CN106595633A - Indoor positioning method and device - Google Patents
Indoor positioning method and device Download PDFInfo
- Publication number
- CN106595633A CN106595633A CN201611070529.6A CN201611070529A CN106595633A CN 106595633 A CN106595633 A CN 106595633A CN 201611070529 A CN201611070529 A CN 201611070529A CN 106595633 A CN106595633 A CN 106595633A
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- indoor
- movement
- probability
- position information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides an indoor positioning method and device, and belongs to the technical field of indoor positioning. The method comprises the following steps: predicting the position information of pedestrians according to data acquired by multiple sensors; acquiring indoor movement states of the pedestrians on the basis of an indoor movement model; and calibrating the predicted position information of the pedestrians on the basis of an indoor environmental map model and according to the indoor movement state and position information of indoor preset joints to obtain the final position information of the pedestrians. The indoor movement state of the pedestrians by predicting the position information of the pedestrians and on the basis of the indoor movement model. The predicted position information of the pedestrians is calibrated on the basis of the indoor environmental map model and according to the indoor movement state and the position information of the indoor preset joint so as to obtain the final position information of the pedestrians. Because external equipment does not require to be mounted, costs for hardware can further be reduced while a system with high complexity is avoided, and therefore, costs consumed for indoor positioning are low.
Description
Technical field
The present invention relates to indoor positioning technologies field, more particularly, to a kind of indoor orientation method and device.
Background technology
In current many applications, obtain people or object location information is all extremely important.With science and technology with
And communication technology etc. is constantly progressive, the location technology based on LBS (Location Based Service, location-based service) is also swift and violent
Development.The problem that LBS is mainly solved is that the resource that will have existed is supplied to user, and the surrounding enviroment according to residing for it are providing
Specific service.
In an outdoor environment, can be obtained by GPS (Global Positioning System, global positioning system)
Positional information.As information technology is developed rapidly, GPS positioning technology can meet the daily demand of general public.Correspondingly,
The main flow that GPS technology is always studied.Because GPS is positioned by satellite, before four satellites are positioned simultaneously
Put and just can acquire best positioning precision.But in the environment of indoors, because building is blocked to gps signal,
Satellite signal strength and quality dramatic decrease.Simultaneously as indoor environment is sufficiently complex, it is accurately fixed to carry out indoors
Position.Therefore, indoor positioning technologies difficulty is larger.
In addition, research shows that 90% time is all indoors in people's daily life, that is to say, that people's most of the time is all
Outside gps signal positioning.As can be seen here, indoor positioning technologies are also that people focus on demand.With intelligent communication device
Development, the research of indoor positioning technologies have also been developed.Smart mobile phone and panel computer used in people's daily life
Deng intelligent mobile terminal, MEMS (Micro-Electro-Mechanical System, MEMS), acceleration are integrated with
The high-precision sensor elements such as meter, gyroscope and barometer.Widely using for these sensor elements, is that indoor positioning technologies are carried
Having supplied the precision of basis and sensor element can also meet the demand of indoor positioning technologies.In addition, assistant positioning system is also same
When obtain extensively and sufficiently study.For example, based on the indoor positioning technologies of wireless fingerprint signal, the location technology of view-based access control model
Deng.These modes or it is used in combination with sensor, or as independent location technology.Correspondingly, the essence of indoor positioning
Degree is also improved therewith.In recent years, the company such as Google begins setting up indoor map, progressively covers some and metropolitan significant builds
Thing is built, so that the map of interior can also become the supplementary meanss of positioning.
From the beginning of 2000, on the basis of intelligent terminal gradually popularizes, LBS be gradually used in Emergency Assistance,
The fields such as disaster prevention, logistics management, equipment inspection and health care.In this context, for positioning is from outdoor to interior
Seamless connection demand also be proposed out.
In public safety guarantee, commercialized services and in Warehouse Service field, high-precision indoor positioning technologies have
Very important meaning.For example, in terms of social public security guarantee, accurately indoor positioning technologies can for fireman,
The personnel such as police provide indoor navigation service, and convict positioned etc. in prison.In commercialized services, accurately
Indoor positioning technologies can provide positioning service for family, and navigation can be provided in the indoor environments such as market, museum, in doctor
The nurse positioning service of old man, child and patient is may provide in institute, family.In Warehouse Service, can be to article
Positioned.Therefore, indoor positioning technologies possess and are widely applied scene.
On this basis, the research direction of pedestrian's indoor positioning and airmanship mainly towards inexpensive, easily portable and
Improve positioning precision development.Existing indoor orientation method mainly installs in advance multiple external equipments, such as AP (Acess
Piont, access point), according to signal intensity between mobile terminal and external equipment and the mapping relations of distance, to carry out to pedestrian
Positioning.
During the present invention is realized, it is found that prior art at least has problems with：Need to be mounted so that multiple outer
Portion's equipment, equipment cost expends higher.In addition, generally needing the higher system of design complexities to assist between multiple external equipments
With work.Therefore, that what is expended during indoor positioning is relatively costly.
The content of the invention
The present invention provide it is a kind of overcome the problems referred to above or the indoor orientation method that solves the above problems at least in part and
Device.
According to an aspect of the present invention, there is provided a kind of indoor orientation method, the method includes：
According to the data that multiple sensor is collected, the positional information of pedestrian is predicted；
Based on indoor sport model, the indoor sport state of pedestrian is obtained；
Based on indoor environment cartographic model, according to indoor sport state and the positional information of indoor default node, to prediction
The pedestrian position information for obtaining is calibrated, and obtains the final position information of pedestrian.
According to a further aspect in the invention, there is provided a kind of indoor positioning device, the device includes：
Prediction module, for the data collected according to multiple sensor, predicts the positional information of pedestrian；
Acquisition module, for based on indoor sport model, obtaining the indoor sport state of pedestrian；
Calibration module, for based on indoor environment cartographic model, according to indoor sport state and the position of indoor default node
Confidence ceases, and the pedestrian position information that prediction is obtained is calibrated, and obtains the final position information of pedestrian.
The beneficial effect brought of technical scheme that the application is proposed is：
By the data collected according to multiple sensor, the positional information of pedestrian is predicted.Based on indoor sport model, obtain
Take the indoor sport state of pedestrian.Based on indoor environment cartographic model, according to indoor sport state and the position of indoor default node
Confidence ceases, and the pedestrian position information that prediction is obtained is calibrated, and obtains the final position information of pedestrian.Due to outer without installing
Portion's equipment, so as to while the system for avoiding design complexities higher, can also reduce hardware cost consumption, and then causes interior
The cost expended during positioning is relatively low.
Further, since when carrying out motion feature classification, have chosen accelerometer, barometer and gyro data, improve
Accuracy when motion feature is classified, while the appearance of long-time cumulative error can be avoided.Because position fixing process navigates pedestrian
Position speculates that algorithm, indoor pedestrian movement's feature and HMM matching process are combined togather, so as to ensure
While located higher accuracy rate, the robustness of indoor positioning can also be lifted.
Description of the drawings
Fig. 1 is a kind of schematic flow sheet of indoor orientation method of the embodiment of the present invention；
Fig. 2 is a kind of schematic flow sheet of indoor orientation method of the embodiment of the present invention；
Fig. 3 is a kind of structural representation of indoor positioning device of the embodiment of the present invention.
Specific embodiment
With reference to the accompanying drawings and examples, the specific embodiment of the present invention is described in further detail.Hereinafter implement
Example is not limited to the scope of the present invention for illustrating the present invention.
Existing indoor orientation method mainly installs in advance multiple external equipments, and (Acess Piont are accessed such as AP
Point), according to signal intensity between mobile terminal and external equipment and the mapping relations of distance, to position to pedestrian.Due to
Need that multiple external equipments are installed, equipment cost expends higher.In addition, generally needing design complexities between multiple external equipments
Higher system carrys out collaborative work.Therefore, that what is expended during indoor positioning is relatively costly.
For the problems of the prior art, a kind of indoor orientation method is present embodiments provided.The method is applied to movement
Terminal, mobile terminal includes but is not limited to mobile phone, panel computer and intelligent watch etc..Further, since the embodiment of the present invention needs
The data that sensor acquisition is arrived are applied to, so as to acceleration transducer, gyroscope and barometer etc. can be provided with mobile terminal,
The present embodiment is also not especially limited to this.
Referring to Fig. 1, the method flow that the present embodiment is provided includes：101st, the data collected according to multiple sensor, in advance
Survey the positional information of pedestrian；102nd, based on indoor sport model, the indoor sport state of pedestrian is obtained；103rd, based on indoor environment
Cartographic model, according to indoor sport state and the positional information of indoor default node, enters to the pedestrian position information that prediction is obtained
Row calibration, obtains the final position information of pedestrian.
Method provided in an embodiment of the present invention, by the data collected according to multiple sensor, predicts the position of pedestrian
Information.Based on indoor sport model, the indoor sport state of pedestrian is obtained.Based on indoor environment cartographic model, according to indoor fortune
The positional information of dynamic state and indoor default node, calibrates to the pedestrian position information that prediction is obtained, and obtains pedestrian most
Whole positional information.Due to without installing external equipment, so as to while the system for avoiding design complexities higher, also reduce
Hardware cost is consumed, and then the cost for causing to be expended during indoor positioning is relatively low.
Further, since when carrying out motion feature classification, have chosen accelerometer, barometer and gyro data, improve
Accuracy when motion feature is classified, while the appearance of long-time cumulative error can be avoided.Because position fixing process navigates pedestrian
Position speculates that algorithm, indoor pedestrian movement's feature and HMM matching process are combined togather, so as to ensure
While located higher accuracy rate, the robustness of indoor positioning can also be lifted.
As a kind of alternative embodiment, according to the data that multiple sensor is collected, the positional information of pedestrian, bag are predicted
Include：
Determine pedestrian from the total step number begun to move between stopping movement；
For each step of pedestrian's movement, the positional information before the movement of step-length, steering angle and pedestrian according to pedestrian, calculate
Pedestrian move move a step after positional information, until calculation times reach total step number, using final calculation result as pedestrian position
Information.
As a kind of alternative embodiment, determine that pedestrian, from beginning to move into before the total step number between stopping movement, also wraps
Include：
According to the acceleration of each sampled point, mobile and stopping movement being started to pedestrian and is detected.
As a kind of alternative embodiment, according to the acceleration of each sampled point, movement is started to pedestrian and is detected, wrapped
Include：
For arbitrary sampled point, when the acceleration for detecting arbitrary sampled point is not less than the first predetermined threshold value, it is determined that
Pedestrian starts movement on arbitrary sampled point.
As a kind of alternative embodiment, according to the acceleration of each sampled point, movement is stopped to pedestrian and is detected, wrapped
Include：
For arbitrary sampled point, when the acceleration for detecting arbitrary sampled point is less than the first predetermined threshold value, to from arbitrary
Sampling is lighted, and the continuous sampled point quantity less than the first predetermined threshold value is counted；
When statistical result reaches predetermined number, acquisition statistical result reaches last sampled point during predetermined number,
Determine that pedestrian stops movement on last sampled point.
As a kind of alternative embodiment, determine pedestrian from begin to move into stop it is mobile between total step number, including：
For pedestrian is from beginning to move into the arbitrary sampled point stopped in mobile this period, when detecting arbitrary sampled point
Acceleration be more than the second predetermined threshold value, and the corresponding acceleration of next sampled point of arbitrary sampled point be less than the second predetermined threshold value
When, using next sampled point of a upper sampled point, arbitrary sampled point and arbitrary sampled point of arbitrary sampled point as a paces week
Phase, and the total step number of pedestrian is added one.
As a kind of alternative embodiment, by a upper sampled point of arbitrary sampled point, arbitrary sampled point and arbitrary sampled point
Next sampled point before adding one by the total step number of pedestrian, also includes as a paces cycle：
The acceleration correlation in the cycle is cut down according to previous step, the second predetermined threshold value is calculated.
As a kind of alternative embodiment, the positional information before the movement of step-length, steering angle and pedestrian according to pedestrian, row is calculated
Before the positional information that people is moved after moving a step, also include：
Based on space coordinates, current pedestrian angular acceleration in three directions is obtained；
Based on the projection relation between space coordinates and earth axes, according to current pedestrian angle in three directions
Acceleration and acceleration, calculate the steering angle of pedestrian.
As a kind of alternative embodiment, according to the data that multiple sensor is collected, the positional information of pedestrian, bag are predicted
Include：
According to the air pressure value of pedestrian present position, the floor residing for pedestrian is determined.
As a kind of alternative embodiment, based on indoor sport model, the indoor sport state of pedestrian is obtained, including：
According to the acceleration of each sampled point in very first time window, the corresponding eigenvalue of very first time window is calculated；
Based on kinestate grader, according to the corresponding eigenvalue of very first time window, the motion feature of pedestrian is determined.
As a kind of alternative embodiment, based on indoor sport model, the indoor sport state of pedestrian is obtained, including：
According to the steering angle of the second time window one skilled in the art, the angle of turn of pedestrian is calculated；
According to the angle of turn of pedestrian, the turning feature of pedestrian is determined.
As a kind of alternative embodiment, based on indoor environment cartographic model, according to indoor sport state and indoor default section
The positional information of point, calibrates to the pedestrian position information that prediction is obtained, and obtains the final position information of pedestrian, including：
Based on indoor environment cartographic model, determine that pedestrian is moved to the shifting of adjacent default node in indoor environment cartographic model
Dynamic probability；
The movement probability of each adjacent default node is ranked up, two maximum movements of numerical value in ranking results are chosen
Probability, respectively the first movement probability and the second movement probability, the first movement probability is more than the second movement probability；
When the ratio of the first movement probability and the second movement probability is more than three predetermined threshold values, by the first movement probability pair
Final position information of the positional information of the adjacent default node answered as pedestrian.
As a kind of alternative embodiment, based on indoor environment cartographic model, determine that pedestrian is moved to indoor environment ground artwork
The movement probability of adjacent default node in type, including：
Arbitrary adjacent default node in indoor environment cartographic model, believes according to the position of arbitrary adjacent default node
Breath, calculates the emission probability that pedestrian is moved to arbitrary adjacent default node；
According to Motion Recognition probability matrix, the kinestate for determining arbitrary adjacent default node shows as indoor sport state
State recognition probability；
Product between emission probability and state recognition probability is moved to into the shifting of arbitrary adjacent default node as pedestrian
Dynamic probability.
As a kind of alternative embodiment, the movement probability of each adjacent default node is ranked up, chooses ranking results
Two maximum movement probabilities of middle numerical value, after respectively the first movement probability and the second movement probability, also include：
When the ratio of the first movement probability and the second movement probability is not more than three predetermined threshold values, the row that prediction is obtained
Final position information of people's positional information as pedestrian.
Above-mentioned all optional technical schemes, can adopt the alternative embodiment for arbitrarily combining to form the present invention, and here is no longer
Repeat one by one.
Based on the content that above-mentioned Fig. 1 correspondence embodiments are provided, a kind of indoor orientation method is embodiments provided.
Referring to Fig. 2, the method flow that the present embodiment is provided includes：201st, determine pedestrian from the total step begun to move between stopping movement
Number；202nd, for each step of pedestrian's movement, the positional information before the movement of step-length, steering angle and pedestrian according to pedestrian is calculated
Pedestrian move move a step after positional information, until calculation times reach total step number, using final calculation result as pedestrian position
Information；203rd, based on indoor sport model, the indoor sport state of pedestrian is obtained；204th, based on indoor environment cartographic model, root
According to indoor sport state and the positional information of indoor default node, the pedestrian position information that prediction is obtained is calibrated, obtained
The final position information of pedestrian.
Wherein, 201, determine pedestrian from begin to move into stop it is mobile between total step number.
The method that the present embodiment is provided is mainly the data for first collecting according to multiple sensor, predicts the position letter of pedestrian
Breath, then the process to realize positioning is calibrated to the pedestrian position information that prediction is obtained.Wherein, this step 201 to step 202
The data for mainly being collected according to multiple sensor, predict the process of pedestrian position information.
It is unknown when to be started movement indoors and when stopped movement due to pedestrian, so as to perform sheet
Before step 201, can be detected with starting mobile and stopping movement to pedestrian according to the acceleration of each sampled point, this reality
Apply example to be not especially limited this.
With regard to the acceleration according to each sampled point, the mode that movement is detected is started to pedestrian, the present embodiment is to this
It is not especially limited, including but not limited to：For arbitrary sampled point, when the acceleration for detecting arbitrary sampled point is not less than first
During predetermined threshold value, it is determined that pedestrian starts movement on arbitrary sampled point.
Wherein, sampled point it is corresponding be sensor sampling period.First predetermined threshold value can be according to practical situation value, this
Embodiment is not especially limited to this.For example, with the first predetermined threshold value as 1.5m/s2As a example by.If the sampling of acceleration transducer
Cycle is 20ms, then every 20ms be exactly a sampled point.I.e. acceleration transducer gathers accekeration on each sampled point
When, whether mobile terminal can also judge the accekeration collected on each sampled point more than or equal to 1.5m/s2.If detecting
The acceleration of one sampled point is more than 1.5m/s2, it is determined that pedestrian lights from the sampling and starts movement.
The present embodiment stops the mobile mode for being detected to pedestrian and makees specifically not to the acceleration according to each sampled point
Limit, including but not limited to：For arbitrary sampled point, when the acceleration for detecting arbitrary sampled point is less than the first predetermined threshold value
When, to lighting from arbitrary sampling, the continuous sampled point quantity less than the first predetermined threshold value is counted；When statistical result reach it is pre-
If during quantity, acquisition statistical result reaches last sampled point during predetermined number, determines pedestrian in last sampled point
It is upper to stop movement.Wherein, predetermined number is configured also dependent on practical situation, and the present embodiment is not especially limited to this.
For example, with the first predetermined threshold value as 1.5m/s2, predetermined number is for as a example by 30.If detecting the 10th sampled point
Acceleration be less than 1.5m/s2, then continue to detect the 11st, the 12nd ..., the acceleration of the 40th sampled point.When the 10th
The acceleration of continuous 30 sampled points is both less than 1.5m/s after individual sampled point2When, i.e., when the 11st, the 12nd ..., the 40th
The acceleration of sampled point is less than 1.5m/s2When, last sampled point when acquisition has reached 30 sampled points, i.e., the 40th
Sampled point.Correspondingly, on the 40th sampled point, pedestrian stops movement.
It is determined that pedestrian start it is mobile and stop it is mobile after, it may be determined that pedestrian stops mobile this period from beginning to move into
The total step number of interior walking.The present embodiment pair do not determine pedestrian from begin to move into stop it is mobile between the mode of total step number make to have
Body is limited, including but not limited to：For pedestrian is from the arbitrary sampled point stopped in mobile this period is begun to move into, work as detection
Acceleration to arbitrary sampled point is more than the second predetermined threshold value, and the corresponding acceleration of next sampled point of arbitrary sampled point is less than
During the second predetermined threshold value, next sampled point of a upper sampled point, arbitrary sampled point and arbitrary sampled point of arbitrary sampled point is made
For a paces cycle, and the total step number of pedestrian is added one.
Due to people when walking, acceleration of the one leg when carrying away is larger, and prepares to accelerate during landing after carrying away
Degree is less, so as to be based on above-mentioned principle, continuous two sampled points can be detected in above process.Two are adopted
Sampling point is compared with the second predetermined threshold value, when previous sampled point is more than the second predetermined threshold value and latter sampled point is less than the
During two predetermined threshold values, can be considered that pedestrian has walked a step.It is more than the sampled point of the second predetermined threshold value accordingly for acceleration, when
When the corresponding acceleration of next sampled point of the sampled point is less than the second predetermined threshold value, can be by a upper sampled point to next sampled point
Between this period as a paces cycle.For example, if the acceleration of the 3rd sampled point is more than the second predetermined threshold value and the
The acceleration of 4 sampled points is less than the second predetermined threshold value, then can be by the 2nd sampled point, the 3rd sampled point and the 4th sampled point
As a paces cycle, and it is considered as pedestrian and has walked a step within this paces cycle.Correspondingly, total step number can add one.Need
Illustrate, the initial value of total step number is 0 before statistics total step number.
In addition, it is determined that before total step number, the acceleration correlation in the cycle can be also cut down according to previous step, calculating second is pre-
If threshold value, the present embodiment is not especially limited to this.According to the experimental result to pedestrian's dead reckoning, the second predetermined threshold value can lead to
Cross dynamic threshold equation to calculate, the dynamic threshold equation (1) is as follows：
Wherein, α and β are the parameters for pre-setting, and can distinguish value for 0.25 and 0.75, and the present embodiment is not made to have to this
Body is limited.γ be environment noise variance, can value be 0.09, the present embodiment is also not especially limited to this.ToldCut down for previous step
Second predetermined threshold value in cycle, A1And A2For acceleration correlation.A1And A2Each can represent previous step and cut down acceleration in the cycle
Maximum and minima, A1And A2Can also be the average or variance of acceleration, the present embodiment is not especially limited to this.
Wherein, 202 the position before the movement of step-length, steering angle and pedestrian, for each step of pedestrian's movement, according to pedestrian
Information, calculates the positional information that pedestrian is moved after moving a step, until calculation times reach total step number, using final calculation result as row
The positional information of people.
Before this step is performed, the steering of the positional information before step-length, pedestrian's movement of pedestrian and pedestrian can be first obtained
Angle.Wherein, the step-length of pedestrian is estimated that the present embodiment is not especially limited to this according to pedestrian's height.Due to the present embodiment
The method of offer is iterative process, i.e., the side that the positional information before the last movement of pedestrian also can be provided by the present embodiment
Method obtaining, so as to the method institute that last time performs the present embodiment offer in the positional information before obtaining pedestrian's movement, can be obtained
Corresponding result of calculation.It should be noted that when first time indoor positioning is carried out to pedestrian, initial position can be according to reality
Border situation is configured, and the present embodiment is not especially limited to this.
Further, since what pedestrian was possible to do when mobile is curvilinear motion, so as in order to more accurately to pedestrian position
Put and be predicted, the steering angle of pedestrian can also be obtained.Mode of the present embodiment not to obtaining the steering angle of pedestrian makees concrete limit
It is fixed, including but not limited to：Based on space coordinates, current pedestrian angular acceleration in three directions is obtained；Sat based on space
Projection relation between mark system and earth axes, according to current pedestrian angular acceleration in three directions and acceleration, meter
Calculate the steering angle of pedestrian.
Wherein, the angular velocity on three directions of XYZ axles can be divided into according to space coordinates.Angular acceleration on three directions
Can be obtained by the gyroscope in mobile terminal, the present embodiment is not especially limited to this.In the steering angle for calculating pedestrian
Before, the angular displacement on three directions, the present embodiment can be calculated according to the angular acceleration on three directions by way of integration
This is not especially limited.Integral process refers to equation below (2)：
Wherein,AndAngular acceleration respectively on tri- directions of XYZ.tbeginFor move move a step it is initial when
Carve, tstopTo move the end time for moving a step.θx、θyAnd θzAngular displacement respectively on tri- directions of XYZ.
If it should be noted that when the angular displacement on tri- directions of XYZ in a time window is smaller, such as less than
Angle threshold, then can be considered that pedestrian makees in this time window is linear motion.For example, so that angle threshold is for 15 ° as an example.
Angular displacement on tri- directions of XYZ in a time windowx、θyAnd θzWhen respectively less than 15 °, then can determine that pedestrian at this
What is made in time window is linear motion.
Based on above-mentioned principle, pedestrian can calculate the acceleration arithmetic average on three directions during straight line moving
Value.Correspondingly, the steering of pedestrian can according to current pedestrian angular displacement in three directions and acceleration arithmetic mean of instantaneous value, be calculated
Angle, the present embodiment is not especially limited to this.Above-mentioned calculating process, can pass through pedestrian's dead reckoning model (3) being defined as below
It is indicated：
Wherein, OzFor the steering angle of pedestrian.θx、θyAnd θzAngular displacement on respectively three directions.AndPoint
Acceleration arithmetic mean of instantaneous value that Wei be on three directions.
After the steering angle of pedestrian is calculated, for each step of pedestrian's movement, can be according to the step-length of pedestrian, steering angle
And the positional information before pedestrian's movement, calculate the positional information that pedestrian is moved after moving a step.The calculating process refers to equation below
(4)：
Wherein, lkFor the step-length of pedestrian.Based on earth axes, xk-1And yk-1It is that position of the pedestrian before shifting moves a step is believed
Breath, xkAnd ykThe positional information after moving a step is being moved for pedestrian.
Based on the total step number determined in above-mentioned steps 201, can determine that pedestrian is walking so multistep according to above-mentioned formula (4)
Positional information afterwards, that is, predict the pedestrian position information for obtaining.
It should be noted that the positional information of the mainly pedestrian based on earth axes of said process prediction.Due to
When carrying out indoor positioning to pedestrian, it may be desirable to which the floor of the building that is located to it is positioned, so as to predict the row for obtaining
People's positional information can also include the floor that pedestrian is located.The present embodiment additionally provides a kind of side of determination pedestrian place floor
Method, including but not limited to：According to the air pressure value of pedestrian present position, the floor residing for pedestrian is determined.
Due to being inversely proportional to into height in earth atmosphere inner air pressure, i.e., when height increases, air pressure can be reduced,
Such that it is able to the air pressure obtained using barometric surveying, height that pedestrian is located is calculated.According to the layer of pedestrian place building
The high height being located with pedestrian, it may be determined that the floor that pedestrian is located, the present embodiment is not especially limited to this.Based on ICAO
(International Civil Aviation Organization, International Civil Aviation Organization) model, would know that height is every
Increase about 8.7 meters of atmospheric pressures and reduce 1mbar.According to the normal atmospheric pressure of 1993, calculating the height at pedestrian place can join
Examine equation below (5)：
Wherein, P0That what is represented is normal atmospheric pressure (1013.25mbar).H is the height that pedestrian is located, and unit is rice.
Wherein, 203, based on indoor sport model, the indoor sport state of pedestrian is obtained.
Before this step is performed, motor habit that can be first according to pedestrian indoors determines pedestrian's kinestate indoors,
The present embodiment is not especially limited to this.In the present embodiment, the kinestate of pedestrian is divided into into 7 according to real life scene
It is individual, respectively：Walk, sit down, standing, upstairs, downstairs, turn and U-shaped turning.
Wherein, the motion feature walking, sit down, standing, being in pedestrian's moving process upstairs and downstairs.Turn and U-shaped
Turn be pedestrian in moving process turning feature.Because pedestrian is when turning, it may be possible to which the little turning of adjustment direction also has
The big turning possibly turned around, so as in order to distinguish both turnings, when above-mentioned turning feature is divided, division is in order to turn and U
Type is turned.When judging to turn with U-shaped turning, can according to angle of turn of the pedestrian in time window and preset threshold range it
Between comparative result judging.For example, when angle of turn is at 50 °～135 °, it is believed that be a common turning.Work as turning angle
When degree is more than 135 °, it is believed that be a u turn.
Based on the above, this step when the indoor design condition of pedestrian is obtained, can obtain respectively pedestrian motion feature and
Turning feature.Not to being based on indoor sport model, the mode for obtaining the motion feature of pedestrian makees concrete restriction to the present embodiment, including
But it is not limited to：According to the acceleration of each sampled point in very first time window, the corresponding eigenvalue of very first time window is calculated；Base
In kinestate grader, according to the corresponding eigenvalue of very first time window, the motion feature of pedestrian is determined.
Wherein, kinestate grader can be instructed by KNN (k-Nearest-Neighbor, K arest neighbors) grader
Practice, the present embodiment is not especially limited to this.The experimenter that specifically can first choose predetermined number puts into practice above-mentioned five kinds of motions spy
Levy, that is, walk, sit down, standing, upstairs and downstairs, and obtain eigenvalue of the experimenter when motion feature is put into practice.By inciting somebody to action
A kind of eigenvalue of motion feature and each experimenter when the motion feature is put into practice every time is input into into KNN models, to KNN
Model is ceaselessly trained, till frequency of training reaches preset times.Finally, can be moved according to training result
State classifier and Motion Recognition probability matrix.Wherein, kinestate grader is used to determine pedestrian according to the eigenvalue of input
Motion feature.
Motion Recognition probability matrix is identified pair of every kind of motion feature of pedestrian and is identified as other motion features
Probability matrix.For example, so that the current motion feature of pedestrian is actually " sitting down " as an example.Based on kinestate grader, root
Can recognize that the motion feature of the pedestrian is " sitting down " really according to the eigenvalue of input.Now, recognition result be it is correct, this
Correspond to a probability.But originally it is " sitting down ", it is also possible to be identified as " walking ".Now, recognition result be it is wrong, this
Also correspond to a probability.Based on above-mentioned theory, by ceaselessly training to KNN models, kinestate grader is being obtained
At the same time it can also obtain Motion Recognition probability matrix.
Correspondingly, after kinestate grader is obtained, only pedestrian need to be obtained in the corresponding eigenvalue of very first time window,
Just kinestate grader can be based on, the motion feature of pedestrian is determined.Wherein, eigenvalue can according in very first time window each
The acceleration of sampled point is calculated, and the present embodiment is not especially limited to this.Eigenvalue can be included in very first time window
Amplitude of acceleration etc., the present embodiment pair on the average of acceleration and variance, air pressure value and three directions on three directions
This is not especially limited.The length of very first time window can take 2s～3s, and the present embodiment is not especially limited to this.Consider
The seriality of action when pedestrian walks, very first time window may be arranged as 50% overlap and cover, and the present embodiment is to this
It is not especially limited.For example, very first time window can with value as 0s～2s, 1s～3s, 2s～4s ....
Motion feature except determining pedestrian, this can determine the turning feature of pedestrian.The present embodiment pair does not determine pedestrian
The mode of turning feature make concrete restriction, including but not limited to：According to the steering angle of the second time window one skilled in the art, row is calculated
The angle of turn of people；According to the angle of turn of pedestrian, the turning feature of pedestrian is determined.
Wherein, the length of the second time window can also take 2s～3s, and the present embodiment is not especially limited to this.In addition,
Very first time window can be with identical with the length of the second time window, it is also possible to different, and the present embodiment does not make concrete limit to this yet
It is fixed.Specifically when the angle of turn of pedestrian is calculated, the first steering angle of the second time window initial time can be first calculated, then be calculated
Second steering angle of the second time window end time.Using the difference between the first steering angle and the second steering angle as pedestrian's
Angle of turn.Wherein, the process for calculating steering angle refers to the process of above-mentioned formula (3), and here is omitted.
For example, with the second time window length as 2s, the second time window is as a example by 1s～3s.In the turning for calculating pedestrian
During angle, the steering angle of pedestrian when can first calculate 1s, then when calculating 3s pedestrian steering angle, so as to by the difference of two steering angles
As the angle of turn of pedestrian.
By said process, the motion feature and turning feature of pedestrian may finally be obtained.Wherein, motion feature is row
Walk, sit down, standing, upstairs and downstairs in one kind, turning be characterized as turning and U-shaped turning in one kind.It is movement character combined
And turning feature, you can obtain the indoor sport state of pedestrian.
Wherein, 204, based on indoor environment cartographic model, according to indoor sport state and the position letter of indoor default node
Breath, calibrates to the pedestrian position information that prediction is obtained, and obtains the final position information of pedestrian.
Because above-mentioned steps 201 predict that the pedestrian position information for obtaining may have certain error into step 202,
So as to preset the positional information of node in being based on indoor environment cartographic model in this step, in step 201 to step 202
The pedestrian position information that prediction is obtained is calibrated.The present embodiment not to based on indoor environment cartographic model, according to indoor sport
The positional information of state and indoor default node, calibrates to the pedestrian position information that prediction is obtained, and obtains the final of pedestrian
The mode of positional information makees concrete restriction, including but not limited to：Based on indoor environment cartographic model, determine that pedestrian is moved to interior
The movement probability of adjacent default node in environmental map model；The movement probability of each adjacent default node is ranked up, is selected
Take two maximum movement probabilities of numerical value, respectively the first movement probability and the second movement probability in ranking results, the first movement
Probability is more than the second movement probability；When the ratio of the first movement probability and the second movement probability is more than three predetermined threshold values, will
Final position information of the positional information of the corresponding adjacent default node of the first movement probability as pedestrian.
Wherein, indoor environment cartographic model is to be obtained by real life scenario building.Specifically, stair in a solitary building
The position of the node such as corner point and passageway corner point typically can be predetermined.According to the node coordinate of each node, each
Direction and distance, pedestrian's kinestate on each node between node and its adjacent node that spatially can go directly, can
Set up indoor environment cartographic model.
Based on indoor environment cartographic model, determine that pedestrian is moved to adjacent default node in indoor environment cartographic model
Before movement probability, the positional information before pedestrian's movement can be first obtained.From above-mentioned steps 201 to the content in step 204,
Because the method that the present embodiment is provided is iterative calculation, i.e., continue deduction pedestrian according to last result of calculation and move next time
Positional information after dynamic, so as to this step is in the positional information before obtaining pedestrian's movement, can obtain the last time by this enforcement
The calculated pedestrian position information of method that example is provided, the present embodiment is not especially limited to this.
It is determined that after the positional information before pedestrian's movement, according to the position of each default node in indoor environment cartographic model
Information, it may be determined that position of the pedestrian from before movement can directly reach which the default node in indoor environment cartographic model.
These default nodes are the adjacent default node corresponding to the position before pedestrian's movement.Based on the above, for arbitrary phase
The default node of neighbour, the present embodiment pair does not determine that pedestrian is moved to the movement probability of adjacent default node in indoor environment cartographic model
Mode make concrete restriction, including but not limited to：Arbitrary adjacent default node in indoor environment cartographic model, according to arbitrary
The positional information of adjacent default node, calculates the emission probability that pedestrian is moved to arbitrary adjacent default node；According to Motion Recognition
Probability matrix, the kinestate for determining arbitrary adjacent default node shows as the state recognition probability of indoor sport state；To send out
The product penetrated between probability and state recognition probability is moved to the movement probability of arbitrary adjacent default node as pedestrian.
Wherein, emission probability is by the probability of hidden state one observer state of generation, the position before pedestrian's movement
Information is a hidden state, and the positional information of adjacent default node is observer state.Calculate emission probability when, refer to as
Lower formula (6)：
In above-mentioned formula (6), P (zt|ri) it is emission probability.ztFor the positional information of adjacent default node, riFor pedestrian
Positional information before movement, zt-riRepresent Euclidean distance between the two.σ for pedestrian's displacement value of calculation standard deviation, this reality
The value for applying σ in example is 0.1.
Based on the related content of Motion Recognition probability matrix in above-mentioned steps 203, for arbitrary adjacent default node, true
When the kinestate of the fixed adjacent default node shows as the state recognition probability of indoor sport state, can be according to indoor sport shape
The motion feature of motion feature and the adjacent default node in state, in Motion Recognition probability matrix corresponding probability is searched.Will
The probability for finding is used as state recognition probability.
In addition, in the movement that arbitrary adjacent default node is moved to according to emission probability and state recognition probability calculation pedestrian
During probability, calculating process refers to equation below (7)：
P(zt,mt|ri)=P (zt|ri)P(mt|ri) (7)
Wherein, P (zt|ri) be emission probability, P (mt|ri) be state recognition probability, P (zt,mt|ri) it is movement probability.
Due to move with pedestrian in environmental map model indoors the adjacent default node in front position might have it is multiple, from
And the movement probability of each adjacent default node according to above-mentioned calculating process, can be calculated.After multiple movement probabilities are calculated,
All of movement probability can be ranked up, two maximum movement probabilities of numerical value are chosen from ranking results, be calculated as the first shifting
Dynamic probability and the second movement probability.Wherein, the first movement probability is mobile general more than the second movement probability, i.e. the first movement probability
Maximum in rate, the second movement probability is the second largest value in movement probability.
For the positional information for more accurately determining pedestrian, the ratio of the first movement probability and the second movement probability can be calculated
Value.When ratio is more than three predetermined threshold values, illustrate that pedestrian is moved to the corresponding adjacent default node of the first movement probability can
Energy property, is significantly larger than moved to the probability of the corresponding adjacent default node of the second movement probability.Thus, it is believed that pedestrian's movement
During adjacent default node corresponding to the first movement probability, credibility is higher.Now, can be corresponding adjacent by the first movement probability
The positional information of default node and is abandoned the position for obtaining is predicted in above-mentioned steps 201 to 202 as the final position information of pedestrian
Confidence ceases.
In addition, when the ratio of the first movement probability and the second movement probability is not more than three predetermined threshold values, can will be above-mentioned
Step 201 predicts the pedestrian position information that obtains as the final position information of pedestrian into 202.
Method provided in an embodiment of the present invention, by determining pedestrian from the total step number begun to move between stopping movement.
For each step of pedestrian's movement, the positional information before the movement of step-length, steering angle and pedestrian according to pedestrian, pedestrian's movement is calculated
Positional information after one step, until calculation times reach total step number, using final calculation result as pedestrian positional information.It is based on
Indoor sport model, obtains the indoor sport state of pedestrian.Based on indoor environment cartographic model, according to indoor sport state and room
The positional information of interior default node, calibrates to the pedestrian position information that prediction is obtained, and obtains the final position information of pedestrian.
Due to without installing external equipment, disappearing so as to while the system for avoiding design complexities higher, can also reduce hardware cost
Consumption, and then the cost for causing to be expended during indoor positioning is relatively low.
Further, since when carrying out motion feature classification, have chosen accelerometer, barometer and gyro data, improve
Accuracy when motion feature is classified, while the appearance of long-time cumulative error can be avoided.Because position fixing process navigates pedestrian
Position speculates that algorithm, indoor pedestrian movement's feature and HMM matching process are combined togather, so as to ensure
While located higher accuracy rate, the robustness of indoor positioning can also be lifted.
A kind of indoor positioning device is embodiments provided, the device is used to perform the corresponding realities of above-mentioned Fig. 1 or Fig. 2
Apply the indoor orientation method provided in example.Referring to Fig. 3, the device includes：
Prediction module 301, for the data collected according to multiple sensor, predicts the positional information of pedestrian；
Acquisition module 302, for based on indoor sport model, obtaining the indoor sport state of pedestrian；
Calibration module 303, for based on indoor environment cartographic model, according to the default node of indoor sport state and interior
Positional information, calibrates to the pedestrian position information that prediction is obtained, and obtains the final position information of pedestrian.
As a kind of alternative embodiment, prediction module 301, including：
Determining unit, for determining pedestrian from the total step number begun to move between stopping movement；
First computing unit, for each step moved for pedestrian, step-length, the steering angle and pedestrian movement according to pedestrian
Front positional information, calculates the positional information that pedestrian is moved after moving a step, and until calculation times reach total step number, will finally calculate knot
Positional information of the fruit as pedestrian.
As a kind of alternative embodiment, prediction module 301, also include：
Detector unit, detects for according to the acceleration of each sampled point, starting mobile and stopping movement to pedestrian.
As a kind of alternative embodiment, detector unit, for for arbitrary sampled point, when detect arbitrary sampled point plus
When speed is not less than the first predetermined threshold value, it is determined that pedestrian starts movement on arbitrary sampled point.
As a kind of alternative embodiment, detector unit, for for arbitrary sampled point, when detect arbitrary sampled point plus
When speed is less than the first predetermined threshold value, to lighting from arbitrary sampling, the continuous sampled point quantity less than the first predetermined threshold value is carried out
Statistics；When statistical result reaches predetermined number, acquisition statistical result reaches last sampled point during predetermined number, it is determined that
Pedestrian stops movement on last sampled point.
As a kind of alternative embodiment, determining unit, for moving this period from stopping is begun to move into for pedestrian
Interior arbitrary sampled point, when detecting the acceleration of arbitrary sampled point more than the second predetermined threshold value, and arbitrary sampled point is next
The corresponding acceleration of sampled point be less than the second predetermined threshold value when, by a upper sampled point of arbitrary sampled point, arbitrary sampled point and appoint
The total step number of pedestrian is added one by next sampled point of one sampled point as a paces cycle.
As a kind of alternative embodiment, prediction module 301, also include：
Second computing unit, for cutting down the acceleration correlation in the cycle according to previous step, calculates the second predetermined threshold value.
As a kind of alternative embodiment, prediction module 301, also include：
Acquiring unit, for based on space coordinates, obtaining current pedestrian angular acceleration in three directions；
3rd computing unit, for based on the projection relation between space coordinates and earth axes, according to current line
People's angular acceleration in three directions and acceleration, calculate the steering angle of pedestrian.
As a kind of alternative embodiment, prediction module 301, for according to the air pressure value of pedestrian present position, it is determined that
Floor residing for pedestrian.
As a kind of alternative embodiment, acquisition module 302, for according to the acceleration of each sampled point in very first time window
Degree, calculates the corresponding eigenvalue of very first time window；Based on kinestate grader, according to the corresponding feature of very first time window
Value, determines the motion feature of pedestrian.
As a kind of alternative embodiment, acquisition module 302, for according to the steering angle of the second time window one skilled in the art, meter
Calculate the angle of turn of pedestrian；According to the angle of turn of pedestrian, the turning feature of pedestrian is determined.
As a kind of alternative embodiment, calibration module 303, including：
Determining unit, for based on indoor environment cartographic model, determining that pedestrian is moved to phase in indoor environment cartographic model
The movement probability of the default node of neighbour；
Unit is chosen, for the movement probability of each adjacent default node to be ranked up, numerical value in ranking results is chosen
Two maximum movement probabilities, respectively the first movement probability and the second movement probability, the first movement probability is more than the second movement
Probability；
First comparing unit, for being more than the 3rd predetermined threshold value when the ratio of the first movement probability and the second movement probability
When, using the positional information of the corresponding adjacent default node of the first movement probability as pedestrian final position information.
As a kind of alternative embodiment, determining unit, for arbitrary adjacent default section in indoor environment cartographic model
Point, according to the positional information of arbitrary adjacent default node, calculates the emission probability that pedestrian is moved to arbitrary adjacent default node；Root
According to Motion Recognition probability matrix, the kinestate for determining arbitrary adjacent default node shows as the state recognition of indoor sport state
Probability；Product between emission probability and state recognition probability is general as the movement that pedestrian is moved to arbitrary adjacent default node
Rate.
As a kind of alternative embodiment, calibration module 303, also include：
Second comparing unit, for being not more than the 3rd predetermined threshold value when the ratio of the first movement probability and the second movement probability
When, final position information of the pedestrian position information that prediction is obtained as pedestrian.
Device provided in an embodiment of the present invention, by the data collected according to multiple sensor, predicts the position of pedestrian
Information.Based on indoor sport model, the indoor sport state of pedestrian is obtained.Based on indoor environment cartographic model, according to indoor fortune
The positional information of dynamic state and indoor default node, calibrates to the pedestrian position information that prediction is obtained, and obtains pedestrian most
Whole positional information.Due to without installing external equipment, so as to while the system for avoiding design complexities higher, also reduce
Hardware cost is consumed, and then the cost for causing to be expended during indoor positioning is relatively low.
Further, since when carrying out motion feature classification, have chosen accelerometer, barometer and gyro data, improve
Accuracy when motion feature is classified, while the appearance of long-time cumulative error can be avoided.Because position fixing process navigates pedestrian
Position speculates that algorithm, indoor pedestrian movement's feature and HMM matching process are combined togather, so as to ensure
While located higher accuracy rate, the robustness of indoor positioning can also be lifted.
Finally, the present processes are only preferably embodiment, are not intended to limit protection scope of the present invention.It is all
Within the spirit and principles in the present invention, any modification, equivalent substitution and improvements made etc. should be included in the protection of the present invention
Within the scope of.
Claims (7)
1. a kind of indoor orientation method, it is characterised in that methods described includes：
According to the data that multiple sensor is collected, the positional information of pedestrian is predicted；
Based on indoor sport model, the indoor sport state of the pedestrian is obtained；
Based on indoor environment cartographic model, according to the indoor sport state and the positional information of indoor default node, to prediction
The pedestrian position information for obtaining is calibrated, and obtains the final position information of the pedestrian.
2. method according to claim 1, it is characterised in that described based on indoor sport model, obtains the pedestrian's
Indoor sport state, including：
According to the acceleration of each sampled point in very first time window, the corresponding eigenvalue of the very first time window is calculated；
Based on kinestate grader, according to the corresponding eigenvalue of the very first time window, determine that the motion of the pedestrian is special
Levy.
3. method according to claim 1, it is characterised in that described based on indoor sport model, obtains the pedestrian's
Indoor sport state, including：
According to the steering angle of the pedestrian in the second time window, the angle of turn of the pedestrian is calculated；
According to the angle of turn of the pedestrian, the turning feature of the pedestrian is determined.
4. method according to claim 1, it is characterised in that described based on indoor environment cartographic model, according to the room
The positional information of interior kinestate and indoor default node, calibrates to the pedestrian position information that prediction is obtained, and obtains described
The final position information of pedestrian, including：
Based on indoor environment cartographic model, determine that the pedestrian is moved to adjacent default node in the indoor environment cartographic model
Movement probability；
The movement probability of each adjacent default node is ranked up, two maximum movements of numerical value in ranking results is chosen general
Rate, respectively the first movement probability and the second movement probability, first movement probability is more than second movement probability；
It is when the ratio of first movement probability and the second movement probability is more than three predetermined threshold values, the described first movement is general
Final position information of the positional information of the corresponding adjacent default node of rate as the pedestrian.
5. method according to claim 4, it is characterised in that described based on indoor environment cartographic model, determines the row
People is moved to the movement probability of adjacent default node in the indoor environment cartographic model, including：
For arbitrary adjacent default node in the indoor environment cartographic model, according to the position of arbitrary adjacent default node
Information, calculates the emission probability that the pedestrian is moved to arbitrary adjacent default node；
According to Motion Recognition probability matrix, the kinestate for determining arbitrary adjacent default node shows as the indoor sport
The state recognition probability of state；
Product between the emission probability and the state recognition probability is moved to as the pedestrian described arbitrary adjacent
The movement probability of default node.
6. method according to claim 4, it is characterised in that the movement probability by each adjacent default node is carried out
Sequence, chooses two maximum movement probabilities of numerical value in ranking results, respectively the first movement probability and the second movement probability it
Afterwards, also include：
When the ratio of first movement probability and the second movement probability is not more than three predetermined threshold values, the row that prediction is obtained
Final position information of people's positional information as the pedestrian.
7. a kind of indoor positioning device, it is characterised in that described device includes：
Prediction module, for the data collected according to multiple sensor, predicts the positional information of pedestrian；
Acquisition module, for based on indoor sport model, obtaining the indoor sport state of the pedestrian；
Calibration module, for based on indoor environment cartographic model, according to the indoor sport state and the position of indoor default node
Confidence ceases, and the pedestrian position information that prediction is obtained is calibrated, and obtains the final position information of the pedestrian.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611070529.6A CN106595633B (en) | 2016-11-25 | 2016-11-25 | Indoor orientation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611070529.6A CN106595633B (en) | 2016-11-25 | 2016-11-25 | Indoor orientation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106595633A true CN106595633A (en) | 2017-04-26 |
| CN106595633B CN106595633B (en) | 2019-07-19 |
Family
ID=58595552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611070529.6A Active CN106595633B (en) | 2016-11-25 | 2016-11-25 | Indoor orientation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106595633B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107063268A (en) * | 2017-06-05 | 2017-08-18 | 合肥展游软件开发有限公司 | A kind of museum's navigation system and application method |
| CN107356229A (en) * | 2017-07-07 | 2017-11-17 | 中国电子科技集团公司电子科学研究院 | A kind of indoor orientation method and device |
| CN108645406A (en) * | 2018-04-19 | 2018-10-12 | 北京理工大学 | A kind of indoor autonomic positioning method based on score field pedestrian movement perception |
| CN109413683A (en) * | 2017-08-15 | 2019-03-01 | 华为技术有限公司 | A kind of method and apparatus obtaining emission probability, transition probability and sequence positioning |
| CN109991641A (en) * | 2019-04-10 | 2019-07-09 | 广东工业大学 | A kind of acquisition methods, the apparatus and system of position of mobile equipment information |
| CN111854753A (en) * | 2020-06-02 | 2020-10-30 | 深圳全景空间工业有限公司 | Indoor space modeling method |
| US11085992B2 (en) | 2017-06-30 | 2021-08-10 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for positioning a terminal device |
| CN115223442A (en) * | 2021-07-22 | 2022-10-21 | 上海数川数据科技有限公司 | Automatic generation method of indoor pedestrian map |
| CN115336936A (en) * | 2021-05-12 | 2022-11-15 | 尚科宁家(中国)科技有限公司 | Floor-crossing control method for cleaning robot and cleaning robot |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110141485A1 (en) * | 2009-12-16 | 2011-06-16 | Industrial Technology Research Institute | System and Method for Localizing a Carrier, Estimating a Posture of the Carrier and Establishing a Map |
| CN102821464A (en) * | 2012-08-13 | 2012-12-12 | 北京邮电大学 | Indoor storey positioning method and device |
| CN103701991A (en) * | 2013-12-20 | 2014-04-02 | 百度在线网络技术（北京）有限公司 | Mobile terminal state recognition method and mobile terminal |
| CN104215238A (en) * | 2014-08-21 | 2014-12-17 | 北京空间飞行器总体设计部 | Indoor positioning method of intelligent mobile phone |
| CN104977006A (en) * | 2015-08-11 | 2015-10-14 | 北京纳尔信通科技有限公司 | Indoor positioning method based on fuzzy theory and multi-sensor fusion |
| CN105004343A (en) * | 2015-07-27 | 2015-10-28 | 上海美琦浦悦通讯科技有限公司 | Indoor wireless navigation system and method |
| CN105509736A (en) * | 2015-12-03 | 2016-04-20 | 北京机械设备研究所 | Indoor composite locating method for fire rescue |
-
2016
- 2016-11-25 CN CN201611070529.6A patent/CN106595633B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110141485A1 (en) * | 2009-12-16 | 2011-06-16 | Industrial Technology Research Institute | System and Method for Localizing a Carrier, Estimating a Posture of the Carrier and Establishing a Map |
| CN102821464A (en) * | 2012-08-13 | 2012-12-12 | 北京邮电大学 | Indoor storey positioning method and device |
| CN103701991A (en) * | 2013-12-20 | 2014-04-02 | 百度在线网络技术（北京）有限公司 | Mobile terminal state recognition method and mobile terminal |
| CN104215238A (en) * | 2014-08-21 | 2014-12-17 | 北京空间飞行器总体设计部 | Indoor positioning method of intelligent mobile phone |
| CN105004343A (en) * | 2015-07-27 | 2015-10-28 | 上海美琦浦悦通讯科技有限公司 | Indoor wireless navigation system and method |
| CN104977006A (en) * | 2015-08-11 | 2015-10-14 | 北京纳尔信通科技有限公司 | Indoor positioning method based on fuzzy theory and multi-sensor fusion |
| CN105509736A (en) * | 2015-12-03 | 2016-04-20 | 北京机械设备研究所 | Indoor composite locating method for fire rescue |
Non-Patent Citations (2)
| Title |
|---|
| CHENGKAI HUANG 等: "Smartphone based Indoor Position and Orientation Tracking Fusing Inertial and Magnetic Sensing", 《17TH INTERNATIONAL SYMPOSIUM ON WIRELESS PERSONAL MULTIMEDIA COMMUNICATIONS》 * |
| 闫亭亭: "基于粒子滤波的智能移动终端室内定位方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107063268A (en) * | 2017-06-05 | 2017-08-18 | 合肥展游软件开发有限公司 | A kind of museum's navigation system and application method |
| US11085992B2 (en) | 2017-06-30 | 2021-08-10 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for positioning a terminal device |
| CN107356229A (en) * | 2017-07-07 | 2017-11-17 | 中国电子科技集团公司电子科学研究院 | A kind of indoor orientation method and device |
| CN109413683A (en) * | 2017-08-15 | 2019-03-01 | 华为技术有限公司 | A kind of method and apparatus obtaining emission probability, transition probability and sequence positioning |
| US11290975B2 (en) | 2017-08-15 | 2022-03-29 | Huawei Technologies Co., Ltd. | Method and apparatus for obtaining emission probability, method and apparatus for obtaining transition probability, and sequence positioning method and apparatus |
| US12047902B2 (en) | 2017-08-15 | 2024-07-23 | Huawei Technologies Co., Ltd. | Method and apparatus for obtaining emission probability, method and apparatus for obtaining transition probability, and sequence positioning method and apparatus |
| CN108645406A (en) * | 2018-04-19 | 2018-10-12 | 北京理工大学 | A kind of indoor autonomic positioning method based on score field pedestrian movement perception |
| CN109991641A (en) * | 2019-04-10 | 2019-07-09 | 广东工业大学 | A kind of acquisition methods, the apparatus and system of position of mobile equipment information |
| CN111854753A (en) * | 2020-06-02 | 2020-10-30 | 深圳全景空间工业有限公司 | Indoor space modeling method |
| CN115336936A (en) * | 2021-05-12 | 2022-11-15 | 尚科宁家(中国)科技有限公司 | Floor-crossing control method for cleaning robot and cleaning robot |
| CN115223442A (en) * | 2021-07-22 | 2022-10-21 | 上海数川数据科技有限公司 | Automatic generation method of indoor pedestrian map |
| CN115223442B (en) * | 2021-07-22 | 2024-04-09 | 上海数川数据科技有限公司 | Automatic generation method of indoor pedestrian map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106595633B (en) | 2019-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106595633A (en) | Indoor positioning method and device | |
| US9146113B1 (en) | System and method for localizing a trackee at a location and mapping the location using transitions | |
| KR101851836B1 (en) | Systems and methods for estimating the motion of an object | |
| Shi et al. | A robust pedestrian dead reckoning system using low-cost magnetic and inertial sensors | |
| CA2653622C (en) | Method and system for locating and monitoring first responders | |
| US9807725B1 (en) | Determining a spatial relationship between different user contexts | |
| Shin et al. | Indoor 3D pedestrian tracking algorithm based on PDR using smarthphone | |
| CN104977006A (en) | Indoor positioning method based on fuzzy theory and multi-sensor fusion | |
| Ladetto et al. | In step with INS navigation for the blind, tracking emergency crews | |
| CN110686671B (en) | Indoor 3D real-time positioning method and device based on multi-sensor information fusion | |
| JP2013531781A (en) | Method and system for detecting zero speed state of object | |
| CN110579211B (en) | Walking positioning method and system | |
| Wang et al. | Recent advances in pedestrian inertial navigation based on smartphone: A review | |
| Hasan et al. | Smart phone based sensor fusion by using Madgwick filter for 3D indoor navigation | |
| Saadatzadeh et al. | An improvement in smartphone-based 3D indoor positioning using an effective map matching method | |
| US10883833B2 (en) | Methods and systems for determining vertical location in enclosed spaces | |
| Gu et al. | Half-voting random forest algorithm and its application in indoor pedestrian navigation | |
| Terra et al. | Traveled distance estimation algorithm for indoor localization | |
| Li et al. | A robust humanoid robot navigation algorithm with ZUPT | |
| JP2020085783A (en) | Pedestrian-purpose positioning device, pedestrian-purpose positioning system, and pedestrian-purpose positioning method | |
| Li et al. | Sensor fusion-based infrastructure independent and agile real-time indoor positioning technology for disabled and elderly people | |
| Gao et al. | Mapless Indoor Navigation Based on Landmarks | |
| Kröger et al. | Method of pedestrian dead reckoning using speed recognition | |
| Anacleto et al. | Providing location everywhere | |
| Tsubouchi et al. | Enhancing indoor altitude estimation on smartphones: Resolving ventilation fan effects |
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 |