CN106448431A - Mobile phone sensor-based indoor planar graph construction method adopting crowdsourcing mode - Google Patents
Mobile phone sensor-based indoor planar graph construction method adopting crowdsourcing mode Download PDFInfo
- Publication number
- CN106448431A CN106448431A CN201610710437.3A CN201610710437A CN106448431A CN 106448431 A CN106448431 A CN 106448431A CN 201610710437 A CN201610710437 A CN 201610710437A CN 106448431 A CN106448431 A CN 106448431A
- Authority
- CN
- China
- Prior art keywords
- mobile phone
- room
- line segment
- track line
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
- G09B29/003—Maps
- G09B29/005—Map projections or methods associated specifically therewith
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
The present invention discloses an intelligent mobile phone sensor-based indoor planar graph automatic construction method adopting a crowdsourcing mode. Compared with the prior art, the method of the present invention identifies the pedestrian activities according to the altitude data and the acceleration data to determine whether the users go upstairs or downstairs by the stairs, the vertical ladders or escalators, thereby being able to construct the indoor planar graphs of multiple floors. The method of the present invention combines a clustering algorithm to determine the doorway positions of the rooms according to the WiFi signal change front and behind the turning point positions in a pedestrian track, thereby being able to construct the more accurate room positions and sizes. By adopting a principal component analysis method, the method of the present invention can determine the lengths and widths of the corridors. The beneficial effects of the present invention are that: the mobile phone sensor data can be acquired and processed on the condition of only using the intelligent mobile phones and on the condition of general user passive participation, the approximate indoor planar graphs of the floors can be constructed automatically, and the problems that the large-scale indoor planar graph construction is difficult, the participation of the professional staff is needed, and the cost is high, are solved.
Description
Technical field
The present invention relates to pedestrian's dead reckoning and indoor map constructing technology, particularly relate to one and pass through smart mobile phone
Sensor gathers high number of row people in mass-rent mode and walks trace information, automatically builds the method for indoor plane figure.
Background technology
With the development of positioning and airmanship, various location Based service are increasing to the demand of map.Outdoor
The structure of map and drafting have had the method for a set of maturation through development for many years, and by professional surveying and mapping, personnel pass through professional equipment
Gather data, then processed and map making by the geographical software of specialty.But the structure of indoor map and drafting are always treated so far
The problem solving, is also to hinder location Based service in one of wide variety of principal element of indoor acquisition.At present indoorly
The structure of figure is mainly by mapping worker measurement house data map making or based on architectural design structure chart drafting plane
Figure.Although these methods can carry out map building and the drafting of part building, but due to the reason such as high cost and privacy,
Most indoor environments cannot use professional method to carry out mapping, and architectural design structure chart also tend to due to a variety of causes without
Method obtains, thus causes a large amount of indoor environment also cannot implement with navigation without available map, indoor positioning.
In recent years, with the development of mobile phone sensing technology, the sensor such as accelerometer, magnetometer, barometer has become intelligence
The standard configuration of energy mobile phone, has been greatly facilitated the pedestrian activity's identification based on smart mobile phone and has led with pedestrian's dead reckoning and indoor
The development of boat technology.By to the collection of intelligent mobile phone sensor data and process can obtain pedestrian's current activity state and
Movement track, according to a large amount of domestic consumers in indoor movement track, in conjunction with complex data analysis algorithm, it is possible to obtain indoor
The room in region and corridor structure, thus automatically construct indoor plane figure, to utilize location Based service indoor wide
General application.
Content of the invention
The indoor based on intelligent mobile phone sensor that the present invention proposes a kind of new blanket employing mass-rent mode are put down
Face figure method for auto constructing.The method comprises the steps：
A. owing to using mass-rent mode to carry out indoor plane figure structure, it is therefore desirable to a large number of users participates in.Participating user with
Body carries smart mobile phone, smart mobile phone integrated accelerometer, magnetometer, barometer, satellite navigation system receiver and WiFi
Adapter.Smart mobile phone and each sensor are in opening, and running background Data Acquisition ＆ Processing Software.
B. mass-rent mode is used to carry out data acquisition and produce a large number of users run trace.This step is at user's smart mobile phone
End performs, and needs a large number of users to participate in, and each user's smart mobile phone end performs following steps：
B1. the satellite navigation system receiver in smart mobile phone monitors satellite-signal in real time, when from receiving satellite-signal
When becoming not receiving satellite-signal, this position, as block entrance and track initial point, enters B2 step；
B2. each sensing data in Real-time Collection smart mobile phone：Gather acceleration information by accelerometer；Pass through magnetic force
Meter gathers magnetic field strength date；Gather barometric information by barometer；Smoothing and noise-reducing process is carried out to the data collecting；
B3. according to acceleration information, it is judged that whether user is in walking states, if it is, perform B4 step；
B4. each step in walking estimating step length are identified according to acceleration information；Combine according to magnetic field strength date
Acceleration information calculates direction of travel；According to back position, obtain new position in conjunction with current step and direction of travel；Gather
The WiFi AP list of current location and signal strength signal intensity；Each step is put as a tracing point, connects all tracing points and constitute
The run trace of this time of pedestrian；
B5. it is calculated altitude data according to barometric information, carry out according to altitude data and acceleration information
Pedestrian activity identifies, determines that whether user carries out upstairs or downstairs by stair, vertical ladder or staircase；If it is, by this position
Tagging is in run trace, and as new floor and new track initial point；
B6. judge that whether each tracing point in run trace is turning point (turns left, turn right, turn afterwards), if turning to
Point, then split to run trace at this point, obtains a series of track line segment；
B7. all run trace data are sent to central server to process；
C. run trace cluster and plane build automatically, and this step performs at central server, comprises the following steps：
C1. a large amount of walking trajectory sections from a large number of users smart mobile phone are received；
C2. change according to the WiFi signal before and after each turning point position, determine whether this turning point is room doorway；Even
Track line segment between continuous two rooms doorway belongs to room type track line segment, other the trajectory then belonging to corridor type
Section；
C3. clustering algorithm is used to cluster the track line segment of room type and the track line segment of corridor type respectively,
One class is a region；
If C4. region is room type, then extract all tracing points that track line segment therein comprises, utilize α-
Shape method determines room shape and size；
If C5. region is corridor type, then PCA is utilized to determine principal direction and time direction of data variation,
So that it is determined that the length in corridor and width；
C6. the position according to the room determining and corridor, shapes and sizes draw indoor each layer plane figure, will determine simultaneously
Vertical ladder, the position of staircase and stair is marked in the drawings.
The invention has the beneficial effects as follows and can adopt in the case of only using smart mobile phone and domestic consumer's non-active participation
Collection mobile phone sensor data are simultaneously processed, and automatically build each floor indoor plane figure of approximation.Compared to the prior art, this
Bright carry out pedestrian activity's identification according to altitude data and acceleration information, determine user whether by stair, vertical ladder or
Staircase carries out upstairs or goes downstairs such that it is able to the indoor plane figure carrying out many floors builds；The present invention is according to pedestrian's track transfer
WiFi signal change before and after a position combines clustering algorithm, determines the position on room doorway, thus constructs accurate
Room location and size；Using PCA, the present invention can determine the length and width in corridor.The method without by
Professional and special equipment, can solve the problem that extensive indoor plane figure builds and be difficult to and need professional to participate in and cost height
Problem, be conducive to the extensive application of indoor location Based service.
Brief description
Fig. 1 is system enforcement figure
Fig. 2 is the upper recognizer downstairs of pedestrian
Fig. 3 (a) is to change, according to WiFi signal, the possible room doorway location point determining
Fig. 3 (b) is the room doorway location point changing according to WiFi signal and being determined by clustering algorithm
Fig. 4 (a) is the corridor length utilizing PCA to obtain
Fig. 4 (b) is the width of corridor utilizing PCA to obtain
Detailed description of the invention
This method uses mass-rent mode to carry out the automatic structure of indoor plane figure, needs a large amount of domestic consumer to participate in.Each
Participating user carries with smart mobile phone, and smart mobile phone integrated accelerometer, magnetometer, barometer, satellite navigation system receive
Device and WIFI adapter.Accelerometer can measure the 3-axis acceleration of mobile phone in real time, and magnetometer can measure mobile phone in real time
The three-axle magnetic field intensity of position, barometer can measure the atmospheric pressure value of mobile phone present position thus calculate height above sea level,
Satellite navigation system (GPS or the Big Dipper) receiver is able to receive that the signal of aeronautical satellite and obtains current geographic position coordinate,
WIFI adapter can record WiFi access device and signal strength signal intensity thereof in local environment.In user's participation process, smart mobile phone
And each sensor is in opening, running background Data Acquisition ＆ Processing Software, the data after acquisition process are sent to server
End carries out focusing on and map structuring.Fig. 1 shows the indoor plane figure based on mobile phone sensor of this employing mass-rent mode
The basic process of method for auto constructing.
Step 1：Satellite navigation system receiver in smart mobile phone monitors satellite-signal in real time, when from receive satellite letter
When number becoming not receiving satellite-signal, i.e. satellite-signal is lost, then show now indoor by outdoor entrance, using this position as
Block entrance and track initial point, enter step 2；
Step 2：Each sensing data in Real-time Collection smart mobile phone.Gather 3-axis acceleration data by accelerometer,
Sample frequency is 50Hz, i.e. 20ms is once；Gathering magnetic field strength date by magnetometer, sample frequency is 50Hz, i.e. 20ms mono-
Secondary；Gathering barometric information by barometer, sample frequency is 5Hz, i.e. 200ms is once.Due to embedded in mobile phone sensor itself
The impact of the interference on sensing data for the body-sway motion and surrounding environment, the sensor collecting in non-precision, people's walking
Data have certain noise, once use simple rolling average algorithm (Simple Moving Average, SMA) to enter data
Row smoothing processing is to reduce noise jamming；
Step 3：According to the acceleration information collecting, it is judged that whether user is in walking states, if accekeration is high
In predetermined walking threshold value, it is determined that people is in walking states, step 4；
Step 4：Pedestrian's walking step state identification, step can be carried out according to the acceleration information after smooth and magnetic field strength date
Long estimation and direction estimation.Identification to walking step state is to identify walking cycle from accelerating curve, and carries out based on this
Step size computation.For the identification of walking cycle in accelerating curve, a walking cycle can be divided into inactive state, crest
State and trough state, use the method for State Transferring to identify walking cycle.Inactive state, crest state and trough state are then
State threshold is used to judge.After identifying a complete walking cycle, Kalman filtering is used to combine step-length and vertically add
The relation of speed and adjacent two step by step grow between relation step-length is estimated.First according to body in step-length and walking process
The dry relation between vertical displacement, is calculated basis step-length by acceleration information in this walking cycle, then by karr
Graceful filtering application is in basis step-length, and then obtains more accurate step-size estimation.Direction determines use accelerometer and magnetometer
Jointly complete.First pass through 3-axis acceleration data and acceleration of gravity calculates the angle of pitch and the roll angle of mobile phone, then will
Change into the three-axle magnetic field intensity based on earth coordinates by the three-axle magnetic field intensity based on mobile phone coordinate system that magnetometer records,
Use the magnetic field intensity in x and y direction in earth coordinates, i.e. can determine that pedestrian direction.
After obtaining current step and current direction, according to previous step position, current location can be calculated.Gather present bit
The WiFi AP list put and signal strength signal intensity thereof.Put each step as a tracing point, connect all tracing points and constitute pedestrian
The run trace of this time.Each tracing point is represented by：T, (x, y), o, r}, t represent the time in this position for the pedestrian,
(x, y) is current position coordinates, and o represents current direction, and r represents in the AP list of this station acquisition and signal strength signal intensity.
Step 5：Vertical ladder, stair and staircase are the important symbols in building, are also the important information in indoor plane figure.Root
Height above sea level can be calculated according to barometer data, carry out pedestrian activity's identification, energy according to height above sea level and acceleration information
Enough determine that whether pedestrian carries out upstairs or downstairs by stair, vertical ladder or staircase, thus identify stair, vertical ladder and staircase
Position, is marked in run trace, simultaneously using the outlet of vertical ladder, stair or staircase as the new track initial of a new floor
Point.The identification using on vertical ladder, stair and staircase mode downstairs to pedestrian uses two stage recognition algorithm, algorithm flow such as Fig. 2 institute
Show, comprise the steps of：
1) primary characterization, identify according to altitude data put down away, vertical ladder upstairs, vertical ladder downstairs, stair staircase upstairs,
Stair staircase is gone downstairs.Initially with rolling average algorithm, altitude data is smoothed, to the height above sea level number of degrees after smooth
According to doing linear fit, draw the change slope h of altitude data.Assume HuFor vertical ladder empirical value upstairs, HdFor under vertical ladder
The empirical value in building, H0For upper empirical value downstairs.If h >=Hu, then for vertical ladder upstairs；If H0≤ h ＜ Hu, then be stair or
Staircase is upstairs；If-H0＜ h ＜ H0, then for putting down away；If-Hd＜ h ＜-H0, then it is that stair or staircase are gone downstairs；If h is ＜-Hd, then it is straight
Ladder is gone downstairs；
2) secondary characterization, according to 3-axis acceleration data identify staircase upstairs, stair upstairs, staircase downstairs, under stair
Building.First acceleration magnitude is soughtAccording to the result of primary characterization, if staircase or stair are upstairs,
If am＜ AuThen for staircase upstairs, if am＞ AuThen for stair upstairs；If staircase or stair are gone downstairs, if am＜ AdIt is then staircase
Go downstairs, if am＞ AdThen go downstairs for stair；AuAnd AdIt is respectively the magnitude threshold value that stair are gone downstairs upstairs with stair.
Step 6：According to acceleration information and magnetic field strength date, it is judged that whether each tracing point in run trace is to turn
To point (turn left, turn right, turn afterwards).Calculate the direction of each tracing point and the direction difference DELTA of previous tracing point.If Δ exceedes
Turn to threshold value, then it is assumed that there occurs go to action.In view of being likely to occur continuously the little situation turning to and being accumulated as turning to greatly, will even
The continuous summation of Δ value several times obtains ∑ Δ, if ∑ Δ exceedes turns to threshold value, is also considered as there occurs go to action.It is judged at each
Run trace is once split by the tracing point being set to turning point, thus a continuous print run trace is divided into some
Track line segment.
Step 7：All trajectory segment datas that this walking produces are sent to central server by smart mobile phone end；Central authorities
Server receives a large amount of walking trajectory sections from different user smart mobile phone；
Step 8：Track line segment is divided into room type and corridor type.Determine the type of track line segment, need first to identify
Go out the room doorway position in pedestrian's track.Generally have go to action when entering due to people or go out, therefore check pedestrian's rail
Each turning point position in mark, it is judged that whether this position is room doorway.Two are used here for room doorway position judgment
Level recognizer, comprises the steps of：
1) primary characterization, owing to the WiFi signal in house interior and corridor is typically different, is therefore turned to by detecting each
WiFi signal change before and after some position, the manhatton distance between calculating received signals fingerprint is as changing value, if changing value surpasses
Cross threshold value, then it is assumed that current turning point is in room doorway, as shown in Fig. 3 (a)；
2) secondary characterization, all rooms doorway location point obtaining primary characterization utilizes density-based algorithms
(DBSCAN) cluster, obtain n cluster areas.N cluster areas n cluster centre of correspondence, by each cluster centre half
Turning point in the range of footpath R (R is empirical value) is labeled as doorway location point, completes the secondary identification to doorway location point, such as Fig. 3
Shown in (b).
Owing to the starting point of every track is all corridor, therefore often detect that doorway position, two continuous print rooms then represents capable
Once enter action and the action of once going out of people, the track line segment between the two tracing point just belongs to room type.If
The room doorway quantity eventually detecting is even number, shows that this walking terminates in corridor, then remaining track line segment is corridor class
Type；If be detected that room doorway quantity be odd number, show that this walking terminates in room, then from last room doorway
Position starts to the track line segment that track terminates to fall within room type, and remaining track line segment is corridor type.
Step 9：Central server uses clustering algorithm, is comprised the track line segment of room type and corridor type respectively
Tracing point cluster, form some room type regions and some corridors type area；
Step 10：If cluster areas is room type, then extract all tracks that the track line segment in this region comprises
Point, obtains boundary of a set of points shape by the tracing point in this region and is the room shape that we need.Track boundary of point set shape
Shape has convex closure and two kinds of common polygons of recessed bag.In view of directly taking convex closure or recessed bag shape as room boundaries error relatively
Greatly, a shape between convex closure and recessed bag is needed to represent room boundaries.So using α-shape method to build room
Between shapes and sizes, specifically comprise the steps of：
1) it is that tracing point data set asks for Delaunay triangulation network M；
2) for all limits in M, calculate the length on limit and the adjacent triangle sets on this limit, wherein adjoin 2 three
The limit of dihedral is internal edges, adjacent 1 triangle for boundary edge, can degenerate during calculating in the limit of adjacent 0 triangle
Limit；
3) by all length more than L boundary edge add queue (L for preset length limitation, be used for getting rid of in triangulation network M
Invalid edges), circulate following process：Taking out a limit E from queue, E has unique adjacent triangle T；Find out in T other two
Bar limit E ' and E ", deletes T from their adjacent triangle sets；By E ' and E " in the length that the is newly formed boundary edge more than L
Add queue；E is labeled as invalid edges, if E ' and E " has degeneration, is also labeled as invalid edges；
4) collect all efficiency frontier limits, then obtain the room shape representated by this cluster.
Step 11：If cluster areas is corridor type, then utilize PCA (Principle Component
Analysis-PCA) tracing point change principal direction u is determined1With secondary direction u2, so that it is determined that the length in corridor and width, such as Fig. 4 (a) and 4
Shown in (b), comprise the following steps：
1) assume that tracing point data set is X={ (xi, yi) | i=1,2 ... m}, m are tracing point number.First to track
Point data pre-processes, and data are normalized by employing Z-score standardized method, data after treatment
Meet standardized normal distribution；
2) the covariance matrix P=XX of X is calculatedT/ m, carries out singular value decomposition to P and obtains characteristic vector U=[u1u2…
un], wherein u1It is the main characteristic vector of P, u2For sub-eigenvector；
3) vector u1And u2Constitute a new base of X, for tracing point data set X,It is that X is in dimension u1On projection
Length,It is that X projects to u2Length in dimension, the length of the two length corresponding corridor area respectively and width.
Step 12：Indoor each layer plane figure is drawn in position according to the room determining and corridor, shapes and sizes, will simultaneously
The position of the vertical ladder, staircase and the stair that determine is marked in the drawings.
Claims (5)
1. use the indoor plane figure construction method based on mobile phone sensor of mass-rent mode, comprise the following steps：
A. owing to using mass-rent mode to carry out indoor plane figure structure, it is therefore desirable to a large number of users participates in, and participating user is taken with oneself
Band smart mobile phone, smart mobile phone integrated accelerometer, magnetometer, barometer, satellite navigation system receiver and WiFi adaptation
Device, smart mobile phone and each sensor are in opening, and running background Data Acquisition ＆ Processing Software,
B. using mass-rent mode carry out data acquisition and produce a large number of users run trace, this step is held at user's smart mobile phone end
OK, needing a large number of users to participate in, each user's smart mobile phone end performs following steps：
B1. the satellite navigation system receiver in smart mobile phone monitors satellite-signal in real time, when becoming from receiving satellite-signal
When not receiving satellite-signal, this position, as block entrance and track initial point, enters B2 step；
B2. each sensing data in Real-time Collection smart mobile phone：Gather acceleration information by accelerometer；Adopted by magnetometer
Collection magnetic field strength date；Gather barometric information by barometer；Smoothing and noise-reducing process is carried out to the data collecting；
B3. according to acceleration information, it is judged that whether user is in walking states, if it is, perform B4 step；
B4. each step in walking estimating step length are identified according to acceleration information；Combine according to magnetic field strength date and accelerate
Degrees of data calculates direction of travel；According to back position, obtain new position in conjunction with current step and direction of travel；Gather current
The WiFi AP list of position and signal strength signal intensity；Each step is put as a tracing point, connects all tracing points and constitute pedestrian
The run trace of this time；
B5. it is calculated altitude data according to barometric information, carry out pedestrian according to altitude data and acceleration information
Activity recognition, determines that whether user carries out upstairs or downstairs by stair, vertical ladder or staircase；If it is, mark this position
Remember in run trace, and as new floor and new track initial point；
B6. judge that whether each tracing point in run trace is turning point (turns left, turn right, turn afterwards), if turning point, then
At this point, run trace is split, obtain a series of track line segment；
B7. all run trace data are sent to central server to process；
C. run trace cluster and plane build automatically.This step performs at central server, comprises the following steps：
C1. a large amount of walking trajectory sections from a large number of users smart mobile phone are received；
C2. change according to the WiFi signal before and after each turning point position, determine whether this turning point is room doorway；Continuous two
Track line segment between individual room doorway belongs to room type track line segment, other the track line segment then belonging to corridor type；
C3. clustering algorithm is used to cluster the track line segment of room type and the track line segment of corridor type respectively, one
Class is a region；
If C4. region is room type, then extract all tracing points that track line segment therein comprises, utilize α-shape side
Method determines room shape and size；
If C5. region is corridor type, then PCA is utilized to determine principal direction and time direction of data variation, thus
Determine length and the width in corridor；
C6. the position according to the room determining and corridor, shapes and sizes draw indoor each layer plane figure, simultaneously straight by determine
The position of ladder, staircase and stair is marked in the drawings.
2. as described in claim 1, use the indoor plane figure construction method based on mobile phone sensor of mass-rent mode, its feature
It is described in step B5, carry out pedestrian activity's identification according to altitude data and acceleration information, determine whether user leads to
Cross stair, vertical ladder or staircase carry out upstairs or go downstairs, use two stage recognition algorithm：Primary characterization is according to altitude data
Change slope identify put down away, vertical ladder upstairs, vertical ladder downstairs, stair staircase upstairs, stair staircase goes downstairs；Secondary characterization is in one-level
On the basis of identification according to 3-axis acceleration magnitude identify staircase upstairs, stair upstairs, staircase downstairs, stair go downstairs.
3. as described in claim 1, use the indoor plane figure construction method based on mobile phone sensor of mass-rent mode, its feature
It is described in step C2, according to the WiFi signal change before and after each turning point position, determine whether this turning point is room
Doorway, uses two stage recognition algorithm：In primary characterization, detect the WiFi signal change before and after each turning point position, calculate letter
Manhatton distance between number fingerprint is as changing value, if changing value exceedes threshold value, then it is assumed that current turning point is likely to be at
Room doorway；In secondary characterization, all possible room doorway location point obtaining primary characterization utilizes gathering based on density
Class algorithm clusters, and the turning point in the range of each cluster centre radius R (R is empirical value) is labeled as doorway location point.
4. as described in claim 1, use the indoor plane figure construction method based on mobile phone sensor of mass-rent mode, its feature
It is described in step C2, it is determined that behind the position of doorway, determine that track line segment is room type or corridor type：Continuous two
Track line segment between room doorway belongs to room type track line segment；If the room doorway quantity eventually detecting is even
Number, then remaining track line segment is corridor type；If be detected that room doorway quantity be odd number, then from last room door
Mouth position starts to the track line segment that track terminates to fall within room type, and remaining track line segment is corridor type.
5. as described in claim 1, use the indoor plane figure construction method based on mobile phone sensor of mass-rent mode, its feature
Be described in step C5, if region is corridor type, then utilize PCA determine data variation principal direction and
Secondary direction, so that it is determined that the length in corridor and width.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610710437.3A CN106448431A (en) | 2016-08-24 | 2016-08-24 | Mobile phone sensor-based indoor planar graph construction method adopting crowdsourcing mode |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610710437.3A CN106448431A (en) | 2016-08-24 | 2016-08-24 | Mobile phone sensor-based indoor planar graph construction method adopting crowdsourcing mode |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106448431A true CN106448431A (en) | 2017-02-22 |
Family
ID=58182546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610710437.3A Pending CN106448431A (en) | 2016-08-24 | 2016-08-24 | Mobile phone sensor-based indoor planar graph construction method adopting crowdsourcing mode |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106448431A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108668245A (en) * | 2018-04-13 | 2018-10-16 | 哈尔滨工业大学 | A kind of indoor orientation method based on WiFi Yu earth's magnetic field database |
| CN109798900A (en) * | 2019-03-08 | 2019-05-24 | 珠海格力电器股份有限公司 | Indoor orientation method, device and the air borne sensor of air borne sensor |
| CN110132266A (en) * | 2019-05-05 | 2019-08-16 | 深圳市荣盛智能装备有限公司 | Floor method of discrimination, device, electronic equipment and storage medium |
| CN110647600A (en) * | 2018-06-26 | 2020-01-03 | 百度在线网络技术（北京）有限公司 | Three-dimensional map construction method and device, server and storage medium |
| CN110907981A (en) * | 2019-12-09 | 2020-03-24 | Oppo广东移动通信有限公司 | Positioning mode control method and device and electronic equipment |
| CN111311748A (en) * | 2020-02-19 | 2020-06-19 | 广东小天才科技有限公司 | Indoor stereogram construction method and device, terminal equipment and storage medium |
| CN111368014A (en) * | 2019-12-23 | 2020-07-03 | 广东小天才科技有限公司 | Motion trail generation method, terminal equipment and storage medium |
| CN111750851A (en) * | 2019-09-10 | 2020-10-09 | 广东小天才科技有限公司 | Method and device for identifying inter-floor movement mode and intelligent equipment |
| CN112401877A (en) * | 2020-10-27 | 2021-02-26 | 中国电力科学研究院有限公司 | Method and system for monitoring behavior state of target object |
| CN113848878A (en) * | 2021-08-24 | 2021-12-28 | 深圳大学 | Indoor and outdoor three-dimensional pedestrian road network construction method based on multi-source data |
| CN114111784A (en) * | 2021-10-26 | 2022-03-01 | 杭州电子科技大学 | Crowdsourcing-based automatic construction method and system for indoor corridor map |
| CN114125696A (en) * | 2020-08-31 | 2022-03-01 | 华为技术有限公司 | Construction method, positioning method and device of fingerprint map of multi-floor building |
| WO2023005865A1 (en) * | 2021-07-28 | 2023-02-02 | 华为技术有限公司 | Method for constructing indoor map and related apparatus |
| CN116184312A (en) * | 2022-12-22 | 2023-05-30 | 泰州雷德波达定位导航科技有限公司 | Indoor crowdsourcing fingerprint library construction method based on semantic Wi-Fi |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090043504A1 (en) * | 2007-05-31 | 2009-02-12 | Amrit Bandyopadhyay | System and method for locating, tracking, and/or monitoring the status of personnel and/or assets both indoors and outdoors |
| CN104180805A (en) * | 2014-08-29 | 2014-12-03 | 中国海洋大学 | Smart phone-based indoor pedestrian positioning and tracking method |
| CN104282221A (en) * | 2013-07-01 | 2015-01-14 | 北京四维图新科技股份有限公司 | Method for constructing road network of indoor map |
| CN104394588A (en) * | 2014-11-15 | 2015-03-04 | 北京航空航天大学 | Indoor positioning method based on Wi-Fi fingerprints and multi-dimensional scaling analysis |
| CN104655128A (en) * | 2015-03-11 | 2015-05-27 | 武汉大学 | Indoor and outdoor parallel navigation system applicable to intelligent mobile terminal |
| CN105263113A (en) * | 2015-10-26 | 2016-01-20 | 深圳大学 | Wi-Fi location fingerprint map building method and system based on crowd-sourcing |
| CN105547301A (en) * | 2016-02-25 | 2016-05-04 | 华南理工大学 | Indoor map construction method and device based on geomagnetism |
| US20160223340A1 (en) * | 2015-02-03 | 2016-08-04 | The Regents Of The University Of Michigan | Last-Mile Navigation Using Smartphones |
-
2016
- 2016-08-24 CN CN201610710437.3A patent/CN106448431A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090043504A1 (en) * | 2007-05-31 | 2009-02-12 | Amrit Bandyopadhyay | System and method for locating, tracking, and/or monitoring the status of personnel and/or assets both indoors and outdoors |
| CN104282221A (en) * | 2013-07-01 | 2015-01-14 | 北京四维图新科技股份有限公司 | Method for constructing road network of indoor map |
| CN104180805A (en) * | 2014-08-29 | 2014-12-03 | 中国海洋大学 | Smart phone-based indoor pedestrian positioning and tracking method |
| CN104394588A (en) * | 2014-11-15 | 2015-03-04 | 北京航空航天大学 | Indoor positioning method based on Wi-Fi fingerprints and multi-dimensional scaling analysis |
| US20160223340A1 (en) * | 2015-02-03 | 2016-08-04 | The Regents Of The University Of Michigan | Last-Mile Navigation Using Smartphones |
| CN104655128A (en) * | 2015-03-11 | 2015-05-27 | 武汉大学 | Indoor and outdoor parallel navigation system applicable to intelligent mobile terminal |
| CN105263113A (en) * | 2015-10-26 | 2016-01-20 | 深圳大学 | Wi-Fi location fingerprint map building method and system based on crowd-sourcing |
| CN105547301A (en) * | 2016-02-25 | 2016-05-04 | 华南理工大学 | Indoor map construction method and device based on geomagnetism |
Non-Patent Citations (1)
| Title |
|---|
| 许强: ""基于信号分析的室内定位特征点识别技术研究"", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108668245A (en) * | 2018-04-13 | 2018-10-16 | 哈尔滨工业大学 | A kind of indoor orientation method based on WiFi Yu earth's magnetic field database |
| CN110647600A (en) * | 2018-06-26 | 2020-01-03 | 百度在线网络技术（北京）有限公司 | Three-dimensional map construction method and device, server and storage medium |
| CN110647600B (en) * | 2018-06-26 | 2023-10-20 | 百度在线网络技术（北京）有限公司 | Three-dimensional map construction method, device, server and storage medium |
| CN109798900A (en) * | 2019-03-08 | 2019-05-24 | 珠海格力电器股份有限公司 | Indoor orientation method, device and the air borne sensor of air borne sensor |
| CN110132266A (en) * | 2019-05-05 | 2019-08-16 | 深圳市荣盛智能装备有限公司 | Floor method of discrimination, device, electronic equipment and storage medium |
| CN110132266B (en) * | 2019-05-05 | 2020-06-30 | 深圳市荣盛智能装备有限公司 | Floor discrimination method and device, electronic equipment and storage medium |
| CN111750851A (en) * | 2019-09-10 | 2020-10-09 | 广东小天才科技有限公司 | Method and device for identifying inter-floor movement mode and intelligent equipment |
| CN110907981A (en) * | 2019-12-09 | 2020-03-24 | Oppo广东移动通信有限公司 | Positioning mode control method and device and electronic equipment |
| CN111368014A (en) * | 2019-12-23 | 2020-07-03 | 广东小天才科技有限公司 | Motion trail generation method, terminal equipment and storage medium |
| CN111368014B (en) * | 2019-12-23 | 2024-04-19 | 广东小天才科技有限公司 | Motion trail generation method, terminal equipment and storage medium |
| CN111311748A (en) * | 2020-02-19 | 2020-06-19 | 广东小天才科技有限公司 | Indoor stereogram construction method and device, terminal equipment and storage medium |
| CN111311748B (en) * | 2020-02-19 | 2023-06-30 | 广东小天才科技有限公司 | Indoor stereogram construction method and device, terminal equipment and storage medium |
| CN114125696A (en) * | 2020-08-31 | 2022-03-01 | 华为技术有限公司 | Construction method, positioning method and device of fingerprint map of multi-floor building |
| WO2022042655A1 (en) * | 2020-08-31 | 2022-03-03 | 华为技术有限公司 | Method for constructing fingerprint map of multi-floor building, positioning method, and apparatus |
| CN112401877A (en) * | 2020-10-27 | 2021-02-26 | 中国电力科学研究院有限公司 | Method and system for monitoring behavior state of target object |
| WO2023005865A1 (en) * | 2021-07-28 | 2023-02-02 | 华为技术有限公司 | Method for constructing indoor map and related apparatus |
| CN113848878A (en) * | 2021-08-24 | 2021-12-28 | 深圳大学 | Indoor and outdoor three-dimensional pedestrian road network construction method based on multi-source data |
| CN113848878B (en) * | 2021-08-24 | 2023-08-08 | 深圳大学 | Indoor and outdoor three-dimensional pedestrian road network construction method based on crowd source data |
| CN114111784A (en) * | 2021-10-26 | 2022-03-01 | 杭州电子科技大学 | Crowdsourcing-based automatic construction method and system for indoor corridor map |
| CN116184312A (en) * | 2022-12-22 | 2023-05-30 | 泰州雷德波达定位导航科技有限公司 | Indoor crowdsourcing fingerprint library construction method based on semantic Wi-Fi |
| CN116184312B (en) * | 2022-12-22 | 2023-11-21 | 泰州雷德波达定位导航科技有限公司 | Indoor crowdsourcing fingerprint library construction method based on semantic Wi-Fi |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106448431A (en) | Mobile phone sensor-based indoor planar graph construction method adopting crowdsourcing mode | |
| CN109525935B (en) | Intelligent floor sensing method and control system for universal indoor environment | |
| Alzantot et al. | Crowdinside: Automatic construction of indoor floorplans | |
| Zhou et al. | ALIMC: Activity landmark-based indoor mapping via crowdsourcing | |
| CN108632761B (en) | Indoor positioning method based on particle filter algorithm | |
| US8977494B2 (en) | Method and apparatus for identification of points of interest within a predefined area | |
| CN107339992B (en) | Indoor positioning and landmark semantic identification method based on behaviors | |
| CN108537101B (en) | Pedestrian positioning method based on state recognition | |
| WO2021212878A1 (en) | Indoor positioning algorithm based on crowdsensing and multi-fusion technologies | |
| CN106017476B (en) | A method of generating indoor positioning navigation graph model | |
| CN106840163A (en) | A kind of indoor orientation method and system | |
| CN110933604B (en) | KNN indoor positioning method based on position fingerprint time sequence characteristics | |
| CN107121140A (en) | A kind of location acquiring method based on Multiple Source Sensor | |
| CN104394588A (en) | Indoor positioning method based on Wi-Fi fingerprints and multi-dimensional scaling analysis | |
| CN110207704A (en) | A kind of pedestrian navigation method based on the identification of architectural stair scene intelligent | |
| Ehrlich et al. | Pedestrian localisation inside buildings based on multi-sensor smartphones | |
| Zhou et al. | Anonymous crowdsourcing-based WLAN indoor localization | |
| Luo et al. | iMap: Automatic inference of indoor semantics exploiting opportunistic smartphone sensing | |
| Ye et al. | BTrack: Using barometer for energy efficient location tracking on mountain roads | |
| Ye et al. | Infrastructure-free floor localization through crowdsourcing | |
| CN105960011A (en) | Indoor target positioning method based on sensor network and Bayesian method | |
| CN107958118B (en) | Wireless signal acquisition method based on spatial relationship | |
| CN115220028A (en) | Millimeter wave-based non-portable equipment positioning and household activity sensing method | |
| CN108763808A (en) | A kind of underground utilities geometric data fusion method | |
| Zhou et al. | Automatic construction of floor plan with smartphone sensors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170222 |