CN106595633B - Indoor orientation method and device - Google Patents
Indoor orientation method and device Download PDFInfo
- Publication number
- CN106595633B CN106595633B CN201611070529.6A CN201611070529A CN106595633B CN 106595633 B CN106595633 B CN 106595633B CN 201611070529 A CN201611070529 A CN 201611070529A CN 106595633 B CN106595633 B CN 106595633B
- Authority
- CN
- China
- Prior art keywords
- pedestrian
- indoor
- probability
- position information
- moving
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 230000033001 locomotion Effects 0.000 claims description 227
- 238000005070 sampling Methods 0.000 claims description 96
- 230000001133 acceleration Effects 0.000 claims description 62
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 10
- 238000005516 engineering process Methods 0.000 abstract description 16
- 238000013461 design Methods 0.000 abstract description 7
- 238000009434 installation Methods 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 21
- 238000006073 displacement reaction Methods 0.000 description 6
- 238000001514 detection method Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000474 nursing effect Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
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 present invention provides a kind of indoor orientation method and device, belongs to indoor positioning technologies field.Method includes: to predict the location information of pedestrian according to the collected data of multiple sensor；Based on indoor sport model, the indoor sport state of pedestrian is obtained；Based on indoor environment cartographic model, is calibrated according to indoor sport state and the location information of indoor default node, the pedestrian position information obtained to prediction, obtain the final position information of pedestrian.The location information that the present invention passes through prediction pedestrian.Based on indoor sport model, the indoor sport state of pedestrian is obtained.Based on indoor environment cartographic model, is calibrated according to indoor sport state and the location information of indoor default node, the pedestrian position information obtained to prediction, obtain the final position information of pedestrian.Due to not having to installation external equipment, to can also reduce hardware cost consumption, cost is relatively low so that expending when indoor positioning while avoiding design complexities higher system.
Description
Technical Field
The invention relates to the technical field of indoor positioning, in particular to an indoor positioning method and device.
Background
In many current application fields, it is very important to acquire position information of a person or an object. With the continuous progress of scientific technology, communication technology, etc., Location Based Service (LBS) positioning technology is also rapidly developed. The LBS mainly solves the problem of providing existing resources to users to provide specific services according to their surrounding environment.
In an outdoor environment, the position information can be obtained by a GPS (Global Positioning System). With the rapid development of information technology, the GPS positioning technology can meet the daily requirements of the common people. Accordingly, GPS technology has been the mainstream of research. Because the GPS is positioned by the satellites, the best positioning precision can be obtained on the premise that four satellites are positioned simultaneously. However, in an indoor environment, the satellite signal strength and quality are rapidly degraded due to the obstruction of the building to the GPS signal. Meanwhile, since the indoor environment is very complicated, accurate positioning cannot be performed indoors. Therefore, the indoor positioning technology is difficult.
In addition, studies have shown that people are indoors 90% of their daily lives, i.e., people are out of GPS signal location for most of their time. Therefore, indoor positioning technology is also greatly needed. With the development of intelligent communication devices, research on indoor positioning technology has also been developed. Smart mobile terminals such as smart phones and tablet computers used in daily life of people integrate high-precision sensor elements such as MEMS (Micro-Electro-Mechanical systems), accelerometers, gyroscopes, barometers, and the like. The wide use of these sensor elements provides a basis for indoor positioning techniques and the accuracy of the sensor elements can also meet the needs of indoor positioning techniques. In addition, the assisted positioning technology has also been widely and fully studied. Such as wireless fingerprint signal based indoor positioning techniques, vision based positioning techniques, etc. Either in conjunction with the sensors or as a stand-alone location technique. Accordingly, the accuracy of indoor positioning is also improved. In recent years, companies such as google begin to build indoor maps, which gradually cover some landmark buildings in the large cities, so that the indoor maps can also be used as an auxiliary means for positioning.
From 2000, based on the increasing popularity of intelligent terminals, LBS is gradually applied to the fields of emergency assistance, disaster prevention, logistics management, equipment inspection, medical care, and the like. In this context, the need for locating a seamless connection from outdoors to indoors has also been addressed.
In the fields of public safety guarantee, commercial service and warehousing service, the high-precision indoor positioning technology has very important significance. For example, in terms of social public safety, accurate indoor positioning technology can provide indoor navigation services for firefighters, police and other personnel, position a prisoner in a prison and the like. In the commercial service, the precise indoor positioning technology can provide positioning service for families, provide navigation in indoor environments such as shopping malls and museums, and provide nursing positioning service for old people, children and patients in hospitals and families. In a warehouse service, items may be located. Therefore, the indoor positioning technology has wide application scenes.
On the basis, the research direction of indoor positioning and navigation technology of pedestrians is mainly developed towards low cost, easy portability and improvement of positioning precision. The existing indoor positioning method is mainly to install a plurality of external devices, such as an AP (access point), in advance, and position the pedestrian according to the mapping relationship between the signal strength and the distance between the mobile terminal and the external device.
In the process of implementing the invention, the prior art is found to have at least the following problems: since a plurality of external devices need to be installed, the equipment cost is high. In addition, a system with high design complexity is generally required to work together among a plurality of external devices. Therefore, the cost for indoor positioning is high.
Disclosure of Invention
The present invention provides an indoor positioning method and apparatus that overcomes, or at least partially solves, the above mentioned problems.
According to an aspect of the present invention, there is provided an indoor positioning method, including:
predicting the position information of the pedestrian according to the data acquired by the multiple sensors;
acquiring an indoor motion state of the pedestrian based on the indoor motion model;
and based on the indoor environment map model, calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node to obtain the final position information of the pedestrian.
According to another aspect of the present invention, there is provided an indoor positioning apparatus including:
the prediction module is used for predicting the position information of the pedestrian according to the data acquired by the multiple sensors;
the acquisition module is used for acquiring the indoor motion state of the pedestrian based on the indoor motion model;
and the calibration module is used for calibrating the predicted pedestrian position information based on the indoor environment map model according to the indoor motion state and the position information of the indoor preset node to obtain the final position information of the pedestrian.
The beneficial effect that technical scheme that this application provided brought is:
the position information of the pedestrian is predicted according to the data collected by the multiple sensors. And acquiring the indoor motion state of the pedestrian based on the indoor motion model. And based on the indoor environment map model, calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node to obtain the final position information of the pedestrian. Because no external equipment is needed to be installed, the hardware cost consumption can be reduced while the system with higher design complexity is avoided, and the cost consumed in indoor positioning is lower.
In addition, when the motion characteristics are classified, data of an accelerometer, a barometer and a gyroscope are selected, so that the accuracy of the motion characteristics in classification is improved, and meanwhile, long-time accumulated errors can be avoided. In the positioning process, the pedestrian dead reckoning algorithm, the indoor pedestrian motion characteristic and the hidden Markov model matching method are combined together, so that the robustness of indoor positioning can be improved while the high positioning accuracy is ensured.
Drawings
Fig. 1 is a schematic flow chart of an indoor positioning method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of an indoor positioning method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of an indoor positioning device according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
The existing indoor positioning method is mainly to install a plurality of external devices, such as an AP (access point), in advance, and position the pedestrian according to the mapping relationship between the signal strength and the distance between the mobile terminal and the external device. Since a plurality of external devices need to be installed, the equipment cost is high. In addition, a system with high design complexity is generally required to work together among a plurality of external devices. Therefore, the cost for indoor positioning is high.
To solve the problems in the prior art, the present embodiment provides an indoor positioning method. The method is applied to mobile terminals, and the mobile terminals include but are not limited to mobile phones, tablet computers, smart watches and the like. In addition, since the embodiment of the present invention needs to be applied to data collected by a sensor, an acceleration sensor, a gyroscope, a barometer, and the like may be installed in the mobile terminal, which is not particularly limited in this embodiment.
Referring to fig. 1, the method flow provided by this embodiment includes: 101. predicting the position information of the pedestrian according to the data acquired by the multiple sensors; 102. acquiring an indoor motion state of the pedestrian based on the indoor motion model; 103. and based on the indoor environment map model, calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node to obtain the final position information of the pedestrian.
According to the method provided by the embodiment of the invention, the position information of the pedestrian is predicted according to the data acquired by the multiple sensors. And acquiring the indoor motion state of the pedestrian based on the indoor motion model. And based on the indoor environment map model, calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node to obtain the final position information of the pedestrian. Because no external equipment is needed to be installed, the hardware cost consumption can be reduced while the system with higher design complexity is avoided, and the cost consumed in indoor positioning is lower.
In addition, when the motion characteristics are classified, data of an accelerometer, a barometer and a gyroscope are selected, so that the accuracy of the motion characteristics in classification is improved, and meanwhile, long-time accumulated errors can be avoided. In the positioning process, the pedestrian dead reckoning algorithm, the indoor pedestrian motion characteristic and the hidden Markov model matching method are combined together, so that the robustness of indoor positioning can be improved while the high positioning accuracy is ensured.
As an alternative embodiment, the step of predicting the position information of the pedestrian according to the data collected by the multiple sensors comprises the following steps:
determining the total number of steps of the pedestrian from starting to stopping moving;
and for each step of the pedestrian movement, calculating the position information of the pedestrian after the step movement according to the step length, the steering angle and the position information of the pedestrian before the movement until the calculation times reach the total step number, and taking the final calculation result as the position information of the pedestrian.
As an alternative embodiment, before determining the total number of steps of the pedestrian from the start of the movement to the stop of the movement, the method further comprises:
and detecting the start and stop of the movement of the pedestrian according to the acceleration of each sampling point.
As an alternative embodiment, the detection of the beginning of the movement of the pedestrian according to the acceleration of each sampling point comprises:
for any sampling point, when the acceleration of any sampling point is not smaller than a first preset threshold value, the pedestrian is determined to start moving at any sampling point.
As an alternative embodiment, the detection of the stop of the movement of the pedestrian according to the acceleration of each sampling point comprises:
for any sampling point, when the acceleration of the sampling point is detected to be smaller than a first preset threshold value, counting the number of the sampling points which are continuously smaller than the first preset threshold value from the sampling point;
and when the statistical result reaches the preset number, acquiring the last sampling point when the statistical result reaches the preset number, and determining that the pedestrian stops moving on the last sampling point.
As an alternative embodiment, determining the total number of steps of the pedestrian from starting to stopping movement comprises:
and for any sampling point in the period from the start of moving to the stop of moving of the pedestrian, when the fact that the acceleration of any sampling point is larger than a second preset threshold value and the acceleration corresponding to the next sampling point of any sampling point is smaller than the second preset threshold value is detected, taking the last sampling point, any sampling point and the next sampling point of any sampling point as a step period, and adding one to the total step number of the pedestrian.
As an alternative embodiment, before taking the last sampling point of any sampling point, and the next sampling point of any sampling point as a step period and adding one to the total number of steps of the pedestrian, the method further includes:
and calculating a second preset threshold according to the acceleration related value in the previous step cutting period.
As an alternative embodiment, before calculating the position information of the pedestrian after moving one step according to the step length of the pedestrian, the steering angle and the position information of the pedestrian before moving, the method further comprises:
acquiring angular acceleration of the current pedestrian in three directions based on a space coordinate system;
and calculating the steering angle of the pedestrian according to the angular acceleration and the acceleration of the current pedestrian in three directions based on the projection relation between the space coordinate system and the ground coordinate system.
As an alternative embodiment, the step of predicting the position information of the pedestrian according to the data collected by the multiple sensors comprises the following steps:
and determining the floor where the pedestrian is located according to the air pressure value of the position where the pedestrian is located.
As an alternative embodiment, the acquiring the indoor motion state of the pedestrian based on the indoor motion model includes:
calculating a characteristic value corresponding to the first time window according to the acceleration of each sampling point in the first time window;
and determining the motion characteristics of the pedestrian according to the characteristic value corresponding to the first time window based on the motion state classifier.
As an alternative embodiment, the acquiring the indoor motion state of the pedestrian based on the indoor motion model includes:
calculating the turning angle of the pedestrian according to the turning angle of the pedestrian in the second time window;
and determining the turning characteristics of the pedestrian according to the turning angle of the pedestrian.
As an optional embodiment, based on an indoor environment map model, calibrating the predicted pedestrian position information according to an indoor motion state and position information of an indoor preset node to obtain final position information of a pedestrian, including:
determining the moving probability of the pedestrian moving to the adjacent preset node in the indoor environment map model based on the indoor environment map model;
sequencing the movement probability of each adjacent preset node, and selecting two movement probabilities with the largest numerical values in the sequencing result, wherein the two movement probabilities are respectively a first movement probability and a second movement probability, and the first movement probability is larger than the second movement probability;
and when the ratio of the first movement probability to the second movement probability is larger than a third preset threshold value, taking the position information of the adjacent preset node corresponding to the first movement probability as the final position information of the pedestrian.
As an optional embodiment, determining, based on the indoor environment map model, a moving probability that a pedestrian moves to an adjacent preset node in the indoor environment map model includes:
for any adjacent preset node in the indoor environment map model, calculating the emission probability of the pedestrian moving to any adjacent preset node according to the position information of any adjacent preset node;
determining the state identification probability that the motion state of any adjacent preset node is expressed as an indoor motion state according to the motion identification probability matrix;
and taking the product of the emission probability and the state recognition probability as the moving probability of the pedestrian moving to any adjacent preset node.
As an optional embodiment, the method for ranking the movement probabilities of each neighboring preset node, and selecting two movement probabilities with the largest values in the ranking result after the first movement probability and the second movement probability respectively, further includes:
and when the ratio of the first movement probability to the second movement probability is not greater than a third preset threshold, using the predicted pedestrian position information as the final pedestrian position information.
All the above-mentioned optional technical solutions can be combined arbitrarily to form the optional embodiments of the present invention, and are not described herein again.
Based on the content provided by the embodiment corresponding to fig. 1, an embodiment of the present invention provides an indoor positioning method. Referring to fig. 2, the method flow provided by this embodiment includes: 201. determining the total number of steps of the pedestrian from starting to stopping moving; 202. for each step of the pedestrian movement, calculating the position information of the pedestrian after the pedestrian moves one step according to the step length, the steering angle and the position information of the pedestrian before the pedestrian moves until the calculation times reach the total step number, and taking the final calculation result as the position information of the pedestrian; 203. acquiring an indoor motion state of the pedestrian based on the indoor motion model; 204. and based on the indoor environment map model, calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node to obtain the final position information of the pedestrian.
Wherein 201, the total number of steps of the pedestrian from starting to stopping moving is determined.
The method provided by the embodiment mainly comprises the steps of predicting the position information of the pedestrian according to data collected by the multiple sensors, and calibrating the predicted position information of the pedestrian to realize the positioning process. The steps 201 to 202 are mainly processes of predicting pedestrian position information according to data collected by multiple sensors.
Since it is unknown when the pedestrian starts moving and stops moving indoors, the pedestrian can be detected according to the acceleration of each sampling point before the step 201 is executed, which is not particularly limited in the embodiment.
As to the manner of detecting the start of the movement of the pedestrian according to the acceleration of each sampling point, the present embodiment is not particularly limited, and includes but is not limited to: for any sampling point, when the acceleration of any sampling point is not smaller than a first preset threshold value, the pedestrian is determined to start moving at any sampling point.
Wherein, the sampling point corresponds to the sampling period of the sensor. The first preset threshold may be a value according to an actual situation, which is not specifically limited in this embodiment. For example, with a first preset threshold of 1.5m/s2For example. If the sampling period of the acceleration sensor is 20ms, every 20ms is a sampling point. Namely, when the acceleration sensor collects the acceleration value on each sampling point, the mobile terminal can also judge whether the acceleration value collected on each sampling point is more than or equal to 1.5m/s2. If the acceleration of a sampling point is detected to be more than 1.5m/s2Then it is determined that the pedestrian starts moving from the sampling point.
The present embodiment does not specifically limit the manner of detecting the stop of the movement of the pedestrian according to the acceleration of each sampling point, and includes but is not limited to: for any sampling point, when the acceleration of the sampling point is detected to be smaller than a first preset threshold value, counting the number of the sampling points which are continuously smaller than the first preset threshold value from the sampling point; and when the statistical result reaches the preset number, acquiring the last sampling point when the statistical result reaches the preset number, and determining that the pedestrian stops moving on the last sampling point. The preset number may also be set according to an actual situation, which is not specifically limited in this embodiment.
For example, with a first preset threshold of 1.5m/s2The preset number is 30 for example. If the acceleration of the 10 th sampling point is detected to be less than 1.5m/s2Then the acceleration continues to be detected at the 11 th, 12 th, … … th, and 40 th sample points. When the acceleration of continuous 30 sampling points after the 10 th sampling point is less than 1.5m/s2When the acceleration of the 11 th, 12 th, … … th and 40 th sampling points is less than 1.5m/s2Then, the last sampling point when the total number of samples reaches 30, i.e., the 40 th sampling point, is obtained. Accordingly, at the 40 th sampling point, the pedestrian stops moving.
After determining that the pedestrian starts to move and stops moving, the total number of steps taken by the pedestrian from the start of moving to the stop of moving can be determined. The present embodiment does not specifically limit the manner of determining the total number of steps from the start movement to the stop movement of the pedestrian, and includes but is not limited to: and for any sampling point in the period from the start of moving to the stop of moving of the pedestrian, when the fact that the acceleration of any sampling point is larger than a second preset threshold value and the acceleration corresponding to the next sampling point of any sampling point is smaller than the second preset threshold value is detected, taking the last sampling point, any sampling point and the next sampling point of any sampling point as a step period, and adding one to the total step number of the pedestrian.
Because the acceleration of one leg is large when the person walks and small when the person is ready to land after the leg is lifted, two continuous sampling points can be detected in the process based on the principle. And comparing the two sampling points with a second preset threshold, and when the current sampling point is greater than the second preset threshold and the latter sampling point is less than the second preset threshold, the pedestrian can be considered to walk one step. Correspondingly, for a sampling point with the acceleration greater than the second preset threshold, when the acceleration corresponding to the next sampling point of the sampling point is less than the second preset threshold, the time period from the last sampling point to the next sampling point can be used as a step period. For example, if the acceleration of the 3 rd sampling point is greater than the second preset threshold and the acceleration of the 4 th sampling point is less than the second preset threshold, the 2 nd sampling point, the 3 rd sampling point, and the 4 th sampling point may be regarded as a step period, and the pedestrian is considered to have moved one step in the step period. Accordingly, the total number of steps may be increased by one. Note that the initial value of the total number of steps before counting the total number of steps is 0.
In addition, before determining the total number of steps, a second preset threshold may be calculated according to the acceleration related value in the previous step period, which is not specifically limited in this embodiment. According to the experimental result of the dead reckoning of the pedestrian, the second preset threshold value can be calculated by a dynamic threshold value equation (1) as follows:
wherein α and β are preset parameters, and can be respectively set to 0.25 and 0.75, which is not specifically limited in this embodiment, γ is an ambient noise variance, and can be set to 0.09, which is also not specifically limited in this embodimentoldFor a second predetermined threshold value, A, of the previous step of the felling cycle1And A2Is an acceleration-related value. A. the1And A2Respectively representing the maximum and minimum values of acceleration, A, during the previous step of the felling cycle1And A2The mean or variance of the acceleration may also be used, which is not specifically limited in this embodiment.
And 202, for each step of the pedestrian movement, calculating the position information of the pedestrian after the step movement according to the step length of the pedestrian, the steering angle and the position information of the pedestrian before the movement until the calculation times reach the total steps, and taking the final calculation result as the position information of the pedestrian.
Before the step is executed, the step length of the pedestrian, the position information before the pedestrian moves and the steering angle of the pedestrian can be obtained. The pedestrian step length is estimated according to the height of the pedestrian, which is not specifically limited in this embodiment. Since the method provided by the embodiment is an iterative calculation process, that is, the position information of the pedestrian before the last movement can also be obtained by the method provided by the embodiment, when the position information of the pedestrian before the movement is obtained, the calculation result corresponding to the method provided by the embodiment executed last time can be obtained. It should be noted that, when the pedestrian is first located indoors, the initial position may be set according to actual conditions, and this embodiment is not particularly limited.
In addition, the pedestrian can do curvilinear motion when moving, so that the steering angle of the pedestrian can be acquired in order to predict the position of the pedestrian more accurately. The present embodiment does not specifically limit the manner of obtaining the steering angle of the pedestrian, and includes but is not limited to: acquiring angular acceleration of the current pedestrian in three directions based on a space coordinate system; and calculating the steering angle of the pedestrian according to the angular acceleration and the acceleration of the current pedestrian in three directions based on the projection relation between the space coordinate system and the ground coordinate system.
The angular velocities in the three directions of the XYZ axes can be classified according to a spatial coordinate system. The angular accelerations in the three directions may be obtained by a gyroscope in the mobile terminal, which is not particularly limited in this embodiment. Before calculating the steering angle of the pedestrian, the angular displacements in the three directions may be calculated from the angular accelerations in the three directions by means of integration, which is not specifically limited in this embodiment. The integration process can refer to the following equation (2):
wherein,andangular accelerations in three directions of XYZ are respectively. t is tbeginTo move by the start of a step, tstopIs the end time of the movement by one step. Thetax、θyAnd thetazAngular displacements in three directions of XYZ are respectively.
It should be noted that, if the angular displacements in the three XYZ directions in a time window are all small, for example, smaller than the angle threshold, it is considered that the pedestrian performs a linear motion in the time window. For example, the angle threshold is 15 °. Angular displacement theta in XYZ three directions in a time windowx、θyAnd thetazAll of which are smaller than 15 deg., it can be determined that the pedestrian is making a linear movement within this time window.
Based on the principle, the arithmetic mean value of the acceleration in three directions can be calculated during the process that the pedestrian walks in a straight line. Accordingly, the steering angle of the pedestrian can be calculated according to the arithmetic average of the angular displacement and the acceleration of the current pedestrian in the three directions, which is not particularly limited in the embodiment. The calculation process can be represented by a pedestrian dead reckoning model (3) defined as follows:
wherein, OzIs the steering angle of the pedestrian. Thetax、θyAnd thetazAngular displacements in three directions, respectively.Andwhich are the arithmetic mean of the accelerations in the three directions, respectively.
After the steering angle of the pedestrian is obtained through calculation, for each step of the movement of the pedestrian, the position information of the pedestrian after the step of the movement can be calculated according to the step length of the pedestrian, the steering angle and the position information of the pedestrian before the movement. The calculation process can refer to the following formula (4):
wherein lkIs the pedestrian step size. Based on the ground coordinate system, xk-1And yk-1For positional information of the pedestrian before moving by one step, xkAnd ykThe position information of the pedestrian after moving one step.
Based on the total number of steps determined in step 201, the position information of the pedestrian after walking such multiple steps, i.e., the predicted position information of the pedestrian, can be determined according to the above formula (4).
It should be noted that the above process predicts the position information of the pedestrian based on the ground coordinate system. When the pedestrian is located indoors, the floor of the building where the pedestrian is located may need to be located, so that the predicted pedestrian position information may further include the floor where the pedestrian is located. The embodiment also provides a method for determining the floor where the pedestrian is located, which includes but is not limited to: and determining the floor where the pedestrian is located according to the air pressure value of the position where the pedestrian is located.
Since the air pressure in the earth atmosphere is inversely proportional to the altitude, that is, the air pressure is reduced when the altitude is increased, the air pressure measured by the barometer can be used for calculating the altitude of the pedestrian. According to the floor height of the building where the pedestrian is located and the height of the pedestrian, the floor where the pedestrian is located can be determined, and this embodiment is not particularly limited. Based on the ICAO (International Civil Aviation Organization) model, it is known that the atmospheric pressure decreases by 1mbar for every about 8.7 meters increase in altitude. According to standard atmospheric pressure in 1993, the height of the pedestrian can be calculated by referring to the following formula (5):
wherein, P0Typical is standard atmospheric pressure (1013.25 mbar). H is the height of the pedestrian in meters.
And 203, acquiring the indoor motion state of the pedestrian based on the indoor motion model.
Before executing this step, the moving state of the pedestrian in the room may be determined according to the moving habit of the pedestrian in the room, which is not specifically limited in this embodiment. In the embodiment, the motion state of the pedestrian is divided into 7 according to the actual life scene, which are respectively: walking, sitting down, standing, going upstairs, going downstairs, turning and U-shaped turning.
Wherein, walking, sitting down, standing, going upstairs and downstairs are all the motion characteristics of the pedestrian in the moving process. Turning and U-shaped turning are turning characteristics of pedestrians in the moving process. Since the pedestrian may turn in a small turn with the direction adjusted or in a large turn with the turn around, the turning characteristic is divided into a turn and a U-turn to distinguish the two turns. When the turning and the U-shaped turning are determined, the determination can be carried out according to the comparison result between the turning angle of the pedestrian in the time window and the preset threshold value range. For example, when the turning angle is 50 ° to 135 °, it is considered as a normal turning. When the turning angle is greater than 135 °, it can be considered as a U-turn.
Based on the above, in the step, when the indoor state of the pedestrian is obtained, the motion characteristic and the turning characteristic of the pedestrian can be respectively obtained. The present embodiment does not specifically limit the manner of obtaining the motion characteristics of the pedestrian based on the indoor motion model, and includes but is not limited to: calculating a characteristic value corresponding to the first time window according to the acceleration of each sampling point in the first time window; and determining the motion characteristics of the pedestrian according to the characteristic value corresponding to the first time window based on the motion state classifier.
The motion state classifier may be trained by a KNN (K-Nearest-Neighbor) classifier, which is not specifically limited in this embodiment. Specifically, a preset number of experimenters can be selected to practice the five motion characteristics, namely walking, sitting, standing, going upstairs and going downstairs, and characteristic values of the experimenters in practicing the motion characteristics are obtained. Inputting a motion characteristic and a characteristic value of each experimenter when practicing the motion characteristic into the KNN model, and continuously training the KNN model until the training times reach the preset times. And finally, obtaining a motion state classifier and a motion recognition probability matrix according to the training result. The motion state classifier is used for determining the motion characteristics of the pedestrian according to the input characteristic value.
The motion recognition probability matrix is a probability matrix that each motion feature of the pedestrian is recognized as a pair and as other motion features. For example, take the example that the pedestrian's current motion characteristic is actually "sitting down". Based on the motion state classifier, it is possible to recognize that the motion feature of the pedestrian is actually "sitting" from the input feature value. At this point, the recognition result is correct, which corresponds to a probability. But is originally "sitting" and may also be identified as "walking". At this point, the recognition result is erroneous, which also corresponds to a probability. Based on the theory, the KNN model is continuously trained, so that the motion state classifier is obtained, and meanwhile, the motion recognition probability matrix can be obtained.
Correspondingly, after the motion state classifier is obtained, the motion characteristics of the pedestrian can be determined based on the motion state classifier only by acquiring the characteristic value corresponding to the pedestrian in the first time window. The characteristic value may be calculated according to the acceleration of each sampling point in the first time window, which is not specifically limited in this embodiment. The characteristic values may include a mean and a variance of the accelerations in the three directions in the first time window, an air pressure value, and amplitudes of the accelerations in the three directions, which is not specifically limited in this embodiment. The length of the first time window may be 2s to 3s, which is not particularly limited in this embodiment. The first time window may be set to overlap coverage of 50% in consideration of the continuity of the motion when the pedestrian walks, and this embodiment is not particularly limited. For example, the first time window may take values of 0s to 2s, 1s to 3s, 2s to 4s … ….
In addition to determining the motion characteristics of the pedestrian, the turning characteristics of the pedestrian may be determined. The present embodiment is not particularly limited to the manner of determining the turning characteristic of the pedestrian, and includes but is not limited to: calculating the turning angle of the pedestrian according to the turning angle of the pedestrian in the second time window; and determining the turning characteristics of the pedestrian according to the turning angle of the pedestrian.
The length of the second time window may also be 2s to 3s, which is not specifically limited in this embodiment. In addition, the lengths of the first time window and the second time window may be the same or different, and this embodiment is not limited in this respect. Specifically, when the turning angle of the pedestrian is calculated, the first turning angle at the starting time of the second time window may be calculated first, and then the second turning angle at the ending time of the second time window may be calculated. And taking the difference value between the first steering angle and the second steering angle as the turning angle of the pedestrian. The process of calculating the steering angle may refer to the process of equation (3), and is not described herein again.
For example, the second time window length is 2s, and the second time window is 1s to 3 s. When the turning angle of the pedestrian is calculated, the steering angle of the pedestrian at 1s can be calculated first, and then the steering angle of the pedestrian at 3s can be calculated, so that the difference value of the two steering angles is used as the turning angle of the pedestrian.
Through the process, the motion characteristic and the turning characteristic of the pedestrian can be finally obtained. Wherein, the motion characteristic is one of walking, sitting down, standing, going upstairs and downstairs, and the turning characteristic is one of turning and U-shaped turning. And combining the motion characteristic and the turning characteristic to obtain the indoor motion state of the pedestrian.
And 204, calibrating the predicted pedestrian position information based on the indoor environment map model according to the indoor motion state and the position information of the indoor preset node to obtain the final position information of the pedestrian.
Since there may be a certain error in the pedestrian location information predicted in the above steps 201 to 202, the pedestrian location information predicted in the steps 201 to 202 may be calibrated based on the location information of the preset node in the indoor environment map model in this step. In this embodiment, the method for obtaining the final position information of the pedestrian by calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node based on the indoor environment map model is not specifically limited, and includes but is not limited to: determining the moving probability of the pedestrian moving to the adjacent preset node in the indoor environment map model based on the indoor environment map model; sequencing the movement probability of each adjacent preset node, and selecting two movement probabilities with the largest numerical values in the sequencing result, wherein the two movement probabilities are respectively a first movement probability and a second movement probability, and the first movement probability is larger than the second movement probability; and when the ratio of the first movement probability to the second movement probability is larger than a third preset threshold value, taking the position information of the adjacent preset node corresponding to the first movement probability as the final position information of the pedestrian.
The indoor environment map model is constructed from actual life scenes. In particular, the positions of the nodes such as the corner points of stairs and the corner points of aisles in a building are usually predetermined. And establishing an indoor environment map model according to the node coordinates of each node, the direction and distance between each node and the adjacent nodes which can reach directly in the space, and the motion state of the pedestrian on each node.
Before determining the moving probability of the pedestrian moving to the adjacent preset node in the indoor environment map model based on the indoor environment map model, the position information of the pedestrian before moving can be obtained. As can be seen from the above-mentioned contents in step 201 to step 204, since the method provided in this embodiment is iterative, that is, the position information of the pedestrian after the next movement is continuously derived according to the last calculation result, when the position information of the pedestrian before the movement is obtained in this step, the position information of the pedestrian calculated by the method provided in this embodiment may be obtained last time, which is not specifically limited in this embodiment.
After the position information of the pedestrian before moving is determined, according to the position information of each preset node in the indoor environment map model, the position of the pedestrian before moving can be determined to directly reach the preset nodes in the indoor environment map model. The preset nodes are adjacent preset nodes corresponding to positions of pedestrians before moving. Based on the above, for any adjacent preset node, the present embodiment does not specifically limit the manner of determining the moving probability of the pedestrian moving to the adjacent preset node in the indoor environment map model, and includes but is not limited to: for any adjacent preset node in the indoor environment map model, calculating the emission probability of the pedestrian moving to any adjacent preset node according to the position information of any adjacent preset node; determining the state identification probability that the motion state of any adjacent preset node is expressed as an indoor motion state according to the motion identification probability matrix; and taking the product of the emission probability and the state recognition probability as the moving probability of the pedestrian moving to any adjacent preset node.
The emission probability is the probability of generating an observation state from a hidden state, the position information of the pedestrian before moving is the hidden state, and the position information of the adjacent preset node is the observation state. In calculating the transmission probability, the following formula (6) may be referred to:
in the above formula (6), P (z)t|ri) Is the probability of transmission. z is a radical oftFor location information of adjacent preset nodes, riAs positional information before the pedestrian moves, zt-riRepresenting the euclidean distance between the two. σ is a standard deviation of the calculated value of the pedestrian moving distance, and the value of σ in the present embodiment is 0.1.
Based on the relevant content of the motion recognition probability matrix in step 203, for any adjacent preset node, when determining that the motion state of the adjacent preset node represents the state recognition probability of the indoor motion state, the corresponding probability may be searched for in the motion recognition probability matrix according to the motion feature in the indoor motion state and the motion feature of the adjacent preset node. And taking the searched probability as the state recognition probability.
In addition, when the moving probability of the pedestrian moving to any adjacent preset node is calculated according to the transmission probability and the state identification probability, the calculation process may refer to the following formula (7):
P(zt,mt|ri)＝P(zt|ri)P(mt|ri) (7)
wherein, P (z)t|ri) For the emission probability, P (m)t|ri) To identify probabilities for states, P (z)t,mt|ri) Is the probability of movement.
Since there may be a plurality of preset nodes adjacent to the position of the pedestrian before moving in the indoor environment map model, the movement probability of each adjacent preset node may be calculated according to the above calculation process. After the plurality of movement probabilities are obtained through calculation, all the movement probabilities can be ranked, and two movement probabilities with the largest values are selected from ranking results and are counted as a first movement probability and a second movement probability. The first movement probability is greater than the second movement probability, that is, the first movement probability is the maximum value of the movement probabilities, and the second movement probability is the second largest value of the movement probabilities.
In order to more accurately determine the position information of the pedestrian, a ratio of the first movement probability to the second movement probability may be calculated. When the ratio is greater than the third preset threshold, it indicates that the possibility that the pedestrian moves to the adjacent preset node corresponding to the first movement probability is much greater than the possibility that the pedestrian moves to the adjacent preset node corresponding to the second movement probability. Therefore, when the pedestrian moves to the adjacent preset node corresponding to the first moving probability, the reliability is high. At this time, the position information of the adjacent preset node corresponding to the first movement probability may be used as the final position information of the pedestrian, and the position information predicted in the above steps 201 to 202 is discarded.
In addition, when the ratio of the first movement probability to the second movement probability is not greater than the third preset threshold, the pedestrian position information predicted in the above steps 201 to 202 may be used as the final position information of the pedestrian.
The method provided by the embodiment of the invention determines the total steps of the pedestrian from the starting movement to the stopping movement. And for each step of the pedestrian movement, calculating the position information of the pedestrian after the step movement according to the step length, the steering angle and the position information of the pedestrian before the movement until the calculation times reach the total step number, and taking the final calculation result as the position information of the pedestrian. And acquiring the indoor motion state of the pedestrian based on the indoor motion model. And based on the indoor environment map model, calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node to obtain the final position information of the pedestrian. Because no external equipment is needed to be installed, the hardware cost consumption can be reduced while the system with higher design complexity is avoided, and the cost consumed in indoor positioning is lower.
In addition, when the motion characteristics are classified, data of an accelerometer, a barometer and a gyroscope are selected, so that the accuracy of the motion characteristics in classification is improved, and meanwhile, long-time accumulated errors can be avoided. In the positioning process, the pedestrian dead reckoning algorithm, the indoor pedestrian motion characteristic and the hidden Markov model matching method are combined together, so that the robustness of indoor positioning can be improved while the high positioning accuracy is ensured.
An embodiment of the present invention provides an indoor positioning apparatus, which is configured to perform the indoor positioning method provided in the embodiment corresponding to fig. 1 or fig. 2. Referring to fig. 3, the apparatus includes:
the prediction module 301 is configured to predict the position information of the pedestrian according to the data acquired by the multiple sensors;
an obtaining module 302, configured to obtain an indoor motion state of a pedestrian based on an indoor motion model;
the calibration module 303 is configured to calibrate the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node based on the indoor environment map model, so as to obtain the final position information of the pedestrian.
As an alternative embodiment, the prediction module 301 includes:
a determination unit for determining a total number of steps of the pedestrian from the start movement to the stop movement;
and the first calculation unit is used for calculating the position information of the pedestrian after moving one step according to the step length of the pedestrian, the steering angle and the position information before moving the pedestrian for each step of the movement of the pedestrian until the calculation times reach the total step number, and taking the final calculation result as the position information of the pedestrian.
As an alternative embodiment, the prediction module 301 further includes:
and the detection unit is used for detecting the start and stop of the movement of the pedestrian according to the acceleration of each sampling point.
As an alternative embodiment, the detection unit is configured to determine, for any sampling point, that the pedestrian starts moving at any sampling point when the acceleration of any sampling point is detected to be not less than the first preset threshold.
As an optional embodiment, the detection unit is configured to, for any sampling point, count the number of sampling points that are continuously smaller than a first preset threshold from any sampling point when the acceleration of any sampling point is detected to be smaller than the first preset threshold; and when the statistical result reaches the preset number, acquiring the last sampling point when the statistical result reaches the preset number, and determining that the pedestrian stops moving on the last sampling point.
As an optional embodiment, the determining unit is configured to, for any sampling point in the period from the start of moving to the stop of moving of the pedestrian, when it is detected that the acceleration of any sampling point is greater than the second preset threshold and the acceleration corresponding to the next sampling point of any sampling point is smaller than the second preset threshold, take the last sampling point of any sampling point, and the next sampling point of any sampling point as a step period, and add one to the total number of steps of the pedestrian.
As an alternative embodiment, the prediction module 301 further includes:
and the second calculating unit is used for calculating a second preset threshold value according to the acceleration related value in the previous felling period.
As an alternative embodiment, the prediction module 301 further includes:
the acquisition unit is used for acquiring the angular acceleration of the current pedestrian in three directions based on a space coordinate system;
and the third calculation unit is used for calculating the steering angle of the pedestrian according to the angular acceleration and the acceleration of the current pedestrian in three directions based on the projection relation between the space coordinate system and the ground coordinate system.
As an alternative embodiment, the prediction module 301 is configured to determine the floor where the pedestrian is located according to the air pressure value of the location where the pedestrian is located.
As an optional embodiment, the obtaining module 302 is configured to calculate, according to an acceleration of each sampling point in a first time window, a feature value corresponding to the first time window; and determining the motion characteristics of the pedestrian according to the characteristic value corresponding to the first time window based on the motion state classifier.
As an alternative embodiment, the obtaining module 302 is configured to calculate a turning angle of the pedestrian according to the turning angle of the pedestrian in the second time window; and determining the turning characteristics of the pedestrian according to the turning angle of the pedestrian.
As an alternative embodiment, the calibration module 303 includes:
the determining unit is used for determining the moving probability of the pedestrian moving to the adjacent preset node in the indoor environment map model based on the indoor environment map model;
the selecting unit is used for sequencing the moving probability of each adjacent preset node, selecting two moving probabilities with the largest numerical values in the sequencing result, namely a first moving probability and a second moving probability respectively, wherein the first moving probability is larger than the second moving probability;
and the first comparison unit is used for taking the position information of the adjacent preset node corresponding to the first movement probability as the final position information of the pedestrian when the ratio of the first movement probability to the second movement probability is larger than a third preset threshold.
As an optional embodiment, the determining unit is configured to calculate, for any adjacent preset node in the indoor environment map model, an emission probability that a pedestrian moves to any adjacent preset node according to position information of any adjacent preset node; determining the state identification probability that the motion state of any adjacent preset node is expressed as an indoor motion state according to the motion identification probability matrix; and taking the product of the emission probability and the state recognition probability as the moving probability of the pedestrian moving to any adjacent preset node.
As an alternative embodiment, the calibration module 303 further includes:
and the second comparison unit is used for taking the predicted pedestrian position information as the final position information of the pedestrian when the ratio of the first movement probability to the second movement probability is not more than a third preset threshold.
According to the device provided by the embodiment of the invention, the position information of the pedestrian is predicted according to the data acquired by the multiple sensors. And acquiring the indoor motion state of the pedestrian based on the indoor motion model. And based on the indoor environment map model, calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node to obtain the final position information of the pedestrian. Because no external equipment is needed to be installed, the hardware cost consumption can be reduced while the system with higher design complexity is avoided, and the cost consumed in indoor positioning is lower.
In addition, when the motion characteristics are classified, data of an accelerometer, a barometer and a gyroscope are selected, so that the accuracy of the motion characteristics in classification is improved, and meanwhile, long-time accumulated errors can be avoided. In the positioning process, the pedestrian dead reckoning algorithm, the indoor pedestrian motion characteristic and the hidden Markov model matching method are combined together, so that the robustness of indoor positioning can be improved while the high positioning accuracy is ensured.
Finally, the method of the present application is only a preferred embodiment and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. An indoor positioning method, characterized in that the method comprises:
predicting the position information of the pedestrian according to the data acquired by the multiple sensors;
acquiring an indoor motion state of the pedestrian based on an indoor motion model;
based on an indoor environment map model, calibrating the predicted pedestrian position information according to the indoor motion state and the position information of an indoor preset node to obtain the final position information of the pedestrian;
the step of calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node based on the indoor environment map model to obtain the final position information of the pedestrian comprises the following steps:
determining the moving probability of the pedestrian moving to an adjacent preset node in the indoor environment map model based on the indoor environment map model;
sequencing the movement probability of each adjacent preset node, and selecting two movement probabilities with the largest numerical values in sequencing results, namely a first movement probability and a second movement probability respectively, wherein the first movement probability is larger than the second movement probability;
and when the ratio of the first movement probability to the second movement probability is greater than a third preset threshold, taking the position information of the adjacent preset node corresponding to the first movement probability as the final position information of the pedestrian.
2. The method according to claim 1, wherein the obtaining the indoor motion state of the pedestrian based on the indoor motion model comprises:
calculating a characteristic value corresponding to a first time window according to the acceleration of each sampling point in the first time window;
and determining the motion characteristics of the pedestrian according to the characteristic value corresponding to the first time window based on the motion state classifier.
3. The method according to claim 1, wherein the obtaining the indoor motion state of the pedestrian based on the indoor motion model comprises:
calculating the turning angle of the pedestrian according to the turning angle of the pedestrian in a second time window;
and determining the turning characteristics of the pedestrian according to the turning angle of the pedestrian.
4. The method according to claim 1, wherein the determining the moving probability of the pedestrian moving to the adjacent preset node in the indoor environment map model based on the indoor environment map model comprises:
for any adjacent preset node in the indoor environment map model, calculating the emission probability of the pedestrian moving to the any adjacent preset node according to the position information of the any adjacent preset node, wherein the emission probability is the probability of generating an observation state from a hidden state, the position information of the pedestrian before moving is a hidden state, and the position information of the any adjacent preset node is an observation state;
determining the state identification probability of the motion state of any adjacent preset node as the indoor motion state according to a motion identification probability matrix, wherein the motion identification probability matrix is the probability matrix of each motion characteristic of the pedestrian being identified as a pair and other motion characteristics;
and taking the product of the emission probability and the state identification probability as the moving probability of the pedestrian moving to any adjacent preset node.
5. The method according to claim 1, wherein the step of ranking the movement probability of each neighboring preset node, selecting two movement probabilities with the largest value in the ranking result, after the first movement probability and the second movement probability respectively, further comprises:
and when the ratio of the first movement probability to the second movement probability is not greater than a third preset threshold, using the predicted pedestrian position information as the final position information of the pedestrian.
6. An indoor positioning device, the device comprising:
the prediction module is used for predicting the position information of the pedestrian according to the data acquired by the multiple sensors;
the acquisition module is used for acquiring the indoor motion state of the pedestrian based on an indoor motion model;
the calibration module is used for calibrating the predicted pedestrian position information according to the indoor motion state and the position information of the indoor preset node based on an indoor environment map model to obtain the final position information of the pedestrian;
the calibration module includes:
the determining unit is used for determining the moving probability of the pedestrian moving to the adjacent preset node in the indoor environment map model based on the indoor environment map model;
the selecting unit is used for sequencing the moving probability of each adjacent preset node, and selecting two moving probabilities with the largest values in the sequencing result, namely a first moving probability and a second moving probability respectively, wherein the first moving probability is larger than the second moving probability;
and the first comparison unit is used for taking the position information of the adjacent preset node corresponding to the first movement probability as the final position information of the pedestrian when the ratio of the first movement probability to the second movement probability is larger than a third preset threshold.
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 CN106595633A (en) | 2017-04-26 |
| CN106595633B true 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) |
Families Citing this family (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 |
| CN110692260B (en) | 2017-06-30 | 2021-08-17 | 北京嘀嘀无限科技发展有限公司 | Terminal equipment positioning system and method |
| CN107356229B (en) * | 2017-07-07 | 2021-01-05 | 中国电子科技集团公司电子科学研究院 | Indoor positioning method and device |
| CN109413683B (en) * | 2017-08-15 | 2021-09-21 | 华为技术有限公司 | Method and device for acquiring emission probability, transition probability and sequence positioning |
| 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 |
| CN111854753B (en) * | 2020-06-02 | 2023-05-23 | 深圳全景空间工业有限公司 | Modeling method for indoor space |
| 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 |
| 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 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI397671B (en) * | 2009-12-16 | 2013-06-01 | Ind Tech Res Inst | System and method for locating carrier, estimating carrier posture and building map |
-
2016
- 2016-11-25 CN CN201611070529.6A patent/CN106595633B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
|---|
| Smartphone based Indoor Position and Orientation Tracking Fusing Inertial and Magnetic Sensing;Chengkai Huang 等;《17th International Symposium on Wireless Personal Multimedia Communications》;20141231;第205-220页 |
| 基于粒子滤波的智能移动终端室内定位方法研究;闫亭亭;《中国优秀硕士学位论文全文数据库 信息科技辑》;20140815(第08期);I136-293 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106595633A (en) | 2017-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106595633B (en) | Indoor orientation method and device | |
| CN107289941B (en) | Inertial navigation-based indoor positioning method and device | |
| CA2653622C (en) | Method and system for locating and monitoring first responders | |
| 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 | |
| CN107396321B (en) | Unsupervised indoor positioning method based on mobile phone sensor and iBeacon | |
| JP2013531781A (en) | Method and system for detecting zero speed state of object | |
| Xu et al. | A robust floor localization method using inertial and barometer measurements | |
| CN109211229A (en) | A kind of personnel's indoor orientation method based on mobile phone sensor and WiFi feature | |
| CN109164411A (en) | A kind of personnel positioning method based on multi-data fusion | |
| Gu et al. | Integration of positioning and activity context information for lifelog in urban city area | |
| AU2015201877B2 (en) | Method and system for locating and monitoring first responders | |
| Qi et al. | Precise 3D foot-mounted indoor localization system using commercial sensors and map matching approach | |
| CN110426034B (en) | Indoor positioning method based on map information auxiliary inertial navigation array | |
| Amanatiadis et al. | An intelligent multi-sensor system for first responder indoor navigation | |
| KR102269074B1 (en) | Method and apparatus for determining positions in indoor | |
| AU2012203438B2 (en) | Method and system for locating and monitoring first responders | |
| Han | Application of inertial navigation high precision positioning system based on SVM optimization | |
| CN106352875A (en) | Dead-reckoning-based navigation system and method | |
| Tsubouchi et al. | Enhancing indoor altitude estimation on smartphones: Resolving ventilation fan effects | |
| JP2020085783A (en) | Pedestrian-purpose positioning device, pedestrian-purpose positioning system, and pedestrian-purpose positioning method | |
| Chirakkal et al. | Exploring smartphone-based indoor navigation: A QR code assistance-based approach | |
| CN114608576B (en) | Indoor positioning method and device | |
| Saadatzadeh et al. | Pedestrian dead reckoning using smartphones sensors: an efficient indoor positioning system in complex buildings of smart cities | |
| Gu et al. | Lifelog using mobility context information in urban city area |
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 |