CN113259844A - Indoor human body orientation recognition system based on reversible positioning tags - Google Patents

Indoor human body orientation recognition system based on reversible positioning tags Download PDF

Info

Publication number
CN113259844A
CN113259844A CN202110663333.2A CN202110663333A CN113259844A CN 113259844 A CN113259844 A CN 113259844A CN 202110663333 A CN202110663333 A CN 202110663333A CN 113259844 A CN113259844 A CN 113259844A
Authority
CN
China
Prior art keywords
map
angle
current
theta
human body
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
Application number
CN202110663333.2A
Other languages
Chinese (zh)
Other versions
CN113259844B (en
Inventor
梁栋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Qidaisong Technology Co ltd
Original Assignee
Beijing Qidaisong Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Qidaisong Technology Co ltd filed Critical Beijing Qidaisong Technology Co ltd
Priority to CN202110663333.2A priority Critical patent/CN113259844B/en
Publication of CN113259844A publication Critical patent/CN113259844A/en
Application granted granted Critical
Publication of CN113259844B publication Critical patent/CN113259844B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/025—Services making use of location information using location based information parameters
    • H04W4/026—Services making use of location information using location based information parameters using orientation information, e.g. compass
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
    • G01P13/00—Indicating or recording presence, absence, or direction, of movement
    • G01P13/02—Indicating direction only, e.g. by weather vane
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/025—Services making use of location information using location based information parameters
    • H04W4/027—Services making use of location information using location based information parameters using movement velocity, acceleration information
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The invention relates to an indoor human body orientation recognition system based on a reversible positioning label, which is realized by the following steps: step S1, obtaining N pieces of map location information closest to the current time from the first database { S }1，S2，…SNAnd corresponding N pieces of map deflection angle information
Figure 371607DEST_PATH_IMAGE001
(ii) a Step S2, based on { S1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map accord with preset linear tracks or not, if so, executing a step S3, otherwise, returning to the step S1; step S3, obtaining
Figure 614500DEST_PATH_IMAGE002
And make a judgment on
Figure 121705DEST_PATH_IMAGE002
Whether the angle difference is greater than a preset second angle difference or not, if so, based on
Figure 487176DEST_PATH_IMAGE001
After updating the current initialization direction binding angle ∂, executing step S4, otherwise, directly executing step S4; step S4 based on
Figure 271592DEST_PATH_IMAGE003
Determining a current human body orientation angle of a person wearing the positioning tag based on the semantic map
Figure DEST_PATH_IMAGE004
Then, the process returns to step S1. The invention improves the accuracy of indoor human body orientation identification and reduces the computational power requirement.

Description

Indoor human body orientation recognition system based on reversible positioning tags
Technical Field
The invention relates to the technical field of computers, in particular to an indoor human body orientation identification system based on a turnable positioning label.
Background
In many existing indoor application scenarios, human body orientation needs to be recognized, for example, in an exhibition scenario, a human body orientation is recognized to determine a human traveling direction, analyze human interest targets, human communication objects, and the like. First, the orientation of a mobile device (e.g., a mobile phone) is bound to be the human orientation, and the human orientation is determined based on an existing indoor map based on a magnetometer or compass of the mobile device. Second, the human body orientation is estimated by recognizing the human face and the posture based on the indoor camera.
However, the existing human body orientation recognition technology has at least the following disadvantages: the first scheme, especially in a region with a complicated magnetic field environment (e.g., a region with a large amount of metal), is greatly affected by the magnetic field environment, resulting in inaccurate orientation of the identified human body, and further, since a person carries the mobile device in a variety of usage scenarios, such as holding the mobile device in a hand or placing the mobile device in a pocket, the orientation of the human body and the orientation of the mobile device are likely to be inconsistent, so that the first scheme has low accuracy of human body orientation identification. In addition, the second scheme has high requirement on an example, and the face recognition needs high calculation force support based on the posture of the deep neural network. Therefore, it is known how to fully cover the human body orientation calculation of the indoor positioning area, improve the accuracy of the indoor human body orientation recognition, and reduce the calculation force requirement, which is a technical problem to be solved urgently.
Disclosure of Invention
The invention aims to provide an indoor human body orientation identification system based on a turnable positioning label, which can comprehensively cover the human body orientation calculation of an indoor positioning area, improve the accuracy of indoor human body orientation identification and reduce the calculation force requirement.
According to one aspect of the invention, an indoor human body orientation identification system based on a reversible positioning tag is provided, which comprises a server and a positioning tag used for being worn on a human body, wherein the server comprises a pre-constructed semantic map, a first database, a processor and a memory stored with a computer program, and the positioning tag comprises a positioning device and an accelerometer; the server receives an information pair reported by a positioning device and an accelerometer of the positioning label at preset time intervals in real time, wherein the information pair comprises original position information and original acceleration information, the original position information and the original acceleration information are converted into map position information and map deflection angle information relative to the semantic map, the map deflection angle information is deflection angle information of the accelerometer relative to an X axis of the semantic map, and the deflection angle information is stored in the first database according to the reporting time sequence; when the processor is executing the computer program, the following steps are implemented:
step C1, obtaining N map position information S closest to the current time from the first database1，S2，…SNAnd corresponding N pieces of map declination information [ theta ]1，θ2，…θNIn which S is1，S2，…SNAnd theta1，θ2，…θNAre all ordered according to the time interval from the reporting time to the current time from small to large, SiIndicating the ith map position information, theta, nearest to the current timeiRepresents the ith map declination information closest to the current time, i =1,2, … N;
step C2, based on { S1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map accord with preset linear tracks or not, if so, executing the step C3, otherwise, returning to the step C1;
step C3, obtaining |. theta1-θN| and determining | theta1-θN-whether or not said positioning tag is greater than a predetermined second angular difference, and if so, determining that said positioning tag is oriented from θiCorresponding reporting time thetaNThe corresponding report time period is turned over based on the { theta1，θ2，…θNExecuting step C4 after updating the current initialization direction binding angle ∂, otherwise, directly executing step C4, wherein the initialization direction binding angle is the initialization direction binding angle between the human body and the positioning label;
step C4 based on theta1、θ2∂ determining a current body orientation angle Φ of a person wearing the localization tag based on the semantic map1=θ1-θ2+ ∂, where ∂ binds the angle for the current initialization direction, and then returns to step C1.
Compared with the prior art, the invention has obvious advantages and beneficial effects. By means of the technical scheme, the indoor human body orientation identification system based on the turnable positioning label can achieve considerable technical progress and practicability, has industrial wide utilization value and at least has the following advantages:
the invention can comprehensively cover the human body orientation calculation of the indoor positioning area without completely depending on the information collected by the camera, and can obtain the human body orientation angle based on the semantic map in combination with the position information and the angle information, thereby being used even in the scene of crowded indoor people and complex environment. The invention can dynamically update the human body and the initial direction binding angle of the positioning label by judging whether the positioning label is overturned, thereby reducing the influence of system errors and improving the robustness of the system. And angle information is acquired based on the accelerometer, so that the influence of a magnetic field is avoided, and the accuracy of indoor human body orientation identification is improved. In addition, the embodiment of the invention does not need to adopt a complex deep neural network, reduces the calculation force requirement and saves the cost.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the present invention may be implemented in accordance with the content of the description, and in order to make the above and other objects, features, and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
Fig. 1 is a schematic diagram of an indoor human body orientation recognition system based on a non-reversible positioning tag according to an embodiment of the present invention;
fig. 2 is a schematic view of an indoor human body orientation recognition system based on a reversible positioning tag according to a second embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description will be made with reference to the accompanying drawings and preferred embodiments for an indoor human body orientation recognition system based on a reversible positioning tag according to the present invention.
Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps may be rearranged. A process may be terminated when its operations are completed, but may have additional steps not included in the figure. A process may correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.
The first embodiment,
The first embodiment is suitable for a scene that the label is worn relatively fixedly, namely, the first embodiment is an application scene that the positioning label is changed into a positioning label which cannot be turned over, for example, the positioning label is installed on a hat or is buckled on clothes, and the positioning label is worn, namely, the positioning label is not easy to turn over after being worn. Specifically, an embodiment of the present invention provides an indoor human body orientation identification system based on a non-reversible positioning tag, as shown in fig. 1, including a server and a positioning tag used for being worn on a human body, where the server includes a pre-constructed semantic map, a first database, a processor, and a memory storing a computer program, and the positioning tag includes a positioning device and an accelerometer; the server receives an information pair reported by a positioning device and an accelerometer of the positioning label at a preset time interval in real time, wherein the information pair comprises original position information and original acceleration information, the original position information and the original acceleration information are converted into map position information and map deflection angle information relative to the semantic map, the map deflection angle information is deflection angle information of the accelerometer relative to an X axis of the semantic map, and the deflection angle information is stored in the first database according to the reporting time sequence.
After the positioning tag is worn on a human body, the original position information and the original acceleration information of the positioning tag can change along with the movement of the human body. The semantic map is a map of indoor meaning constructed according to an indoor environment, and includes information such as where a person can pass through, where an obstacle exists, and where a person can stand or sit. The original position information and the original acceleration information reported by the positioning tag are data obtained by direct measurement of positioning equipment and an accelerometer based on the positioning tag. The semantic map and the display map (namely, the map established by the existing positioning mode such as GSP) have a mapping relation, the original position information and the original acceleration information correspond to the display map, and the original position information can be converted into the map position information relative to the semantic map based on the mapping relation of the original map and the semantic map. Based on the accelerometer, the acceleration component in the space established relative to the X axis and the Y axis of the display map can be solved through the existing geometric operation, and then the declination angle relative to the X axis of the display map can be solved based on the gravity g, so that the map declination angle information relative to the semantic map can be obtained. The positioning device of the positioning tag can specifically adopt the cellular positioning technology, Wi-Fi, Bluetooth, infrared rays, Ultra Wide Band (UWB), Radio Frequency Identification (RFID), ZigBee, motion capture, ultrasonic and other indoor positioning technologies to perform positioning. The accelerometer may specifically be iMU (Inertial measurement unit), iMU is a device for measuring the three-axis attitude angle (or angular rate) and the acceleration of the object, and the embodiment of the present invention only uses the acceleration information acquired by iMU.
When the processor is executing the computer program, the following steps are implemented:
step S1, obtaining N map location information { S } nearest to the current time from the first database1，S2，…SNAnd corresponding N pieces of map declination information [ theta ]1，θ2，…θNIn which S is1，S2，…SNAnd theta1，θ2，…θNAre all ordered according to the time interval from the reporting time to the current time from small to large, SiIndicating the ith map position information, theta, nearest to the current timeiRepresents the ith map declination information closest to the current time, i =1,2, … N;
the value of N is specifically set according to parameters such as the system calculation precision and the resolution of the semantic map.
Step S2, based on { S1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map accord with preset linear tracks or not, if so, executing a step S3, otherwise, returning to the step S1;
it should be noted that, when the human body walks along a straight line, the initial direction binding angle between the human body and the positioning tag can be accurately calculated, so that the initial direction binding angle needs to be based on { S }1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map conform to a preset linear track or not.
Step S3, obtaining |. theta1-θN| and determining | theta1-θNIf yes, based on { theta |, if not, then1，θ2，…θNExecuting step S4 after updating the current initialization direction binding angle ∂, otherwise, directly executing step S4, wherein the initialization direction binding angle is the initialization direction binding angle between the human body and the positioning label;
the human body orientation angle is bound with the orientation angle of the positioning tag based on the initialized orientation binding angle ∂, that is, the orientation angle obtained subsequently based on the positioning tag is the human body orientation angle. It should be noted that, since the system may have accumulated errors over time, a first angular difference for characterizing the system errors is set, and preferably, the first angular difference may be set to be equal to or less than 10 °, when | θ1-θN| is greater than the first angular difference, in { S }1，S2，…SNAnd when the track on the semantic map conforms to the preset linear track, updating the initialized direction binding angle ∂ again, thereby improving the accuracy of the system for acquiring the orientation angle of the human body. It is understood that, when the initial direction binding angle is acquired for the first time when the positioning tag is initially worn, the step S3 is directly based on θ1，θ2，…θNGet the current initialization direction binding angle ∂ without determining | θ1-θN-whether it is greater than a predetermined first angular difference. In an actual use scene, in order to obtain an initial direction binding angle as soon as possible, a straight path with a preset distance can be set at an indoor entrance, so that the initial direction binding angle can be obtained as soon as possible, and the human body orientation angle can be calculated as soon as possible.
Step S4 based on theta1、θ2∂ determining a current body orientation angle Φ of a person wearing the localization tag based on the semantic map1=θ1-θ2+ ∂, where ∂ is the current initialization direction binding angle, then return to step S1.
According to the embodiment of the invention, the human body orientation calculation of the indoor positioning area can be comprehensively covered without completely depending on the information acquired by the camera, and the human body orientation angle is acquired based on the semantic map in combination with the position information and the angle information, so that the method and the device can be used even in the scene of crowded indoor people and complex environment. In addition, the initialization direction binding angle of the human body and the positioning label can be dynamically updated, the influence of system errors is reduced, and the robustness of the system is improved. And angle information is acquired based on the accelerometer, so that the influence of a magnetic field is avoided, and the accuracy of indoor human body orientation identification is improved. In addition, the embodiment of the invention does not need to adopt a complex deep neural network, reduces the calculation force requirement and saves the cost.
It can be understood that, when the included angle between the X axis of the semantic map and the X axis of the display map is 0, the current human body orientation angle of the semantic map is the current human body orientation angle of the person wearing the positioning tag based on the display map, and when the included angle between the X axis of the semantic map and the X axis of the display map is not 0, if the included angle between the X axis of the display map and the X axis of the semantic map is β, the step S4 further includes:
step S41, based on the current human body orientation angle phi of the person wearing the positioning label based on the semantic map1And the included angle beta between the X axis of the display map and the X axis of the semantic map, and determining the current human body orientation angle phi of the person wearing the positioning label based on the display map2=Φ1+β。
It is understood that the system may further include a display device for displaying the display map in real time, and dynamically displaying the position and orientation of the human body on the display map.
As an embodiment, the semantic map is divided into a plurality of grids, a state value of each grid is 1 or 0, a state value of a grid is 0 indicates that the corresponding location can walk, a state value of a grid is 1 indicates that the corresponding location cannot walk, each map location information corresponds to a grid of the semantic map, and in step S2, the map is based on { S { (S) } S1，S2，…SNJudging whether the trajectories of the N map positions closest to the current moment on the semantic map conform to a preset linear trajectory or not, wherein the judging step can comprise the following steps of:
step S201. Obtain each S1，S2，…SNThe grid central point corresponding to the position information of each map in the map and judging S1，S2，…SNAnd if so, determining that the tracks of the N map positions closest to the current moment on the semantic map conform to a preset linear track.
It is understood that step S201 is performed in a manner of not considering map position errors, but position jitter within an error tolerance range may occur in the actual position, so that errors that can be tolerated by the system can be taken into account, and the position jitter within the error tolerance range is also determined to be on a preset straight-line trajectory, specifically, as an example, in step S2, the step is based on { S }1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map conform to a preset linear track or not, and further comprising:
step S211, based on S1Corresponding grid center point and SNDetermining a reference straight line on the semantic map by the corresponding grid center point;
step S212, based on SiCorresponding grid center point and Si+1And determining an ith straight line on the semantic map by the corresponding grid central point, and acquiring an ith included angle between the ith straight line and the reference straight line, wherein i is taken from 1 to 9, and if the ith included angle is less than or equal to a preset included angle threshold value, judging that the track of N map positions closest to the current moment on the semantic map conforms to a preset straight line track.
Wherein the included angle threshold is less than or equal to 45 °, and as a preferred embodiment, the included angle threshold is equal to 45 °.
As an example, in the step S3, the basis is { theta }1，θ2，…θNUpdating the current initialization direction binding angle ∂, including:
step S301 based on theta1And thetaNUpdating current initialization direction binding angle
Figure 929586DEST_PATH_IMAGE001
。
Since there may be a certain error in the map deflection angle information during the actual measurement process, in order to improve the accuracy of the initial direction binding angle calculation, as an embodiment, in the step S3, the basis is θ1，θ2，…θNUpdating the current initialization direction binding angle ∂, including:
step S311 based on { theta1，θ2，…θNUpdating the binding angle of the current initialization direction
Figure 693142DEST_PATH_IMAGE002
。
To further improve the accuracy of the system in calculating the body orientation angle, may be { θ }1，θ2，…θNAssigning a corresponding weight to each map bias angle, and making the bias angle closer to the current time point have a larger weight, as an embodiment, in the step S3, the map bias angles are based on { theta }1，θ2，…θNUpdating the current initialization direction binding angle ∂, including:
step S321, based on { theta1，θ2，…θNUpdating the binding angle of the current initialization direction
Figure 543418DEST_PATH_IMAGE003
Wherein α isiIs thetaiWeight of (a), θiThe closer the corresponding reporting time is to the current time, alphaiThe larger.
It will be appreciated that obstacles in the room are likely to move locations and therefore, to further improve the accuracy of the system, the semantic map may also be updated periodically. As an embodiment, the server further includes a second database for storing indoor obstacle position information, where the obstacle position refers to a position where indoor people cannot pass through, the system further includes an information acquisition device capable of dynamically scanning the indoor obstacle position, which may be specifically a robot with a scanning radar, and when the processor executes the computer program, the following steps are implemented:
step S10, receiving the current indoor obstacle position information reported by the information acquisition device, and storing the current indoor obstacle position information in the second database;
and step S20, updating the semantic map based on the position information of the indoor obstacle at the current moment in the second database at every preset second time interval.
As an embodiment, if the current positioning area is provided with the visual positioning device and the current human body orientation can be calculated by clearly acquiring data, the binding relationship between the positioning tag and the human body orientation can be calibrated based on the visual positioning data, and the current human body orientation angle can also be directly acquired, so that the accuracy of the system for acquiring the human body orientation angle is further improved.
The positioning tag can be worn on the neck of a human body or in a pocket through a cord, and under the condition, if the positioning tag rotates to a larger extent, for example, the positioning tag is installed on a chest card, and the chest card is turned over in the action process of the human body, so that the turning over of the positioning tag is caused, the initialized binding angle is not accurate any more, and the calculation result of the body orientation angle is influenced.
Example II,
The second embodiment is suitable for an application scenario in which the positioning tag is reversible, that is, the positioning tag in the second embodiment is a reversible tag, and specifically, the second embodiment provides an indoor human body orientation identification system based on the reversible positioning tag, as shown in fig. 2, (it is noted that the system framework of the first embodiment and the system framework of the second embodiment are similar, but the steps implemented by the processor executing the computer program are different) comprising a server and a positioning tag for wearing on a human body, wherein the server comprises a pre-constructed semantic map, a first database, a processor and a memory storing the computer program, and the positioning tag comprises a positioning device and an accelerometer; the server receives an information pair reported by a positioning device and an accelerometer of the positioning label at preset time intervals in real time, wherein the information pair comprises original position information and original acceleration information, the original position information and the original acceleration information are converted into map position information and map deflection angle information relative to the semantic map, the map deflection angle information is deflection angle information of the accelerometer relative to an X axis of the semantic map, and the deflection angle information is stored in the first database according to the reporting time sequence; when the processor is executing the computer program, the following steps are implemented:
after the positioning tag is worn on a human body, the original position information and the original acceleration information of the positioning tag can change along with the movement of the human body. The semantic map is a map of indoor meaning constructed according to an indoor environment, and includes information such as where a person can pass through, where an obstacle exists, and where a person can stand or sit. The original position information and the original acceleration information reported by the positioning tag are data obtained by direct measurement of positioning equipment and an accelerometer based on the positioning tag. The semantic map and the display map (namely, the map established by the existing positioning mode such as GSP) have a mapping relation, the original position information and the original acceleration information correspond to the display map, and the original position information can be converted into the map position information relative to the semantic map based on the mapping relation of the original map and the semantic map. Based on the accelerometer, the acceleration component in the space established relative to the X axis and the Y axis of the display map can be solved through the existing geometric operation, and then the declination angle relative to the X axis of the display map can be solved based on the gravity g, so that the map declination angle information relative to the semantic map can be obtained. The positioning device of the positioning tag can specifically adopt the cellular positioning technology, Wi-Fi, Bluetooth, infrared rays, Ultra Wide Band (UWB), Radio Frequency Identification (RFID), ZigBee, motion capture, ultrasonic and other indoor positioning technologies to perform positioning. The accelerometer may specifically be iMU (Inertial measurement unit), iMU is a device for measuring the three-axis attitude angle (or angular rate) and the acceleration of the object, and the embodiment of the present invention only uses the acceleration information acquired by iMU.
Step C1, obtaining the current time from the first databaseNearest N pieces of map position information S1，S2，…SNAnd corresponding N pieces of map declination information [ theta ]1，θ2，…θNIn which S is1，S2，…SNAnd theta1，θ2，…θNAre all ordered according to the time interval from the reporting time to the current time from small to large, SiIndicating the ith map position information, theta, nearest to the current timeiRepresents the ith map declination information closest to the current time, i =1,2, … N;
the value of N is specifically set according to parameters such as the system calculation precision and the resolution of the semantic map.
Step C2, based on { S1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map accord with preset linear tracks or not, if so, executing a step S3, otherwise, returning to the step C1;
it should be noted that, when the human body walks along a straight line, the initial direction binding angle between the human body and the positioning tag can be accurately calculated, so that the initial direction binding angle needs to be based on { S }1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map conform to a preset linear track or not.
Step C3, obtaining |. theta1-θN| and determining | theta1-θN-whether or not said positioning tag is greater than a predetermined second angular difference, and if so, determining that said positioning tag is oriented from θ1Corresponding reporting time thetaNThe corresponding report time period is turned over based on the { theta1，θ2，…θNExecuting step C4 after updating the current initialization direction binding angle ∂, otherwise, directly executing step C4, wherein the initialization direction binding angle is the initialization direction binding angle between the human body and the positioning label;
the human body orientation angle is bound with the orientation angle of the positioning tag based on the initialized orientation binding angle ∂, that is, the orientation angle obtained subsequently based on the positioning tag is the human body orientation angle. Need to explainWhereas a large angular deviation occurs when the positioning tag is reversed, and therefore the initial binding angle needs to be adjusted, preferably the second angular difference may be set to 45, when | θ1-θN| is greater than the second angular difference, in { S1，S2，…SNAnd when the track on the semantic map conforms to the preset linear track, updating the initialized direction binding angle ∂ again, thereby improving the accuracy of the system for acquiring the orientation angle of the human body. It will be appreciated that the step C3 is based directly on θ when the initial orientation binding angle is first obtained when the orientation tag is initially worn1，θ2，…θNGet the current initialization direction binding angle ∂ without determining | θ1-θN-whether it is greater than a predetermined second angular difference. In an actual use scene, in order to obtain an initial direction binding angle as soon as possible, a straight path with a preset distance can be set at an indoor entrance, so that the initial direction binding angle can be obtained as soon as possible, and the human body orientation angle can be calculated as soon as possible.
Step C4 based on theta1、θ2∂ determining a current body orientation angle Φ of a person wearing the localization tag based on the semantic map1=θ1-θ2+ ∂, where ∂ binds the angle for the current initialization direction, and then returns to step C1.
According to the second embodiment of the invention, the human body orientation calculation of the indoor positioning area can be comprehensively covered without completely depending on the information acquired by the camera, and the human body orientation angle is acquired based on the semantic map in combination with the position information and the angle information, so that the second embodiment of the invention can be used even in the scene of crowded indoor people and complex environment. In addition, the second embodiment of the invention can dynamically update the human body and the initial direction binding angle of the positioning label by judging whether the positioning label is overturned, thereby reducing the influence of system errors and improving the robustness of the system. And angle information is acquired based on the accelerometer, so that the influence of a magnetic field is avoided, and the accuracy of indoor human body orientation identification is improved. In addition, the embodiment of the invention does not need to adopt a complex deep neural network, reduces the calculation force requirement and saves the cost.
It can be understood that, when the included angle between the X axis of the semantic map and the X axis of the display map is 0, the current human body orientation angle of the semantic map is the current human body orientation angle of the person wearing the positioning tag based on the display map, and when the included angle between the X axis of the semantic map and the X axis of the display map is not 0, if the included angle between the X axis of the display map and the X axis of the semantic map is β, the step C4 further includes:
step C41, based on the current human body orientation angle phi of the person wearing the positioning label based on the semantic map1And the included angle beta between the X axis of the display map and the X axis of the semantic map, and determining the current human body orientation angle phi of the person wearing the positioning label based on the display map2=Φ1+β。
It is understood that the system may further include a display device for displaying the display map in real time, and dynamically displaying the position and orientation of the human body on the display map.
As an embodiment, the semantic map is divided into a plurality of grids, a state value of each grid is 1 or 0, a grid state value of 0 indicates that the corresponding location can walk, a grid state value of 1 indicates that the corresponding location cannot walk, and each map location information corresponds to one grid of the semantic map, in the step C2, the map location information is based on { S } S1，S2，…SNJudging whether the trajectories of the N map positions closest to the current moment on the semantic map conform to a preset linear trajectory or not, wherein the judging step can comprise the following steps of:
step C201, obtaining each S1，S2，…SNThe grid central point corresponding to the position information of each map in the map and judging S1，S2，…SNAnd if so, determining that the tracks of the N map positions closest to the current moment on the semantic map conform to a preset straight-line track.
It is understood that step C201 is performed in a manner that the map position error is not considered, but the actual position may have position jitter within the error tolerance range, so that the system may be modifiedConsidering the tolerable error of the system, the position jitter within the tolerance range is determined to be on the predetermined straight track, specifically, as an embodiment, in the step C2, the step C2 is based on { S }1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map conform to a preset linear track or not, and further comprising:
step C211, based on S1Corresponding grid center point and SNDetermining a reference straight line on the semantic map by the corresponding grid center point;
step C212, based on SiCorresponding grid center point and Si+1And determining an ith straight line on the semantic map by the corresponding grid central point, and acquiring an ith included angle between the ith straight line and the reference straight line, wherein i is taken from 1 to 9, and if the ith included angle is less than or equal to a preset included angle threshold value, judging that the track of N map positions closest to the current moment on the semantic map conforms to a preset straight line track.
Wherein the included angle threshold is less than or equal to 45 °, and as a preferred embodiment, the included angle threshold is equal to 45 °.
As an embodiment, in order to improve the calculation efficiency of the system, the current map bias angle may be directly used as the current initialization direction binding angle, specifically, in the step C3, the basis is { θ } θ1，θ2，…θNUpdating the current initialization direction binding angle ∂, including:
step C301, based on the map declination angle theta nearest to the current time1Determining a current initialization direction binding angle ∂ = θ1。
In order to improve the system accuracy, the turning point may be determined first, and then the current initialization direction binding angle ∂ may be obtained based on the map drift angle corresponding to the turning point and the following point, as an example, in step C3, the map drift angle is based on { θ [ ]1，θ2，…θNUpdating the current initialization direction binding angle ∂, including:
step C311, based on { theta1，θ2，…θNDeterminationMap deflection angle theta corresponding to turning pointk；
Step C312, based on { theta1，θ2，…θkUpdate the current initialization direction binding angle ∂.
As an embodiment, the step C311 includes:
step C3111, let i = 10;
step C3112, obtaining deviation angle difference delta between two adjacent mapsi=θi-θi-1；
Step C3113, judgment
Figure 290794DEST_PATH_IMAGE004
Whether the angle difference is greater than the second angle difference or not, if so, determining the current thetaiIs determined as thetakOtherwise, let i = i-1, return to step S3112.
The step C312 includes:
step C3121, based on { theta1，θ2，…θkUpdating the binding angle of the current initialization direction
Figure 986349DEST_PATH_IMAGE002
。
To further improve the accuracy of the system in calculating the body orientation angle, may be { θ }1，θ2，…θkEach map declination in the map view is assigned a corresponding weight, and the declination closer to the current time is given a larger weight, as an embodiment, the step C312 includes:
step C3122, based on { theta1，θ2，…θkUpdating the binding angle of the current initialization direction
Figure 197887DEST_PATH_IMAGE005
Wherein α isiIs thetaiWeight of (a), θiThe closer the corresponding reporting time is to the current time, alphaiThe larger.
It will be appreciated that obstacles in the room are likely to move locations and therefore, to further improve the accuracy of the system, the semantic map may also be updated periodically. As an embodiment, the server further includes a second database for storing indoor obstacle position information, where the obstacle position refers to a position where indoor people cannot pass through, the system further includes an information acquisition device capable of dynamically scanning the indoor obstacle position, which may be specifically a robot with a scanning radar, and when the processor executes the computer program, the following steps are implemented:
step C10, receiving the current indoor obstacle position information reported by the information acquisition equipment, and storing the current indoor obstacle position information in the second database;
and step C20, updating the semantic map based on the position information of the indoor obstacle at the current moment in the second database at every preset second time interval.
As an embodiment, if the current positioning area is provided with the visual positioning device and the current human body orientation can be calculated by clearly acquiring data, the binding relationship between the positioning tag and the human body orientation can be calibrated based on the visual positioning data, and the current human body orientation angle can also be directly acquired, so that the accuracy of the system for acquiring the human body orientation angle is further improved.
It should be noted that, the first embodiment and the second embodiment may also be combined, and the initial binding angle is updated by considering both the system error and whether the system is turned over, thereby further improving the universality of the system application.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (10)

1. An indoor human body orientation identification system based on a reversible positioning label is characterized in that,
the system comprises a server and a positioning tag used for being worn on a human body, wherein the server comprises a pre-constructed semantic map, a first database, a processor and a memory stored with a computer program, and the positioning tag comprises a positioning device and an accelerometer; the server receives an information pair reported by a positioning device and an accelerometer of the positioning label at preset time intervals in real time, wherein the information pair comprises original position information and original acceleration information, the original position information and the original acceleration information are converted into map position information and map deflection angle information relative to the semantic map, the map deflection angle information is deflection angle information of the accelerometer relative to an X axis of the semantic map, and the deflection angle information is stored in the first database according to the reporting time sequence; when the processor is executing the computer program, the following steps are implemented:
step C1, obtaining N map position information S closest to the current time from the first database1，S2，…SNAnd corresponding N pieces of map declination information [ theta ]1，θ2，…θNIn which S is1，S2，…SNAnd theta1，θ2，…θNAre all ordered according to the time interval from the reporting time to the current time from small to large, SiIndicating the ith map position information, theta, nearest to the current timeiRepresents the ith map declination information closest to the current time, i =1,2, … N;
step C2, based on { S1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map accord with preset linear tracks or not, if so, executing the step C3, otherwise, returning to the step C1;
step C3, obtaining |. theta1-θN| and determining | theta1-θN-whether or not said positioning tag is greater than a predetermined second angular difference, and if so, determining that said positioning tag is oriented from θ1Corresponding reporting time thetaNThe corresponding report time period is turned over based on the { theta1，θ2，…θNExecuting step C4 after updating the current initialization direction binding angle ∂, otherwise, directly executing step C4, wherein the initialization direction binding angle is the initialization direction binding angle between the human body and the positioning label;
step C4 based on theta1、θ2∂ determining a current body orientation angle Φ of a person wearing the localization tag based on the semantic map1=θ1-θ2+ ∂, where ∂ binds the angle for the current initialization direction, and then returns to step C1.
2. The system of claim 1,
the server further includes a display map, and an included angle between the X-axis of the display map and the X-axis of the semantic map is β, then step C4 further includes:
step C41, based on the current human body orientation angle phi of the person wearing the positioning label based on the semantic map1And the included angle beta between the X axis of the display map and the X axis of the semantic map, and determining the current human body orientation angle phi of the person wearing the positioning label based on the display map2=Φ1+β。
3. The system of claim 1,
the semantic map is divided into a plurality of grids, a state value of each grid is 1 or 0, a state value of each grid is 0 to indicate that a corresponding position can walk, a state value of each grid is 1 to indicate that a corresponding position cannot walk, and position information of each map corresponds to one grid of the semantic map, in the step C2, the map is based on { S { (S) } S1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map conform to a preset linear track or not, wherein the judging step comprises the following steps of:
step C201, obtaining each S1，S2，…SNPosition information of each mapCorresponding grid center point, and judging S1，S2，…SNAnd if so, determining that the tracks of the N map positions closest to the current moment on the semantic map conform to a preset straight-line track.
4. The system of claim 1,
the semantic map is divided into a plurality of grids, a state value of each grid is 1 or 0, a state value of each grid is 0 to indicate that a corresponding position can walk, a state value of each grid is 1 to indicate that a corresponding position cannot walk, and position information of each map corresponds to one grid of the semantic map, in the step C2, the map is based on { S { (S) } S1，S2，…SNJudging whether the tracks of the N map positions closest to the current moment on the semantic map conform to a preset linear track or not, wherein the judging step comprises the following steps of:
step C211, based on S1Corresponding grid center point and SNDetermining a reference straight line on the semantic map by the corresponding grid center point;
step C212, based on SiCorresponding grid center point and Si+1And determining an ith straight line on the semantic map by the corresponding grid central point, and acquiring an ith included angle between the ith straight line and the reference straight line, wherein i is taken from 1 to 9, and if the ith included angle is less than or equal to a preset included angle threshold value, judging that the track of N map positions closest to the current moment on the semantic map conforms to a preset straight line track.
5. The system of claim 4,
the included angle threshold value is less than or equal to 45 degrees.
6. The system of claim 1,
in the step C3, the basis is { theta [ ]1，θ2，…θNUpdating the current initialization direction binding angle ∂, including:
step C301, based on the map declination angle theta nearest to the current time1Determining a current initialization direction binding angle ∂ = θ1。
7. The system of claim 1,
in the step C3, the basis is { theta [ ]1，θ2，…θNUpdating the current initialization direction binding angle ∂, including:
step C311, based on { theta1，θ2，…θNDetermining map deflection angle theta corresponding to turning pointk；
Step C312, based on { theta1，θ2，…θkUpdate the current initialization direction binding angle ∂.
8. The system of claim 7,
the step C311 includes:
step C3111, let i = 10;
step C3112, obtaining deviation angle difference delta between two adjacent mapsi=θi-θi-1；
Step C3113, determining deltaiWhether the angle difference is greater than the second angle difference or not, if so, determining the current thetaiIs determined as thetakOtherwise, let i = i-1, return to step C3112.
9. The system of claim 8,
the step C312 includes:
step C3121, based on { theta1，θ2，…θkUpdating the binding angle of the current initialization direction
Figure 3152DEST_PATH_IMAGE001
。
10. The system of claim 8,
the step C312 includes:
step C3122, based on { theta1，θ2，…θkUpdating the binding angle of the current initialization direction
Figure 810702DEST_PATH_IMAGE002
，
Wherein alpha isiIs thetaiWeight of (a), θiThe closer the corresponding reporting time is to the current time, alphaiThe larger.
CN202110663333.2A 2021-06-16 2021-06-16 Indoor human body orientation recognition system based on reversible positioning tags Active CN113259844B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110663333.2A CN113259844B (en) 2021-06-16 2021-06-16 Indoor human body orientation recognition system based on reversible positioning tags

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110663333.2A CN113259844B (en) 2021-06-16 2021-06-16 Indoor human body orientation recognition system based on reversible positioning tags

Publications (2)

Publication Number Publication Date
CN113259844A true CN113259844A (en) 2021-08-13
CN113259844B CN113259844B (en) 2021-09-28

Family

ID=77188045

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110663333.2A Active CN113259844B (en) 2021-06-16 2021-06-16 Indoor human body orientation recognition system based on reversible positioning tags

Country Status (1)

Country Link
CN (1) CN113259844B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170248428A1 (en) * 2016-02-25 2017-08-31 Electronics And Telecommunications Research Institute Indoor positioning system and method
US20190271554A1 (en) * 2018-03-02 2019-09-05 DeepMap Inc. Semantic label based filtering of objects in an image generated from high definition map data
US20200158862A1 (en) * 2018-11-19 2020-05-21 Invensense, Inc. Method and system for positioning using radar and motion sensors
CN113115214A (en) * 2021-06-16 2021-07-13 北京奇岱松科技有限公司 Indoor human body orientation recognition system based on non-reversible positioning tag

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170248428A1 (en) * 2016-02-25 2017-08-31 Electronics And Telecommunications Research Institute Indoor positioning system and method
US20190271554A1 (en) * 2018-03-02 2019-09-05 DeepMap Inc. Semantic label based filtering of objects in an image generated from high definition map data
US20200158862A1 (en) * 2018-11-19 2020-05-21 Invensense, Inc. Method and system for positioning using radar and motion sensors
CN113115214A (en) * 2021-06-16 2021-07-13 北京奇岱松科技有限公司 Indoor human body orientation recognition system based on non-reversible positioning tag

Also Published As

Publication number Publication date
CN113259844B (en) 2021-09-28

Similar Documents

Publication Publication Date Title
CN107635204B (en) Indoor fusion positioning method and device assisted by exercise behaviors and storage medium
Ban et al. Indoor positioning method integrating pedestrian Dead Reckoning with magnetic field and WiFi fingerprints
EP2946167B1 (en) Method and apparatus for determination of misalignment between device and pedestrian
KR102226846B1 (en) System for Positioning Hybrid Indoor Localization Using Inertia Measurement Unit Sensor and Camera
Ouyang et al. A survey of magnetic-field-based indoor localization
Altun et al. Pedestrian dead reckoning employing simultaneous activity recognition cues
Elloumi et al. Indoor navigation assistance with a Smartphone camera based on vanishing points
CN112525197B (en) Ultra-wideband inertial navigation fusion pose estimation method based on graph optimization algorithm
Wang et al. Pose-invariant inertial odometry for pedestrian localization
CN110412596A (en) A kind of robot localization method based on image information and laser point cloud
Wu et al. Indoor positioning based on walking-surveyed Wi-Fi fingerprint and corner reference trajectory-geomagnetic database
Park et al. Robust pedestrian dead reckoning for multiple poses in smartphones
CN112729301A (en) Indoor positioning method based on multi-source data fusion
Shu et al. Efficient image-based indoor localization with MEMS aid on the mobile device
Cruz et al. MagLand: Magnetic landmarks for road vehicle localization
Qian et al. An improved particle filter based indoor tracking system via joint Wi-Fi/PDR localization
Manos et al. Walking direction estimation using smartphone sensors: A deep network-based framework
CN113115214B (en) Indoor human body orientation recognition system based on non-reversible positioning tag
KR102095135B1 (en) Method of positioning indoor and apparatuses performing the same
CN115112121A (en) Multi-source fusion positioning method, system and terminal based on combination of data and model
Shu et al. Indoor geomagnetic positioning using direction-aware multiscale recurrent neural networks
Kuusniemi et al. Multi-sensor multi-network seamless positioning with visual aiding
Saadatzadeh et al. An improvement in smartphone-based 3D indoor positioning using an effective map matching method
CN113259844B (en) Indoor human body orientation recognition system based on reversible positioning tags
Shu et al. Accurate indoor 3d location based on mems/vision by using a smartphone

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