the grid point r based on WiFi positioning; w (w) r2 The corresponding weight values are located based on the LEDs at the representing grid point r.
In another aspect, the present invention also provides a storage medium storing a program for acquiring an LED positioning signal, the program comprising:
shooting an image comprising the LED lamp by using the positioning terminal;
performing image processing, obtaining flicker frequency of each LED lamp in an image, and identifying the shot LED lamps according to the flicker frequency;
acquiring coordinates of the identified LED lamp in the image, and acquiring a course angle, a pitch angle and a roll angle of the positioning terminal;
and forming a positioning signal at the position grid point of the positioning terminal by the course angle, the pitch angle and the roll angle of the positioning terminal and the coordinates of the identified LED lamp in the image.
Further, image processing is performed to obtain flicker frequencies of each LED lamp in an image, and the method specifically comprises the following steps:
converting the color image into a gray scale image;
sequentially performing image blurring processing and binarization processing;
separating out the graph corresponding to each LED lamp in the image, extracting the outline information of each graph, and finding out the center position;
and counting the interval between black and white stripes in each pattern contour through radon transformation, and calculating the flicker frequency of the LED corresponding to the pattern contour according to the interval.
In still another aspect, the present invention further provides a positioning system, including a plurality of wireless routers, a plurality of LED lamps, and a positioning terminal, a monitoring terminal, and a server, which are disposed in a positioning area:
the positioning terminal acquires WiFi positioning signals and LED positioning signals of the position grid points of the positioning terminal and sends the WiFi positioning signals and the LED positioning signals to the server;
the server locates the locating terminal according to the WiFi locating signal and the LED locating signal and sends locating information to the monitoring terminal;
and the monitoring terminal receives the positioning information and displays the position of the positioning terminal.
Further, the server includes a storage medium storing a positioning program for fusion.
Further, the positioning terminal includes the above-described storage medium storing the program for image processing.
Further, the light of the LEDs is modulated into square wave signals, and the modulation frequencies of the LED lamps are different.
The invention has the following beneficial effects:
the invention provides a fusion positioning method and system based on WiFi and visible light, which combine the advantages of the two positioning methods and realize the advantage complementation of different positioning methods, thereby effectively combining WiFi positioning and visible light positioning and improving the positioning precision and stability.
Drawings
Fig. 1 is an effect diagram of an LED lamp actually photographed in an embodiment of the present invention;
FIG. 2 is an effect diagram of an LED lamp for shooting different frequencies in an embodiment of the invention;
FIG. 3 is a schematic diagram of a positioning system according to an embodiment of the present invention;
fig. 4 is a flow chart of positioning in an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Example 1
The embodiment of the invention provides a dynamic fingerprint fusion positioning method based on WiFi and visible light.
Before positioning, a classifier for performing WiFi positioning and LED positioning is respectively constructed, and then a system for performing fusion positioning is constructed, and the process is called an off-line stage in the embodiment. The fusion positioning process is performed by using the constructed system, and is called an 'online stage'.
Therefore, the embodiment includes two major parts, the first part is to construct a WiFi classifier and an LED classifier separately, and a fusion positioning system to fuse the two positioning methods together. And the second part is to use the constructed WiFi classifier, the built LED classifier and the fusion positioning system to perform specific positioning.
First, the construction steps of the WiFi classifier are described:
(1) Establishing WiFi fingerprint library
Four wireless routers are deployed in a room (location area) and are placed at different corners respectively. In the "off-line phase", the room is first divided into different grid points, the room is first divided into 6*8 =48 grid points, in this example the grid point size is 1m×1m.
And then collecting WiFi RSSI data at different grid points, holding the mobile phone (positioning terminal) to stand in a certain grid point, controlling the mobile phone to start collecting data, marking corresponding labels (namely grid point numbers: 1,2 and …), and storing the labels in a file. Each of the data sets includes RSSI information of 4 routers, and thus a WiFi fingerprint library of 48×100×4 is obtained.
(2) Structure classifier
After the WiFi fingerprint library is obtained, training can be performed, and a classifier is constructed. We choose the Python language to process, based on the powerful machine learning library Scikit-Learn in Python, the fingerprint library is first divided into training set (track set) and Validation set (Validation set) according to 9:1 to avoid overfitting. Since the features of the model are not linearly separable, a nonlinear classifier is chosen, here we choose a support vector machine algorithm (SVM, support Vector Machine) model to train to get a WiFi classifier with WiHi localization. Because the data volume is relatively small, training can be completed within tens of seconds.
After the WiFi classifier is obtained, the RSSI data newly collected each time are input into the WiFi classifier, a predicted positioning result of the RSSI data collecting position can be obtained, and the target position can be positioned in a specific lattice point by the positioning result.
Next, the construction steps of the LED classifier are described:
(1) Setting LED lamp
Setting a plurality of LED lamps in a positioning area, and recording the positions of the LED lamps; the LED lamp light is modulated into square wave signals (square wave higher than 100Hz, human eyes cannot perceive flicker, visual discomfort is not caused, brightness is properly reduced, the square wave signals are easy to process and high in anti-interference capability), the LED lamp light is usually modulated into 200Hz-4000Hz, and the LED lamps are modulated into different frequencies.
It should be noted that, because the positioning terminal needs to be used for photographing to collect the position information of the LED, and image processing is needed after photographing, the larger the light emitting area of the LED is, the better the recognition effect is, so the circular panel lamp (if the lamp is a common lamp, the light emitting area can be enlarged by adding a lamp shade) is selected in the scheme.
In addition, in order to facilitate image processing, the positioning terminal is provided with a camera exposure time (shutter) (the exposure time can be adjusted by a common mobile phone camera), so that the LED lamp in the shot image presents stripes with alternate brightness and darkness; the rest of the object will appear as a black background on the image (due to the shorter exposure time, the effect of non-luminous objects such as ceilings, furniture, etc. forming a "black-painted piece" in the image), which is more advantageous for image processing. As shown in fig. 1.
(2) Establishing fingerprint library
The classifier is constructed by extracting features firstly, and in the WiHi positioning link, the features are directly available, namely the RSSI value. In LED positioning, the amount of photographed picture data is large, and the information really useful is small, so that the picture needs to be preprocessed, the features are extracted, and the fingerprint library stores the features instead of the whole picture.
The frequencies of the LED lamps are different, and the stripe pitch (width corresponds to the modulated frequency) is different in the photographed image, as shown in fig. 2, so that the frequency corresponding to the lamp image can be identified by image processing, which is equal to the identification of the LED lamp. The position coordinates of each LED lamp are fixed, so that the imaging positions of different LED lamps in the image can be the characteristic of positioning.
The process of LED lamp identification through image processing is as follows:
1. the photographed color picture is converted into a gray image, so that the processing speed is improved and the interference can be removed.
2. The image is subjected to fuzzy processing (improving the LED separation accuracy) and binarization processing, so that each LED lamp can be conveniently separated; the binarization process is to set a global threshold T, and divide the image data into two parts by T: a group of pixels greater than T and a group of pixels less than T. The pixel values of the pixel groups larger than T are set to white or black, and the pixel values of the pixel groups smaller than T are set to black or white.
3. And separating each LED lamp, extracting contour information of each LED lamp, and finding out the central position (the position of a pixel point in an image) of each LED. In each contour, the interval between black and white stripes can be counted through radon transformation, so that the flicker frequency of the LED is calculated, and the LED lamp is identified according to the flicker frequency.
Because the camera has a limited visual angle, the shooting range is limited, and a plurality of LEDs are difficult to shoot at the same time, the direction cannot be positioned, and if the direction cannot be determined, the positioning accuracy is greatly reduced. The angle of the mobile phone when taking a picture also affects the imaging position of the LED in the image. In order to improve the positioning accuracy, the electronic compass and the gyroscope of the smart phone can be used for obtaining the three-dimensional inclination angles of the smart phone, namely, a heading angle (Yaw), a Pitch angle (Pitch) and a Roll angle (Roll). The three-dimensional angle is used as another characteristic of LED positioning, so that the positioning accuracy can be improved. In smartphones (Android, IOS), APIs of three-dimensional tilt angles are all opened, and thus, three-dimensional tilt angle features can be easily obtained.
Thus, an LED fingerprint library was constructed, and each feature contained the information shown in table 1:
TABLE 1
Yaw | Pitch | Roll | X1 | Y1 | X2 | Y2 | X3 | Y3 | X4 | Y4 |
Wherein the first three features represent three-dimensional tilt angles, xi and Yi represent imaging positions of the LED lamp with the reference number i in the image (i.e. pixel coordinates in the image are positive numbers), respectively, and if the LED with the reference number i is not present in the image, xi=yi= -1.
For example, when yaw=10.0, pitch=20.0, roll=30.0, only LED No. 3 appears in the image, and the position of LED No. 3 in the image is (500, 800). The characterization is as shown in table 2:
TABLE 2
Yaw | Pitch | Roll | X1 | Y1 | X2 | Y2 | X3 | Y3 | X4 | Y4 |
10.0 | 20.0 | 30.0 | -1 | -1 | -1 | -1 | 500 | 800 | -1 | -1 |
As with the WiHi positioning, the fingerprint library is constructed by collecting data (LED positioning data) in each grid point, extracting information in the picture according to the characteristic format shown above, obtaining a three-dimensional inclination angle, and storing the three-dimensional inclination angle, wherein after each grid point is collected, the LED fingerprint library can be formed. Unlike WiFi positioning, only one data acquisition is required at each location, as the data obtained by the camera is relatively stable.
(3) Construction LED classifier
As with the WiHi localization, training is required to construct the classifier after the fingerprint library is obtained. The method is the same as the WiHi positioning, the LED positioning selects an SVM classifier as well, but the feature dimensions are different (the WiHi positioning 4-dimensional features and the LED positioning 11-dimensional features). And solving the mapping relation between the LED positioning data and the predicted position positioning through a Regression (Regression) algorithm in machine learning, and obtaining the LED classifier.
In actual positioning, the mobile phone automatically takes a picture, recognizes the LED according to the image processing method, and then acquires a three-dimensional inclination angle to jointly form 11-dimensional features. The LED classifier constructed in (3) can be input and a predicted positioning result based on the LED positioning can be output.
LED positioning is directly dependent on the position of the LED in the image, but the LED is sometimes invisible, i.e. the mobile phone camera cannot shoot the LED, so that the positioning result cannot be obtained, and at this time, more dependence on the WiHi positioning is needed.
Finally, the procedure of combining the two positioning methods is as follows:
first, a fusion index ε (x) r (i)):
ε(x r (i))=||x r (i)-x r || 2 (1)
ε(x r (i) A) the predicted value coordinate x representing the ith sample taken at grid point r r (i) With the true coordinate x r Square error of (c). Wherein the predicted value coordinate x r (i) From the above-obtained classifier, the true coordinate x r Then it is obtained from the actual measurement. For example, in the actual positioning, the coordinates of the lattice point predicted by the system are (1, 2), and the coordinates of the true lattice point are (1, 1), thenTherefore, if the index is small, that is, the closer the predicted position and the real position are, the better the positioning accuracy of the system is represented.
Secondly, calculating a corresponding weight w by fusion indexes rj :
Equation (2) is a weight calculation equation, argmin means w obtained by minimizing the above equation rj Values. Wherein N is the number of samples collected at grid point R, R represents the grid point position, j represents the fingerprint library, r=1,. -%, R; j=1, 2; n refers to the number of samples collected at grid point r; i=1, 2..n.
From the fingerprint library data, the weight coefficient of the fingerprint library j for the lattice point r can be calculated. Specifically, in the online lower stage, assuming that we have acquired a WiFi positioning fingerprint library and an LED positioning fingerprint library, we now take 80% of the data in the fingerprint library out for classifier training, and the remaining 20% of the data are used to calculate weight values.
For example, when the classifier is trained and one sample of the remaining 20% of data is used to predict the lattice point, the fusion index of (1) is used to calculate the value as x1 = (1, 1) and x = (0.5 ) assuming that the predicted lattice point coordinates are x1 = (1, 1) and the true lattice point coordinates are x = (0.5 )We are now optimizing this positioning result with the weighting formula of equation (2). That is, we want ε (w x 1) = ||w x 1-x||w 2 W is more than or equal to 0 and less than or equal to 1. In this example, w=0.5, i.e. when this value is taken, we can minimize ε (w×1) to 0.
In this way we can find a weight matrix.
w 11 The optimized weight, w, of the WiFI positioning of the lattice point 1 is 12 The optimal weight for LED positioning for grid point 1 is referred to. Namely, each grid point can calculate the corresponding optimization weight of WiFi positioning and the corresponding optimization weight of LED positioning through the method.
After the system is built, a specific positioning service stage is entered,
firstly, a positioning terminal collects data of the position of the positioning terminal;
then, matching the data of the fingerprint library according to the similarity;
finally, according to the data of the fingerprint library, calculating by using a formula (3) to obtain a positioning result:
f j (x) The data collected on the finger line matches the most similar lattice point r coordinate obtained by the fingerprint database j, and then the weight w of the corresponding fingerprint at the corresponding position obtained under the line is multiplied rj The final positioning position p is obtained.
For example, the result of the positioning prediction by the WiFi classifier is (1, 2), the result of the positioning prediction by the LED classifier is (2, 1), then according to the similarity matching, the lattice point in the fingerprint library most similar to the prediction result is found, and the optimization weight of the lattice point is found in the weight matrix. Specifically, if (1, 2) of WiFi is closest to WiFi fingerprint library lattice point 1, then weight w is taken 11 The result of the LED positioning prediction is closest to the lattice point 2 in the LED fingerprint library, and then the weight w is taken 22 Such that the final output result p=w 11 ×(1,2)+w 22 ×(2,1)。
Therefore, according to the scheme of the embodiment, the positioning result is dynamically adjusted according to the weight according to the data measured in the positioning process, so that the performance of the whole system is improved; the advantages of the two positioning methods are combined, and the complementary advantages of different positioning methods are realized, so that WiFi positioning and visible light positioning are effectively combined, and the positioning accuracy and stability are improved.
Example two
As shown in fig. 3, the embodiment of the invention further relates to a positioning system comprising a wireless local area network and visible light communication. The positioning system comprises a positioning end, a server end and a monitoring end, wherein the positioning end is carried by a monitored target and is used for positioning the position of the target and sending the position information to the server end; the server calculates a positioning result, realizes positioning fusion and sends the positioning result to the monitoring end; the monitoring end is carried by a monitor, and can view the position information of the monitored target in real time. The communication system comprises a wireless local area network and a visible light communication part, wherein the wireless local area network comprises a plurality of Access Points (APs), the APs are used as a sending end to send out WiFi signals, and a mobile phone is used as a receiving end to carry out wireless positioning by utilizing the signal intensity. The visible light communication system comprises a plurality of LED lamps with different frequencies, and the mobile phone identifies the different LED lamps through visible light communication to position. And finally, fusing the results of the two positioning systems by using the positioning method of the first embodiment to obtain the final positioning.
The positioning system of the embodiment can also be used for multi-target positioning and monitoring, namely, one monitoring terminal mobile phone can monitor a plurality of different positioning terminals.
The positioning process by the system is shown in fig. 4, and includes:
step 401, the positioning terminal firstly collects WiFi RSSI and LED visible light signals, the LED visible light signals are images shot by a camera, after image processing, frequency and position information contained in the LED images are extracted, and LED positioning information is formed; the positioning terminal then sends the WiFi positioning information and the LED positioning information to a server,
step 402, a server calculates a final positioning result, and predicts and positions a positioning terminal according to a wireless local area network WiFi positioning signal sent by the positioning terminal to obtain a WiFi positioning position of the positioning terminal;
according to a Light Emitting Diode (LED) positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain an LED positioning position of the positioning terminal;
respectively acquiring weight values corresponding to the WiFi positioning position and the LED positioning position according to the WiFi positioning position and the LED positioning position;
and obtaining the final positioning position of the positioning terminal according to the WiFi positioning position, the LED positioning position and the weight values corresponding to the two positioning positions.
And step 403, the server sends the positioning result to the monitoring terminal, and displays the position of the positioning terminal to realize positioning.
The embodiment also relates to a storage medium arranged at the server side, which can be a server or a data storage, calling and processing device arranged on the server, and the storage medium is used for establishing a WiFi fingerprint library, establishing a WiFi classifier and carrying out WiFi positioning, establishing an LED fingerprint library, an LED classifier and carrying out LED positioning, and is used for establishing a weight matrix, fusing the WiFi positioning and the LED positioning and determining a final positioning result. In particular, the method comprises the steps of,
a storage medium storing a positioning program for performing positioning, the program comprising:
according to a wireless local area network WiFi positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain the WiFi positioning position of the positioning terminal;
according to a Light Emitting Diode (LED) positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain an LED positioning position of the positioning terminal;
respectively acquiring weight values corresponding to the WiFi positioning position and the LED positioning position according to the WiFi positioning position and the LED positioning position;
And obtaining the final positioning position of the positioning terminal according to the WiFi positioning position, the LED positioning position and the weight values corresponding to the two positioning positions.
Before positioning, dividing a positioning area into a plurality of grid points in advance, acquiring a WiFi weight value corresponding to each grid point based on WiFi positioning, and acquiring an LED weight value corresponding to each grid point based on LED positioning;
in the positioning process, taking a WiFi weight value corresponding to a lattice point closest to the WiFi positioning position as a weight value corresponding to the WiFi positioning position; and taking the LED weight value corresponding to the lattice point closest to the LED positioning position as the weight value corresponding to the LED positioning position.
The method for acquiring the WiFi weight value corresponding to each lattice point based on WiFi positioning specifically comprises the following steps:
acquiring a WiFi fingerprint library according to the received signal strength indication RSSI data of set times acquired at each grid point;
acquiring a WiFi classifier for performing position prediction and positioning by using RSSI data according to the WiFi fingerprint library;
calculating a WiFi weight value w corresponding to each grid point based on WiFi positioning by using formulas (2) and (3) r1 ;
ε(x r (i))=||x r (i)-x r || 2 Formula (3)
Wherein,argmin represents the least taken w of equation (2) r1 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at grid point R, R representing the grid point number, r=1.
Wherein the method further comprises:
after the WiFi fingerprint library is obtained, dividing the WiFi fingerprint library into a training set and a verification set according to a set proportion;
and selecting a support vector machine algorithm SVM nonlinear classifier, and training by using a Python language to obtain the WiFi classifier.
And according to the WiFi classifier, predicting and positioning the positioning terminal to obtain the WiFi positioning position of the positioning terminal.
The method for acquiring the LED weight value corresponding to each grid point based on LED positioning specifically comprises the following steps:
according to the LED positioning data collected on each grid point, an LED fingerprint library is obtained;
according to the LED fingerprint library, an LED classifier for performing position prediction and positioning by utilizing LED positioning data is obtained;
calculating the corresponding LED weight value w based on LED positioning on each grid point by using the formula (3) (4) r2 ;
ε(x r (i))=||x r (i)-x r || 2 Formula (3)
Wherein argmin represents w obtained by the minimum of equation (2) r2 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at grid point R, R representing the grid point number, r=1.
Wherein the method further comprises:
after the LED fingerprint library is obtained, dividing the LED fingerprint library into a training set and a verification set according to a set proportion;
and selecting a support vector machine algorithm SVM nonlinear classifier, and training by using Python language to obtain the LED classifier.
Wherein, the LED positioning data includes: and acquiring the course angle, the pitch angle and the roll angle of the LED positioning data and the position coordinates of one or more LED lamps shot by the equipment on an image.
And according to the LED classifier, predicting and positioning the positioning terminal to obtain the LED positioning position of the positioning terminal.
The final positioning position of the positioning terminal is obtained through a formula (1):
wherein p represents the final positioning position of the positioning terminal; j=1, 2; f (f) 1 (x) Representing a predicted positioning position obtained based on WiFi positioning at a lattice point r; f (f) 2 (x) Representing a predicted positioning position obtained based on LED positioning at a grid point r; w (w) r1 Representing a weight value corresponding to the grid point r based on WiFi positioning; w (w) r2 The corresponding weight values are located based on the LEDs at the representing grid point r.
The embodiment of the invention also relates to a storage medium which is positioned at the side of the positioning terminal, and can be the positioning terminal or a hardware device for storing and processing data of the positioning terminal. The storage medium stores a program for acquiring an LED positioning signal, the program comprising:
shooting an image comprising the LED lamp by using the positioning terminal;
performing image processing, obtaining flicker frequency of each LED lamp in an image, and identifying the shot LED lamps according to the flicker frequency;
acquiring coordinates of the identified LED lamp in the image, and acquiring a course angle, a pitch angle and a roll angle of the positioning terminal;
and forming a positioning signal at the position grid point of the positioning terminal by the course angle, the pitch angle and the roll angle of the positioning terminal and the coordinates of the identified LED lamp in the image.
In the above steps, image processing is performed to obtain the flicker frequency of each LED lamp in the image, which specifically includes:
converting the color image into a gray scale image;
sequentially performing image blurring processing and binarization processing;
separating out the graph corresponding to each LED lamp in the image, extracting the outline information of each graph, and finding out the center position;
and counting the interval between black and white stripes in each pattern contour through radon transformation, and calculating the flicker frequency of the LED corresponding to the pattern contour according to the interval.
The invention provides a fusion positioning method and system based on WiFi and visible light, which combine the advantages of the two positioning methods and realize the advantage complementation of different positioning methods, thereby effectively combining WiFi positioning and visible light positioning and improving the positioning precision and stability.
Although the preferred embodiments of the present invention have been disclosed for illustrative purposes, those skilled in the art will appreciate that various modifications, additions and substitutions are possible, and accordingly the scope of the invention is not limited to the embodiments described above.
Claims (23)
1. A positioning method, comprising:
according to a wireless local area network WiFi positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain the WiFi positioning position of the positioning terminal;
according to a Light Emitting Diode (LED) positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain an LED positioning position of the positioning terminal;
respectively acquiring weight values corresponding to the WiFi positioning position and the LED positioning position according to the WiFi positioning position and the LED positioning position;
obtaining a final positioning position of the positioning terminal according to the WiFi positioning position, the LED positioning position and the weight values corresponding to the two positioning positions;
Before positioning, dividing a positioning area into a plurality of grid points in advance, acquiring a WiFi weight value corresponding to each grid point based on WiFi positioning, and acquiring an LED weight value corresponding to each grid point based on LED positioning;
in the positioning process, taking a WiFi weight value corresponding to a lattice point closest to the WiFi positioning position as a weight value corresponding to the WiFi positioning position; and taking the LED weight value corresponding to the lattice point closest to the LED positioning position as the weight value corresponding to the LED positioning position.
2. The positioning method of claim 1, wherein obtaining a WiFi weight value corresponding to each lattice point based on WiFi positioning specifically comprises:
acquiring a WiFi fingerprint library according to the received signal strength indication RSSI data of set times acquired at each grid point;
acquiring a WiFi classifier for performing position prediction and positioning by using RSSI data according to the WiFi fingerprint library;
calculating a WiFi weight value w corresponding to each grid point based on WiFi positioning by using formulas (2) and (3) r1 ;
ε(x r (i))= ||x r (i)-x r || 2 Formula (3)
Wherein argmin represents w obtained by the minimum of equation (2) r1 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at bin R, R representing bin number, r=1, …, R.
3. The positioning method of claim 2, wherein the method further comprises:
after the WiFi fingerprint library is obtained, dividing the WiFi fingerprint library into a training set and a verification set according to a set proportion;
and selecting a support vector machine algorithm SVM nonlinear classifier, and training by using a Python language to obtain the WiFi classifier.
4. The positioning method according to claim 2 or 3, wherein the positioning terminal is predicted and positioned according to the WiFi classifier to obtain a WiFi positioning position of the positioning terminal.
5. The positioning method according to claim 1, wherein obtaining the LED weight value corresponding to each grid point based on LED positioning specifically comprises:
according to the LED positioning data collected on each grid point, an LED fingerprint library is obtained;
according to the LED fingerprint library, an LED classifier for performing position prediction and positioning by utilizing LED positioning data is obtained;
calculating the corresponding LED weight value w based on LED positioning on each grid point by using the formula (3) (4) r2 ;
ε(x r (i))= ||x r (i)-x r || 2 Formula (3)
Wherein argmin represents w obtained at minimum in the formula (4) r2 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at bin R, R representing bin number, r=1, …, R.
6. The positioning method of claim 5, wherein the method further comprises:
after the LED fingerprint library is obtained, dividing the LED fingerprint library into a training set and a verification set according to a set proportion;
and selecting a support vector machine algorithm SVM nonlinear classifier, and training by using Python language to obtain the LED classifier.
7. The positioning method of claim 5, wherein the LED positioning data comprises: and acquiring the course angle, the pitch angle and the roll angle of the LED positioning data and the position coordinates of one or more LED lamps shot by the equipment on an image.
8. The positioning method according to claim 5, 6 or 7, wherein the positioning terminal is predicted and positioned according to the LED classifier to obtain the LED positioning position of the positioning terminal.
9. The positioning method according to claim 2 or 5, wherein the final positioning position of the positioning terminal is obtained by the formula (1):
wherein p represents the final positioning position of the positioning terminal; j=1, 2; f (f) 1 (x) Representing a predicted positioning position obtained based on WiFi positioning at a lattice point r; f (f) 2 (x) Representing a predicted positioning position obtained based on LED positioning at a grid point r; w (w) r1 Representing a weight value corresponding to the grid point r based on WiFi positioning; w (w) r2 The corresponding weight values are located based on the LEDs at the representing grid point r.
10. The method for acquiring the LED positioning signal is characterized by comprising the following steps of:
shooting an image comprising the LED lamp by using the positioning terminal;
performing image processing, obtaining flicker frequency of each LED lamp in an image, and identifying the shot LED lamps according to the flicker frequency;
acquiring coordinates of the identified LED lamp in the image, and acquiring a course angle, a pitch angle and a roll angle of the positioning terminal;
forming a positioning signal at the position grid point of the positioning terminal by the course angle, the pitch angle and the roll angle of the positioning terminal and the coordinates of the identified LED lamp in the image;
the method for processing the image comprises the steps of performing image processing to obtain the flicker frequency of each LED lamp in the image, and specifically comprises the following steps:
converting the color image into a gray scale image;
sequentially performing image blurring processing and binarization processing;
separating out the graph corresponding to each LED lamp in the image, extracting the outline information of each graph, and finding out the center position;
And counting the interval between black and white stripes in each pattern contour through radon transformation, and calculating the flicker frequency of the LED corresponding to the pattern contour according to the interval.
11. A storage medium storing a positioning program for performing positioning, the program comprising:
according to a wireless local area network WiFi positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain the WiFi positioning position of the positioning terminal;
according to a Light Emitting Diode (LED) positioning signal sent by a positioning terminal, predicting and positioning the positioning terminal to obtain an LED positioning position of the positioning terminal;
respectively acquiring weight values corresponding to the WiFi positioning position and the LED positioning position according to the WiFi positioning position and the LED positioning position;
obtaining a final positioning position of the positioning terminal according to the WiFi positioning position, the LED positioning position and the weight values corresponding to the two positioning positions;
before positioning, dividing a positioning area into a plurality of grid points in advance, acquiring a WiFi weight value corresponding to each grid point based on WiFi positioning, and acquiring an LED weight value corresponding to each grid point based on LED positioning;
In the positioning process, taking a WiFi weight value corresponding to a lattice point closest to the WiFi positioning position as a weight value corresponding to the WiFi positioning position; and taking the LED weight value corresponding to the lattice point closest to the LED positioning position as the weight value corresponding to the LED positioning position.
12. The storage medium of claim 11, wherein obtaining a WiFi weight value for each grid point based on WiFi positioning, specifically comprises:
acquiring a WiFi fingerprint library according to the received signal strength indication RSSI data of set times acquired at each grid point;
acquiring a WiFi classifier for performing position prediction and positioning by using RSSI data according to the WiFi fingerprint library;
calculating a WiFi weight value w corresponding to each grid point based on WiFi positioning by using formulas (2) and (3) r1 ;
ε(x r (i))= ||x r (i)-x r || 2 Formula (3)
Wherein argmin represents w obtained by the minimum of equation (2) r1 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at bin R, R representing bin number, r=1, …, R.
13. The storage medium of claim 12, wherein the program comprises:
after the WiFi fingerprint library is obtained, dividing the WiFi fingerprint library into a training set and a verification set according to a set proportion;
And selecting a support vector machine algorithm SVM nonlinear classifier, and training by using a Python language to obtain the WiFi classifier.
14. The storage medium of claim 12 or 13, wherein the positioning terminal is predicted to be positioned according to the WiFi classifier to obtain a WiFi positioning location of the positioning terminal.
15. The storage medium of claim 11, wherein obtaining the LED weight value for each grid point based on the LED location, comprises:
according to the LED positioning data collected on each grid point, an LED fingerprint library is obtained;
according to the LED fingerprint library, an LED classifier for performing position prediction and positioning by utilizing LED positioning data is obtained;
calculating the corresponding LED weight value w based on LED positioning on each grid point by using the formula (3) (4) r2 ;
ε(x r (i))= ||x r (i)-x r || 2 Formula (3)
Wherein argmin represents w obtained at minimum in the formula (4) r2 A value; epsilon (x) r (i) A) the predicted positioning coordinates x representing the ith acquisition data at grid point r r (i) With the true position coordinate x r Square error of (a); n is the number of samples taken at bin R, R representing bin number, r=1, …, R.
16. The storage medium of claim 15, wherein the program further comprises:
after the LED fingerprint library is obtained, dividing the LED fingerprint library into a training set and a verification set according to a set proportion;
And selecting a support vector machine algorithm SVM nonlinear classifier, and training by using Python language to obtain the LED classifier.
17. A storage medium as defined in claim 16, wherein the LED positioning data comprises: and acquiring the course angle, the pitch angle and the roll angle of the LED positioning data and the position coordinates of one or more LED lamps shot by the equipment on an image.
18. A storage medium as claimed in claim 15, 16 or 17, wherein the positioning terminal is predictively positioned according to the LED classifier to obtain the LED positioning position of the positioning terminal.
19. The storage medium of claim 12 or 15, wherein the final positioning position of the positioning terminal is obtained by formula (1):
wherein p represents the final positioning position of the positioning terminal; j=1, 2; f (f) 1 (x) Representing a predicted positioning position obtained based on WiFi positioning at a lattice point r; f (f) 2 (x) Representing a predicted positioning position obtained based on LED positioning at a grid point r; w (w) r1 Representing a weight value corresponding to the grid point r based on WiFi positioning; w (w) r2 The corresponding weight values are located based on the LEDs at the representing grid point r.
20. A storage medium storing a program for acquiring an LED positioning signal, the program comprising:
Shooting an image comprising the LED lamp by using the positioning terminal;
performing image processing, obtaining flicker frequency of each LED lamp in an image, and identifying the shot LED lamps according to the flicker frequency;
acquiring coordinates of the identified LED lamp in the image, and acquiring a course angle, a pitch angle and a roll angle of the positioning terminal;
forming a positioning signal at the position grid point of the positioning terminal by the course angle, the pitch angle and the roll angle of the positioning terminal and the coordinates of the identified LED lamp in the image;
the image processing is performed to obtain the flicker frequency of each LED lamp in the image, and the method specifically comprises the following steps:
converting the color image into a gray scale image;
sequentially performing image blurring processing and binarization processing;
separating out the graph corresponding to each LED lamp in the image, extracting the outline information of each graph, and finding out the center position;
and counting the interval between black and white stripes in each pattern contour through radon transformation, and calculating the flicker frequency of the LED corresponding to the pattern contour according to the interval.
21. A positioning system comprising a plurality of wireless routers, a plurality of LED lamps, and a positioning terminal, a monitoring terminal and a server disposed within a positioning area:
The positioning terminal acquires WiFi positioning signals and LED positioning signals of the position grid points of the positioning terminal and sends the WiFi positioning signals and the LED positioning signals to the server;
the server locates the locating terminal according to the WiFi locating signal and the LED locating signal and sends locating information to the monitoring terminal; the server comprising the storage medium of any one of claims 11 to 19;
and the monitoring terminal receives the positioning information and displays the position of the positioning terminal.
22. The positioning system of claim 21 wherein the positioning terminal comprises the storage medium of claim 20.
23. The positioning system of claim 21 wherein the light of the LEDs is modulated as a square wave signal, the modulation frequency of each LED lamp being different.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710481197.9A CN109116298B (en) | 2017-06-22 | 2017-06-22 | Positioning method, storage medium and positioning system |
PCT/CN2018/092439 WO2018233692A1 (en) | 2017-06-22 | 2018-06-22 | Positioning method, storage medium, and positioning system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710481197.9A CN109116298B (en) | 2017-06-22 | 2017-06-22 | Positioning method, storage medium and positioning system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109116298A CN109116298A (en) | 2019-01-01 |
CN109116298B true CN109116298B (en) | 2023-12-22 |
Family
ID=64732611
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710481197.9A Active CN109116298B (en) | 2017-06-22 | 2017-06-22 | Positioning method, storage medium and positioning system |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109116298B (en) |
WO (1) | WO2018233692A1 (en) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109889981B (en) * | 2019-03-08 | 2020-11-06 | 中南大学 | Positioning method and system based on binary classification technology |
CN111103579A (en) * | 2020-01-15 | 2020-05-05 | 长安大学 | Visible light indoor positioning system and method based on mobile phone camera |
CN111356082B (en) * | 2020-03-10 | 2021-06-08 | 西安电子科技大学 | Indoor mobile terminal positioning method based on WIFI and visible light communication |
CN113494910B (en) * | 2020-04-02 | 2024-06-18 | 广州汽车集团股份有限公司 | Vehicle positioning method and device based on UWB positioning and storage medium |
CN111935628B (en) * | 2020-07-28 | 2022-06-28 | 河南大学 | Wi-Fi positioning method and device based on position fingerprint |
CN113840228B (en) * | 2021-08-25 | 2024-04-02 | 北京航空航天大学杭州创新研究院 | Pedestrian indoor positioning method based on positioning matching |
CN115100279B (en) * | 2022-06-10 | 2024-09-13 | 暨南大学 | BN-CNN-based high-speed visible light positioning image processing method, system and medium |
CN117474991B (en) * | 2023-10-24 | 2024-06-07 | 纬创软件(武汉)有限公司 | SpectFormer-based Poi positioning method and SpectFormer-based Poi positioning device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105388456A (en) * | 2015-10-21 | 2016-03-09 | 宁波大学 | Visible light communication multi-element three-dimensional wireless positioning system |
CN106027149A (en) * | 2016-07-21 | 2016-10-12 | 长春光客科技有限公司 | Multi-user visible light communication device and method adopting a plurality of rotatable top ends |
CN106248077A (en) * | 2016-07-06 | 2016-12-21 | 北京理工大学 | A kind of visible ray integrated positioning system based on particle filter and method |
CN106597374A (en) * | 2016-11-09 | 2017-04-26 | 北京大学 | Indoor visible positioning method and system based on camera shooting frame analysis |
CN106646366A (en) * | 2016-12-05 | 2017-05-10 | 深圳市国华光电科技有限公司 | Visible light positioning method and system based on particle filter algorithm and intelligent equipment |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWM450170U (en) * | 2012-05-07 | 2013-04-01 | Jung-Tang Huang | Internet of things system |
CN103079269A (en) * | 2013-01-25 | 2013-05-01 | 哈尔滨工业大学 | LDE (Linear Discriminant Analysis) algorithm-based WiFi (Wireless Fidelity) indoor locating method |
CN104270194A (en) * | 2014-09-16 | 2015-01-07 | 南京邮电大学 | Visible light indoor positioning method |
CN104198989B (en) * | 2014-09-16 | 2017-10-20 | 北京邮电大学 | A kind of mixed mode indoor locating system based on lighting source and Wi Fi signals |
US10368358B2 (en) * | 2015-10-30 | 2019-07-30 | Kabushiki Kaisha Toshiba | Wireless communication device and wireless communication method for providing opportunity of fair transmission to terminals |
-
2017
- 2017-06-22 CN CN201710481197.9A patent/CN109116298B/en active Active
-
2018
- 2018-06-22 WO PCT/CN2018/092439 patent/WO2018233692A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105388456A (en) * | 2015-10-21 | 2016-03-09 | 宁波大学 | Visible light communication multi-element three-dimensional wireless positioning system |
CN106248077A (en) * | 2016-07-06 | 2016-12-21 | 北京理工大学 | A kind of visible ray integrated positioning system based on particle filter and method |
CN106027149A (en) * | 2016-07-21 | 2016-10-12 | 长春光客科技有限公司 | Multi-user visible light communication device and method adopting a plurality of rotatable top ends |
CN106597374A (en) * | 2016-11-09 | 2017-04-26 | 北京大学 | Indoor visible positioning method and system based on camera shooting frame analysis |
CN106646366A (en) * | 2016-12-05 | 2017-05-10 | 深圳市国华光电科技有限公司 | Visible light positioning method and system based on particle filter algorithm and intelligent equipment |
Non-Patent Citations (2)
Title |
---|
LiFi创造智慧应用新场景;黄文彬;《上海信息化》(第11期);第48-51页 * |
VLC智能照明系统探讨;牛衍方 等;《光源与照明》(第3期);第1-3页 * |
Also Published As
Publication number | Publication date |
---|---|
WO2018233692A1 (en) | 2018-12-27 |
CN109116298A (en) | 2019-01-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109116298B (en) | Positioning method, storage medium and positioning system | |
CN108537122B (en) | Image fusion acquisition system containing meteorological parameters and image storage method | |
CN111507210B (en) | Traffic signal lamp identification method, system, computing equipment and intelligent vehicle | |
Chen et al. | Indoor real-time 3-D visible light positioning system using fingerprinting and extreme learning machine | |
CN109146919B (en) | Tracking and aiming system and method combining image recognition and laser guidance | |
CN108332748B (en) | Indoor visible light positioning method and device | |
CN107730993A (en) | The parking lot intelligent vehicle-tracing system and method identified again based on image | |
CN111753757B (en) | Image recognition processing method and device | |
CN102749072A (en) | Indoor positioning method, indoor positioning apparatus and indoor positioning system | |
CN106462737A (en) | Systems and methods for haziness detection | |
CN109655790A (en) | Multi-target detection and identification system and method based on indoor LED light source | |
CN108288289B (en) | LED visual detection method and system for visible light positioning | |
CN110514298A (en) | A kind of solar irradiation strength calculation method based on ground cloud atlas | |
CN114973310B (en) | Passive human body positioning method and system based on infrared thermal imaging | |
CN113705376B (en) | Personnel positioning method and system based on RFID and camera | |
US20180082410A1 (en) | Image processing using histograms | |
CN115170792B (en) | Infrared image processing method, device and equipment and storage medium | |
CN110488391B (en) | Weather prediction system, method and storage medium for small area | |
CN106600652A (en) | Panoramic camera positioning method based on artificial neural network | |
CN111090074A (en) | Indoor visible light positioning method and equipment based on machine learning | |
KR102542556B1 (en) | Method and system for real-time detection of major vegetation in wetland areas and location of vegetation objects using high-resolution drone video and deep learning object recognition technology | |
CN107132526A (en) | A kind of indoor orientation method and alignment system | |
CN114758364B (en) | Industrial Internet of things scene fusion positioning method and system based on deep learning | |
CN208335208U (en) | Image fusion acquisition system containing meteorological parameters | |
Younus et al. | A unilateral 3D indoor positioning system employing optical camera communications |
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 |