CN109031263B - Indoor fingerprint map construction method based on mobile crowd sensing data - Google Patents
Indoor fingerprint map construction method based on mobile crowd sensing data Download PDFInfo
- Publication number
- CN109031263B CN109031263B CN201810727605.9A CN201810727605A CN109031263B CN 109031263 B CN109031263 B CN 109031263B CN 201810727605 A CN201810727605 A CN 201810727605A CN 109031263 B CN109031263 B CN 109031263B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- time
- user
- information
- closed loop
- 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.)
- Expired - Fee Related
Links
- 238000010276 construction Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 17
- 230000001133 acceleration Effects 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 8
- 238000005457 optimization Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 238000006073 displacement reaction Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
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
- G01S11/00—Systems for determining distance or velocity not using reflection or reradiation
- G01S11/02—Systems for determining distance or velocity not using reflection or reradiation using radio waves
- G01S11/06—Systems for determining distance or velocity not using reflection or reradiation using radio waves using intensity measurements
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention relates to an indoor fingerprint map construction method based on mobile crowd sensing data. The mobile user in the environment is used as a sensing unit, so that automatic collection of fingerprint data and user tracks is realized, the survey workload required by fingerprint positioning can be reduced, and rapid deployment of a fingerprint positioning system in an unknown environment is facilitated.
Description
Technical Field
The invention relates to the technical field of indoor fingerprint positioning, in particular to an indoor fingerprint map construction method based on mobile crowd sensing data.
Background
With the development of the internet of things and the demand of location-based service applications, indoor positioning has received more and more attention in recent years. Because of the sheltering of urban buildings, the outdoor positioning technology represented by the GPS is no longer available indoors, and therefore people need a convenient, universal, and accurate indoor positioning technical scheme. In fact, researchers at home and abroad began exploring indoor positioning 20 years ago. Some attempts have included deploying specialized hardware devices, such as magnetic markers, infrared, RFID, and laser sensors, etc., at key locations in the room, and locating by measuring distance or orientation. While these techniques may provide good positioning accuracy, the additional hardware overhead, specialized equipment, and advanced deployment limit the popularity and applicability of these approaches.
A large number of mobile communication devices (smart phones and notebook computers) on the market are embedded with cheap and various sensors, such as Wi-Fi modules, motion sensors, GPS (global positioning system), cameras and the like. However, most indoor environments are deployed with Wi-Fi Access Points (APs), so that indoor positioning based on Wi-Fi becomes a hot spot of current research. Indeed, Wi-Fi has been used by many companies (including Google, Apple, Microsoft, Baidu, and Skyhook) for indoor positioning and navigation. At present, a position fingerprint method is a widely adopted and most advanced Wi-Fi indoor positioning method, and the method needs to survey an indoor environment in advance, establish fingerprint information corresponding to each position point in a fingerprint map recording environment, and realize the positioning of equipment through fingerprint matching. The biggest challenge faced by this approach is the construction of a large fingerprint database. Especially, urban buildings are large and complicated in structure, and surveying of the environment often requires special equipment and specialized technicians, so that the surveying engineering is very costly. With the change of indoor environment, the fingerprint map needs to be updated and repeatedly surveyed manually, which has become a bottleneck limiting the popularization of the fingerprint positioning method.
In some studies at home and abroad, the SLAM idea is introduced into Wi-Fi positioning, and a high-dimensional signal intensity space is mapped to a low-dimensional two-dimensional position space by utilizing a Gaussian process hidden variable model. These methods often need to rely on a signal propagation model, and need to estimate the signal propagation model parameters of the AP while achieving self-localization.
Disclosure of Invention
The invention aims to solve the technical problem of providing an indoor fingerprint map construction method based on mobile crowd sensing data, and solving the problem of huge survey engineering in the existing fingerprint positioning method.
The technical scheme for solving the technical problems is as follows: an indoor fingerprint map construction method based on mobile crowd sensing data comprises the following steps:
s1, collecting fingerprint information and dead reckoning information of the user through the mobile phone terminal, and uploading the fingerprint information and dead reckoning information to the server;
s2, analyzing the fingerprint information and the dead reckoning information through the server to obtain fingerprint similarity and user trajectory data, and constructing a 'vertex-constraint' graph by using the fingerprint similarity and the user trajectory data;
and S3, optimizing the 'vertex-constraint' graph through a graph optimization algorithm to obtain the fingerprint map.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, the method for constructing the "vertex-constraint" graph in step S2 includes:
s21, forming the poses of the users into vertexes, wherein the position relation among the vertexes is an edge;
s22, performing closed-loop detection on the opposite side to obtain a fingerprint-closed loop and a turning-closed loop;
s23, constructing a 'vertex-constraint' graph through 'fingerprint-closed loop' and 'turning-closed loop'.
Further, the calculation formula of the dead reckoning information R (t, τ) in step S1 is:
in equation (1), μ (t, τ) and σ (t, τ) are the mean and standard deviation of the acceleration between t and t + τ, τ is a time delay parameter, l is a variable, and takes a value of 0 to τ -1, a (t + l) is the acceleration value at time t + l, and μ (t + τ, τ) and σ (t + τ, τ) are the mean and standard deviation of the acceleration between t + τ and t +2 τ.
Further, the fingerprint similarity S in the step S2ijThe calculation method comprises the following steps:
in the formula (2), FiFingerprint information collected for time i, FjFingerprint information collected at time j, L is the number of detected APs, fi,lSignal strength of the ith AP at time i, fj,lThe signal strength of the ith AP at time j.
Further, the method for calculating the "fingerprint-closed loop" in step S22 is as follows:
a1, calculating the relative distance d between the fingerprint i and the corresponding position of the fingerprint jijThe calculation formula is as follows:
in the formula (3), xiAnd xjRespectively, the abscissa, y, of the fingerprint i and the fingerprint jiAnd yjRespectively the abscissa of the fingerprint i and the abscissa of the fingerprint j;
a2, calculating the relative angle theta of the corresponding positions of the fingerprint i and the fingerprint jijThe calculation formula is as follows:
θij＝|θi-θj| (4)
in the formula (4), θiIs the angle, θ, of the fingerprint ijIs the angle of the fingerprint j;
a3, relative distance dijLess than a distance threshold, relative angle thetaijLess than the angle threshold and its fingerprint similarity sijIf the similarity is greater than the similarity threshold, the fingerprint i and the fingerprint j form a "fingerprint-closed loop".
Further, the calculation method of the "turning-closed loop" in step S22 is:
b1, dividing the user trajectory data through a sliding window w to obtain a set Ct of trajectories at time t:
Ct＝{xt'} (5)
in the formula (5), t is time, t 'is the time meeting the sliding window condition, | t' -t | < w, and x is the pose of the user;
and B2, if the difference between theta and theta + exceeds 60 degrees, the t time is in a turning state.
Further, the graph optimization algorithm in step S3 is a minimization function:
in the formula (6), Xt＝(xt,yt,θt) For the time t, t is the dead reckoning data of the user, and t is i, j, i and j are all vertexes, (x)t,yt) Two-dimensional position information of the user at time t, θtThe orientation information of the user at the time t, C is the set of all constraints in the figure, and zijIs a rigid body transformation between vertex i and vertex j.
The invention has the beneficial effects that: the method comprises the steps of crowd sensing data acquisition, closed loop detection and Graph construction, and Graph SLAM-based Graph optimization algorithm. The mobile user in the environment is used as a sensing unit, so that automatic collection of fingerprint data and user tracks is realized, the survey workload required by fingerprint positioning can be reduced, and rapid deployment of a fingerprint positioning system in an unknown environment is facilitated.
Drawings
FIG. 1 is a schematic flow diagram of the present invention;
FIG. 2 is a flowchart illustrating step S2 according to the present invention;
FIG. 3 is a diagram illustrating the constraints within and between users in crowd sensing according to the present invention;
FIG. 4 is a schematic diagram illustrating the periodic variation of IMU acceleration data when a user walks in accordance with the present invention;
FIG. 5 is a diagram illustrating an uncertainty model of fingerprint similarity and distance according to the present invention;
FIG. 6 is a schematic diagram of the user's original trajectory and turn in accordance with the present invention;
FIG. 7 is a schematic diagram of the present invention utilizing a user trajectory for turn detection and matching.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
As shown in fig. 1, a method for constructing an indoor fingerprint map based on mobile crowd sensing data includes the following steps:
s1, collecting fingerprint information and dead reckoning information of the user through the mobile phone terminal, and uploading the fingerprint information and dead reckoning information to the server;
s2, analyzing the fingerprint information and the dead reckoning information through the server to obtain fingerprint similarity and user trajectory data, and constructing a 'vertex-constraint' graph by using the fingerprint similarity and the user trajectory data;
and S3, optimizing the 'vertex-constraint' graph through a graph optimization algorithm to obtain the fingerprint map.
As shown in fig. 2, the construction method of the "vertex-constraint" graph in step S2 is as follows:
s21, forming the poses of the users into vertexes, wherein the position relation among the vertexes is an edge;
s22, performing closed-loop detection on the opposite side to obtain a fingerprint-closed loop and a turning-closed loop;
s23, constructing a 'vertex-constraint' graph through 'fingerprint-closed loop' and 'turning-closed loop'.
As shown in fig. 3, in the constraint schematic diagram in crowd sensing between users, since there is a certain error in the observed data, an uncertainty parameter is added to all constraints, so that the map-based SLAM problem is converted into an optimized pose to minimize the error caused by the constraints.
In the embodiment of the present invention, the graph optimization algorithm in step S3 is a minimization function:
in the formula (6), Xt＝(xt,yt,θt) For the time t, t is the dead reckoning data of the user, and t is i, j, i and j are all vertexes, (x)t,yt) Two-dimensional position for user at time tInformation, thetatThe orientation information of the user at the time t, C is the set of all constraints in the figure, and zijIs a rigid body transformation between vertex i and vertex j.
For laser scanners, this transformation can be estimated by scan matching (e.g., iterative closest point algorithm, ICP); for visual sensors, this transformation can be obtained by feature matching. Given the signal strength of a certain AP, it can be quickly determined whether a certain user has revisited the area because each AP has a unique hardware address, but estimating the relative bit relationship of two measurement points from the signal strength is very difficult because the RSS data itself does not provide any distance or direction information.
Performing closed loop detection using a location fingerprint method, the fingerprint describing the detected AP at a location and the corresponding signal strength; just like the fingerprints and DNA of human body, Wi-Fi fingerprints can be used to uniquely describe a certain position, thereby overcoming the influence of environment on signal propagation; and the distance of two locations can be measured by the similarity of fingerprints.
If the similarity of two fingerprints is higher than a certain threshold, the two positions are considered to be the same, so that a closed loop is detected, and the error is compensated by adding an uncertainty covariance parameter, a diagonal matrix with a large value can be selected in practical application. In order to improve the accuracy of the system, an uncertainty model of the similarity and the distance is established through a training process.
As shown in fig. 4, which is a change rule of vertical acceleration when a human body walks, an inertial navigation element with low power consumption is embedded in all current smart phones, simple dead reckoning can be realized by performing double integration on the acceleration, and due to the influence of data drift and noise, a large accumulated error is brought by continuous double integration. The step counting algorithm based on human walking dynamics can effectively overcome the defect, and the dead reckoning is realized by identifying human behaviors and counting the steps. The adopted algorithm is an autocorrelation analysis method, the integral acceleration value has obvious periodic change when a person moves, the autocorrelation step-counting algorithm counts steps by utilizing the autocorrelation coefficient of the acceleration sequence of the current step-counting period and the previous step-counting period, so that the dead reckoning is realized, and the calculation formula of dead reckoning information R (t, tau) in the step S1 is as follows:
in formula (1), μ (t, τ) and σ (t, τ) are the mean and standard deviation of the acceleration between t and t + τ, τ is a time delay parameter, l is a variable, and takes a value of 0 to τ -1, a (t) + l) is the acceleration value at time t + l, and μ (t + τ, τ) and σ (t + τ, τ) are the mean and standard deviation of the acceleration between t + τ and t +2 τ.
Under the mobile crowd sensing, each user independently collects data, the motion track of each user is based on the initial position of each user, and a common reference coordinate system does not exist, so that the tracks among the users need to be combined, each user has a common reference system, and the power of crowd sensing is fully exerted. Depending on the direction of movement of the user, consider the following two cases: in the first case, it is assumed that the user's direction can be obtained by a compass of the handset. Thus, the moving direction of each mobile phone is under the same reference frame (earth reference frame), and only the coordinate system has displacement. Given two users a and b, the two fingerprints with the maximum similarity in the two tracks are obtained by using the following formula
And
and
the deviation between them is the displacement between the two coordinate systems
Comprises the following steps:
in the second case, the directional error of the cell phone compass is often large, and some low-end cell phones do not support compass sensors, so some dead reckoning systems do not provide a direction of motion relative to the earth's reference frame. For this case, use
And
the displacement is represented by a displacement of the displacement,
representing the rotation, these three parameters can be obtained by minimizing the following distance function:
in equation (8), R is a rotation matrix between two coordinate systems,
d () is the euclidean distance between two points, which is the position of the user's b trajectory and the fingerprint in a where the fingerprint t is most similar to the fingerprint.
The radio frequency fingerprint describes a certain position by using radio frequency signals (such as Wi-Fi, RFID and Bluetooth), and can well overcome the influence of the environment on the propagation of wireless signals, so that the fingerprint is widely applied to indoor positioning. Just like the visual features, the fingerprint information can be used for identifying a certain scene, however, the extraction of the visual features requires a complex algorithm, and the fingerprint information does not have the problem because the hardware address of the AP in the fingerprint is globally unique.
In the embodiment of the present invention, the fingerprint similarity S in step S2ijThe calculation method comprises the following steps:
in the formula (2), FiFingerprint information collected for time i, FjFingerprint information collected at time j, L is the number of detected APs, fi,lSignal strength of the ith AP at time i, fj,lThe signal strength of the ith AP at time j.
The calculation complexity of the fingerprint similarity is greatly related to the number of APs detected by two fingerprints, hundreds of APs can be obtained by one-time scanning in the environment of an airport or a stadium, and the calculation overhead at the moment is not negligible, so that the concept of a signal strength threshold is introduced, and measurement data with less signal strength are filtered. On one hand, the calculation cost of the system can be greatly saved by filtering some APs; on the other hand, too small a signal strength tends to represent more noise, while a larger signal strength may better limit the location, due to the effects of environmental multipath.
As shown in FIG. 5, which is a diagram of uncertainty model of fingerprint similarity and distance, each edge in Graph SLAM needs to specify its uncertainty. For the constructed edges of the odometer, the uncertainty can be derived from the motion model, so the uncertainty of the fingerprint constraint (closed loop of the fingerprint) needs to be specified and trained with odometer data. The odometer typically remains accurate over a range of 30 meters. Therefore, similarity of all fingerprints with distances less than 30 meters is calculated, and K training data are obtained:
skrepresenting the similarity of two fingerprints, dkRepresenting the distance between two fingerprints. Then, a binning method is used for training the samples, and a model is obtained for representing the uncertainty of the distance corresponding to a certain similarity. That is, given a similarity s, the variance var(s) is calculated for all samples spaced b from the similarity s:
in formula (9), c (b) is the number of samples whose statistical similarity falls within interval b, and b(s) is the sample whose similarity lies between [ s-b/2, s + b/2 ].
As shown in fig. 6 and 7, a typical indoor environment often contains many landmarks such as turns, elevators, and stairs, and the detection of these features often greatly improves the accuracy of the indoor positioning system. The present invention fuses turn features in the environment into a SLAM system. After a fingerprint closed loop is obtained, whether the user turns or not is detected by analyzing the motion trail of the user, and turning is matched, so that the turning closed loop is obtained. Due to the limitation of the environment, the actual positions of two correct matching turns are often very close, and are much smaller than the uncertainty caused by the closed loop of the fingerprint, for example, the width of a corridor is often less than 3 meters, and the positioning accuracy of the fingerprint is often much greater than 3 meters. Fig. 7 is a schematic diagram of track-based turn detection and matching.
In the embodiment of the present invention, the method for calculating the "fingerprint-closed loop" in step S22 includes:
a1, calculating the relative distance d between the fingerprint i and the corresponding position of the fingerprint jijThe calculation formula is as follows:
in the formula (3), xiAnd xjRespectively, the abscissa, y, of the fingerprint i and the fingerprint jiAnd yjRespectively are the horizontal coordinates of the fingerprint i and the fingerprint j;
a2, calculating the relative angle theta of the corresponding positions of the fingerprint i and the fingerprint jijThe calculation formula is as follows:
θij＝|θi-θj| (4)
in the formula (4), θiIs the angle, θ, of the fingerprint ijIs the angle of the fingerprint j;
a3, relative distance dijLess than a distance threshold, relative angle thetaijLess than the angle threshold and its fingerprint similarity sijIf the similarity is greater than the similarity threshold, the fingerprint i and the fingerprint j form a "fingerprint-closed loop".
In the embodiment of the present invention, the calculation method of the "turning-closed loop" in step S22 is:
b1, dividing the user trajectory data through a sliding window w to obtain a set Ct of trajectories at time t:
Ct＝{xt'} (5)
in the formula (5), t is time, t 'is the time meeting the sliding window condition, | t' -t | < w, and x is the pose of the user;
and B2, if the difference between theta and theta + exceeds 60 degrees, the t time is in a turning state.
In laser scan matching, ICP (iterative closest point algorithm) is often used to find a coordinate transformation between two sets of scanned point clouds, thereby minimizing the sum of distances between corresponding points of the two sets of point clouds. ICP is therefore used to determine whether two turns match. Because the dead reckoning sampling frequency is low, the two groups of motion tracks are interpolated before ICP is executed. If the average distance value of the corresponding points obtained by ICP is less than a certain threshold value thetafThe two turns are considered to match and this closed loop is added to the turn closed loop.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (4)
1. A method for constructing an indoor fingerprint map based on mobile crowd sensing data is characterized by comprising the following steps:
s1, collecting fingerprint information and dead reckoning information of the user through the mobile phone terminal, and uploading the fingerprint information and dead reckoning information to the server;
s2, analyzing the fingerprint information and the dead reckoning information through the server to obtain fingerprint similarity and user trajectory data, and constructing a 'vertex-constraint' graph by using the fingerprint similarity and the user trajectory data;
the construction method of the "vertex-constraint" graph in the step S2 includes:
s21, forming the poses of the users into vertexes, wherein the position relation among the vertexes is an edge;
s22, performing closed-loop detection on the opposite side to obtain a fingerprint-closed loop and a turning-closed loop;
the method for calculating the "fingerprint-closed loop" in step S22 includes:
a1, calculating the relative distance d between the fingerprint i and the corresponding position of the fingerprint jijThe calculation formula is as follows:
in the formula (3), xiAnd xjRespectively, the abscissa, y, of the fingerprint i and the fingerprint jiAnd yjRespectively the abscissa of the fingerprint i and the abscissa of the fingerprint j;
a2, calculating the relative angle theta of the corresponding positions of the fingerprint i and the fingerprint jijThe calculation formula is as follows:
θij＝|θi-θj| (4)
in the formula (4), θiIs the angle, θ, of the fingerprint ijIs the angle of the fingerprint j;
a3, relative distance dijLess than a distance threshold, relative angle thetaijLess than the angle threshold and its fingerprint similarity sijIf the similarity is larger than the similarity threshold, the fingerprint i and the fingerprint j form a fingerprint-closed loop;
the calculation method of the "turning-closed loop" in the step S22 is as follows:
b1, dividing the user trajectory data through a sliding window w to obtain a set Ct of trajectories at time t:
Ct＝{xt′} (5)
in the formula (5), t is time, t 'is the time meeting the sliding window condition, | t' -t | < w, and x is the pose of the user;
b2, recording the average value in the direction less than the time t in the set Ct as theta-, and recording the average value in the direction more than the time t as theta +, and if the difference between the theta + and the theta + exceeds 60 degrees, the time t is in a turning state;
s23, constructing a 'vertex-constraint' diagram through 'fingerprint-closed loop' and 'turning-closed loop';
and S3, optimizing the 'vertex-constraint' graph through a graph optimization algorithm to obtain the fingerprint map.
2. The method for constructing an indoor fingerprint map based on mobile crowd sensing data according to claim 1, wherein the dead reckoning information R (t, τ) in step S1 is calculated by:
in equation (1), μ (t, τ) and σ (t, τ) are the mean and standard deviation of the acceleration between t and t + τ, τ is a time delay parameter, l is a variable, and takes a value of 0 to τ -1, a (t + l) is the acceleration value at time t + l, and μ (t + τ, τ) and σ (t + τ, τ) are the mean and standard deviation of the acceleration between t + τ and t +2 τ.
3. The indoor fingerprint map construction method based on mobile crowd sensing data of claim 1, wherein the fingerprint similarity S in step S2 isijThe calculation method comprises the following steps:
in the formula (2), FiFingerprint information collected for time i, FjFingerprint information collected at time j, L is the number of detected APs, fi,lSignal strength of the ith AP at time i, fj,lThe signal strength of the ith AP at time j.
4. The indoor fingerprint map construction method based on mobile crowd sensing data of claim 1, wherein the graph optimization algorithm in the step S3 is a minimization function:
in the formula (6), Xt ═ xt,yt,θt) For the time t, t is the dead reckoning data of the user, and t is i, j, i and j are all vertexes, (x)t,yt) Two-dimensional position information of the user at time t, θtThe orientation information of the user at the time t, C is the set of all constraints in the figure, and zijIs a rigid body transformation between vertex i and vertex j.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810727605.9A CN109031263B (en) | 2018-07-05 | 2018-07-05 | Indoor fingerprint map construction method based on mobile crowd sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810727605.9A CN109031263B (en) | 2018-07-05 | 2018-07-05 | Indoor fingerprint map construction method based on mobile crowd sensing data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109031263A CN109031263A (en) | 2018-12-18 |
| CN109031263B true CN109031263B (en) | 2022-04-12 |
Family
ID=65521817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810727605.9A Expired - Fee Related CN109031263B (en) | 2018-07-05 | 2018-07-05 | Indoor fingerprint map construction method based on mobile crowd sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109031263B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110174105B (en) * | 2019-06-14 | 2022-02-11 | 西南科技大学 | Intelligent agent autonomous navigation algorithm and system in complex environment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102905368A (en) * | 2012-10-18 | 2013-01-30 | 无锡儒安科技有限公司 | Mobile auxiliary indoor positioning method and system based on smart phone platform |
| CN104157020A (en) * | 2014-08-12 | 2014-11-19 | 广州中国科学院沈阳自动化研究所分所 | Hand-held intelligent inspection terminal |
| CN104181500A (en) * | 2014-08-19 | 2014-12-03 | 北京邮电大学 | Real-time locating method based on inertia information and chance wireless signal characteristics |
| CN104964683A (en) * | 2015-06-04 | 2015-10-07 | 上海物景智能科技有限公司 | Closed loop correction method for indoor environment map creation |
| US9204257B1 (en) * | 2005-04-12 | 2015-12-01 | Ehud Mendelson | Indoor and outdoor mapping and navigation utilizing RF bluetooth beacons |
| 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 |
| CN105589064A (en) * | 2016-01-08 | 2016-05-18 | 重庆邮电大学 | Rapid establishing and dynamic updating system and method for WLAN position fingerprint database |
| CN106123897A (en) * | 2016-06-14 | 2016-11-16 | 中山大学 | Indoor fusion and positioning method based on multiple features |
| CN106707232A (en) * | 2016-12-20 | 2017-05-24 | 南京工业大学 | WLAN (Wireless local area network) propagation model positioning method based on crowd sensing |
| CN107688665A (en) * | 2017-09-27 | 2018-02-13 | 深圳大学 | A kind of indoor map method for auto constructing, device and storage medium |
-
2018
- 2018-07-05 CN CN201810727605.9A patent/CN109031263B/en not_active Expired - Fee Related
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9204257B1 (en) * | 2005-04-12 | 2015-12-01 | Ehud Mendelson | Indoor and outdoor mapping and navigation utilizing RF bluetooth beacons |
| CN102905368A (en) * | 2012-10-18 | 2013-01-30 | 无锡儒安科技有限公司 | Mobile auxiliary indoor positioning method and system based on smart phone platform |
| CN104157020A (en) * | 2014-08-12 | 2014-11-19 | 广州中国科学院沈阳自动化研究所分所 | Hand-held intelligent inspection terminal |
| CN104181500A (en) * | 2014-08-19 | 2014-12-03 | 北京邮电大学 | Real-time locating method based on inertia information and chance wireless signal characteristics |
| CN104964683A (en) * | 2015-06-04 | 2015-10-07 | 上海物景智能科技有限公司 | Closed loop correction method for indoor environment map creation |
| 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 |
| CN105589064A (en) * | 2016-01-08 | 2016-05-18 | 重庆邮电大学 | Rapid establishing and dynamic updating system and method for WLAN position fingerprint database |
| CN106123897A (en) * | 2016-06-14 | 2016-11-16 | 中山大学 | Indoor fusion and positioning method based on multiple features |
| CN106707232A (en) * | 2016-12-20 | 2017-05-24 | 南京工业大学 | WLAN (Wireless local area network) propagation model positioning method based on crowd sensing |
| CN107688665A (en) * | 2017-09-27 | 2018-02-13 | 深圳大学 | A kind of indoor map method for auto constructing, device and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| "Smartphones based crowdsourcing for indoor localization";C. Wu 等;《IEEE Trans. Mobile Comput.》;20150228;第444-457页 * |
| "基于位置指纹的WIFI室内定位算法研究";董艳侠;《中国优秀硕士学位论文全文数据库 信息科技辑》;20160215;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109031263A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110856112B (en) | Crowd-sourcing perception multi-source information fusion indoor positioning method and system | |
| CN109298389B (en) | Indoor pedestrian combination pose estimation method based on multi-particle swarm optimization | |
| CN111491367B (en) | Indoor positioning method based on crowd sensing and multi-fusion technology | |
| Kim et al. | Smartphone-based collaborative and autonomous radio fingerprinting | |
| Mirowski et al. | SignalSLAM: Simultaneous localization and mapping with mixed WiFi, Bluetooth, LTE and magnetic signals | |
| CN107094319B (en) | High-precision indoor and outdoor fusion positioning system and method | |
| Shang et al. | Improvement schemes for indoor mobile location estimation: A survey | |
| CN104457751B (en) | Indoor and outdoor scene recognition method and system | |
| Lin et al. | Human localization based on inertial sensors and fingerprints in the Industrial Internet of Things | |
| Du et al. | CRCLoc: A crowdsourcing-based radio map construction method for WiFi fingerprinting localization | |
| CN111879305B (en) | Multi-mode perception positioning model and system for high-risk production environment | |
| CN104394588B (en) | Indoor orientation method based on Wi Fi fingerprints and Multidimensional Scaling | |
| CN112729301A (en) | Indoor positioning method based on multi-source data fusion | |
| CN106197418B (en) | A kind of indoor orientation method merged based on the fingerprint technique of sliding window with sensor | |
| Ashraf et al. | A comprehensive analysis of magnetic field based indoor positioning with smartphones: Opportunities, challenges and practical limitations | |
| CN108801267B (en) | Indoor anchor-free positioning method integrating multiple sensors | |
| Kwak et al. | Magnetic field based indoor localization system: A crowdsourcing approach | |
| Yu et al. | Effective fingerprint extraction and positioning method based on crowdsourcing | |
| Gu et al. | Pedestrian positioning using WiFi fingerprints and a foot-mounted inertial sensor | |
| Gong et al. | An enhanced indoor positioning solution using dynamic radio fingerprinting spatial context recognition | |
| Shu et al. | Indoor geomagnetic positioning using direction-aware multiscale recurrent neural networks | |
| Wu et al. | Indoor positioning based on tightly coupling of PDR and one single Wi-Fi FTM AP | |
| Xingli et al. | Indoor positioning technology based on deep neural networks | |
| Wei et al. | MM-Loc: Cross-sensor indoor smartphone location tracking using multimodal deep neural networks | |
| CN109031263B (en) | Indoor fingerprint map construction method based on mobile crowd sensing data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220412 |