[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN112770251A - Self-adaptive human behavior data acquisition and identification system and method based on UWB and LoRa - Google Patents

Self-adaptive human behavior data acquisition and identification system and method based on UWB and LoRa Download PDF

Info

Publication number
CN112770251A
CN112770251A CN202011622869.1A CN202011622869A CN112770251A CN 112770251 A CN112770251 A CN 112770251A CN 202011622869 A CN202011622869 A CN 202011622869A CN 112770251 A CN112770251 A CN 112770251A
Authority
CN
China
Prior art keywords
data
uwb
lora
module
base station
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
CN202011622869.1A
Other languages
Chinese (zh)
Other versions
CN112770251B (en
Inventor
许宏吉
冯金库
熊海良
元辉
董郑
樊士迪
李恬阔
赵文杰
孙晓杰
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.)
Shandong University
Original Assignee
Shandong University
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 Shandong University filed Critical Shandong University
Priority to CN202011622869.1A priority Critical patent/CN112770251B/en
Publication of CN112770251A publication Critical patent/CN112770251A/en
Application granted granted Critical
Publication of CN112770251B publication Critical patent/CN112770251B/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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/285—Selection of pattern recognition techniques, e.g. of classifiers in a multi-classifier system
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/14—Reselecting a network or an air interface
    • 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
    • H04W4/30—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
    • 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
    • H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention belongs to the technical field of positioning and the field of pattern recognition, and provides a self-adaptive human behavior data acquisition and recognition system and method based on UWB and LoRa. The system comprises an inertial data acquisition module, a motion estimation module and a motion estimation module, wherein the inertial data acquisition module is used for sensing the motion data of a user; the physical sign data acquisition module is used for sensing physical sign data of a user; the intelligent sensor scheduling system module is used for acquiring and processing user motion data and sign data at regular time and sending the data to the data transmission base station module in a UWB or LoRa communication mode in a self-adaptive manner; the data transmission base station module is used for forwarding the received data to the server-side processing program module; and the server-side processing program module is used for resolving the data sent by the data transmission base station, storing the resolved data, identifying the human behavior by using the resolved data and the human behavior identification model, and outputting the user position information and the behavior category information together if the resolved data contains positioning information.

Description

Self-adaptive human behavior data acquisition and identification system and method based on UWB and LoRa
Technical Field
The invention belongs to the technical field of positioning and the field of pattern recognition, and particularly relates to a self-adaptive human behavior data acquisition and recognition system and method based on UWB and LoRa.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The human body behavior recognition system based on the sensors is a system which collects behavior information through various sensors and realizes behavior recognition through a reasonable classification model in the process of carrying out various behaviors on a human body. With the development and maturity of communication technologies such as 5G, WiFi, artificial intelligence technologies such as machine learning and deep learning, and indoor positioning technologies based on Ultra Wide Band (UWB), behavior recognition combined with location information will become a major research direction.
In the process of acquiring human behavior and physical sign information, a transmission means is the most important. Currently, commonly used transmission means include bluetooth, WiFi, 4G, and the like. Although some of these transmission means can provide position information, the inventors found that in some environments, especially in indoor environments, high-precision position information cannot be provided, and accurate recognition of human behavior cannot be achieved.
Disclosure of Invention
In order to solve at least one technical problem in the background art, the invention provides a self-adaptive human behavior data acquisition and identification system and method based on UWB and LoRa, which can adaptively switch transmission modes according to different requirements of data transmission and indoor and outdoor positioning in the human information acquisition process, and improve the human behavior data acquisition and identification efficiency.
In order to achieve the purpose, the invention adopts the following technical scheme:
a first aspect of the invention provides an adaptive human behavior data acquisition and identification system based on UWB and LoRa.
An adaptive human behavior data acquisition and identification system based on UWB and LoRa, comprising:
the inertial data acquisition module is used for sensing user motion data;
the physical sign data acquisition module is used for sensing physical sign data of a user;
the intelligent sensor scheduling system module is used for acquiring and processing user motion data and sign data at regular time and sending the data to the data transmission base station module in a UWB or LoRa communication mode in a self-adaptive manner;
the data transmission base station module is used for forwarding the received data to the server-side processing program module;
and the server-side processing program module is used for resolving the data sent by the data transmission base station, storing the resolved data, identifying the human behavior by using the resolved data and the human behavior identification model, and outputting the user position information and the behavior category information together if the resolved data contains positioning information.
As an implementation mode, the intelligent sensor scheduling system module comprises a sensor data cache scheduling submodule, a data frame format processing submodule and an adaptive data transceiving submodule;
the self-adaptive data transceiver module is used for sensing the network state; if both UWB and LoRa networks are present, then UWB networks are preferred;
the intelligent sensor scheduling system module comprises a sensor data caching scheduling submodule and a data caching module, wherein the sensor data caching scheduling submodule is used for packaging user motion data and sign data which are acquired at regular time into a UWB or LoRa data frame format according to the network state and caching the data into a corresponding first-in first-out queue;
the data frame format processing submodule is used for analyzing the UWB or LoRa data frame format;
and the self-adaptive data transceiving submodule is used for sending the analyzed data frame to the data transmission base station module based on the network state.
As an implementation manner, the adaptive data transceiving submodule includes a UWB data transceiving unit and a LoRa data transceiving unit, and a process of the adaptive data transceiving submodule sensing a network state is as follows:
firstly, a UWB data transceiver unit is used for sending a detection packet to the outside, when the UWB host station is in a UWB network, the UWB host station replies a confirmation mark, when the confirmation mark is not received, the LoRa data transceiver unit is used for sending a detection packet to the outside, and if the UWB host station is in a LoRa network, the LoRa base station replies a confirmation mark.
In one embodiment, the UWB data frame format is 32 bytes of data; the first byte represents the data frame type, and the total of the two states comprises positioning data or no positioning data; the second byte is the base station type; the third and fourth bytes are user label ID bits; the fifth byte represents the data frame number; the sixth byte is a data number; the seventh byte is a command type; the eighth byte is selected as a positioning mode; the ninth and the sixteenth bytes are 0 if the two-dimensional positioning is performed, the data representing the third slave base station is 0, only two slave base stations are valid, the seventeenth to the twenty eighth bytes are inertial data, the twenty ninth byte is a heart rate value, the thirty th byte is a blood oxygen concentration value, the thirty eleventh byte is a body surface temperature value, and the thirty second byte is a CRC8 check value.
In one embodiment, the LoRa data frame format is 190 bytes, the first byte represents a data frame type, the second byte represents a data length bit, the third and fourth bytes represent a user tag ID, the fifth and sixth bytes represent a data number, the seventh to the eighty-th bytes represent 15 times of inertial data, the one hundred eighty-seven byte represents a heart rate value, the one hundred eighty-eight byte represents a blood oxygen concentration value, the one hundred eighty-nine byte represents a body surface temperature value, and the one hundred ninety byte represents a CRC8 check value.
As an implementation manner, the data transmission base station module includes a UWB data transmission base station sub-module and a LoRa data transmission base station sub-module, the UWB data transmission base station sub-module includes a UWB transceiving unit and a first ethernet data transceiving unit, and the LoRa data transmission base station sub-module includes a LoRa transceiving unit and a second ethernet data transceiving unit.
As an implementation mode, the UWB data transmission base station sub-module comprises a UWB positioning master base station and three UWB positioning slave base stations, the UWB positioning master base station is responsible for ranging with the intelligent sensor scheduling system module, ranging with the UWB positioning slave base stations, integrating data and sending the data to the server processing program module through the ethernet data transceiver module, and the UWB positioning slave base station is responsible for measuring the distance with the intelligent sensor scheduling system module.
As an embodiment, in the server-side processing program module, if the resolved data includes positioning information, the process of resolving the positioning information is as follows: and the hardware calculates the position information and directly obtains the distance between the user tag and the UWB host station and the distance between the user tag and the UWB slave base station.
As an embodiment, in the server-side processing program module, if the resolved data includes positioning information, the process of resolving the positioning information is as follows: and the software calculates the position information, and calculates the coordinates of the user according to the two-way ranging positioning algorithm through the original data.
The invention provides a working method of an adaptive human body behavior data acquisition and identification system based on UWB and LoRa.
A working method of a self-adaptive human body behavior data acquisition and recognition system based on UWB and LoRa comprises the following steps:
step S01: sensing user information;
step S02: sensing a network state; automatically selecting the UWB transmission mode according to the received confirmation flag to proceed to step S03, or the LoRa transmission mode to proceed to step S04;
step S03: encapsulating data according to the UWB data frame format, sending the encapsulated data to a UWB base station along with a UWB data packet, and entering step S05;
step S04: packaging data according to the LoRa data frame format, sending the data to the LoRa base station at one time, and entering step S06;
step S05: analyzing and buffering the UWB data frame, and proceeding to step S07;
step S06: analyzing and buffering the LoRa data frame, and entering the step S09;
step S07: judging whether the analyzed UWB data packet contains positioning information, and if so, entering step S08;
step S08: returning the data including the positioning information, and proceeding to step S09;
step S09: transmitting data through Ethernet;
step S10: receiving network data;
step S11: determining whether the received data includes positioning information, and if the received data includes positioning data transmitted by the UWB base station, entering step S12; if the location data is transmitted from the LoRa base station, the process goes to step S13, if the location data is not included;
step S12: if the hardware resolves the position information, directly obtaining the distance between the user tag and the UWB host station and the distance between the user tag and the UWB slave base station; if the software calculates the position information, calculating the coordinate of the user according to a TWR positioning algorithm through the original data;
step S13: analyzing data frame data;
step S14: storing the data in a database;
step S15: data standardization;
step S16: data segmentation;
step S17: recognizing human body behaviors; reading the data segmented in the step S16 into the trained CNN network to obtain the current user behavior;
step S18: behavior/location information display; the user position information obtained in step S12 and the user behavior obtained in step S17 are displayed on the same interface.
Compared with the prior art, the invention has the beneficial effects that:
(1) the practicability is as follows: the human behavior recognition system has higher requirements on the size and power consumption of information acquisition equipment, the precision of a sensor and the like, the selected LoRa module and the UWB module have small volume and low power consumption, and particularly, the LoRa module has longer transmission distance and can be used in indoor positioning scenes and outdoor human behavior recognition scenes. The transmission base station uses an Ethernet module, can integrate active Ethernet (POE), and has the advantages of convenient Power supply and easy deployment.
(2) Self-adaptability: the transmission mode can be adaptively switched according to different network environments. If the UWB positioning data frame is covered by the UWB base station, the UWB positioning data frame is received and sent; if the coverage of the LoRa base station is achieved, the LoRa data frame is transmitted and received, and the UWB network is preferably used to add the position information.
(3) High reliability: the data serial number is added into the behavior data in the transmission process, so that the data can be more efficiently associated, and a high-reliability data source is identified for the subsequent behavior; the travel type can be judged more accurately by identifying the human behavior based on the human behavior identification model.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a schematic diagram of a main module structure frame and a connection relationship of an adaptive human behavior data acquisition and recognition system based on UWB and LoRa according to an embodiment of the present invention.
Fig. 2 is a schematic workflow diagram of an adaptive human behavior data acquisition and identification system based on UWB and LoRa according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of network probing and network selection based on LoRa and UWB according to an embodiment of the present invention.
Fig. 4 is a schematic diagram illustrating a frame format of a UWB-based data frame according to an embodiment of the present invention.
Fig. 5 is a schematic diagram illustrating a frame format of a data frame based on LoRa according to an embodiment of the present invention.
Fig. 6 is a schematic diagram of a communication flow between a device a and a device B based on the TWR positioning algorithm according to an embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the self-adaptive human behavior data acquisition and identification system based on UWB and LoRa of the present embodiment includes an inertial data acquisition module, a physical sign data acquisition module, an intelligent sensor scheduling system module, a data transmission base station module, and a server-side processing program module.
In a specific implementation, the inertial data acquisition module is used for sensing user motion data; the user motion data is inertial data including, but not limited to, three-axis acceleration data and three-axis angular velocity data.
Specifically, the inertial data acquisition module comprises an acceleration data acquisition unit and an angular velocity data acquisition unit, wherein the acceleration data acquisition unit is used for acquiring triaxial acceleration data, and the angular velocity data acquisition unit is used for acquiring triaxial angular velocity data.
In specific implementation, the sign data acquisition module is used for sensing sign data of a user; the vital sign data includes, but is not limited to, heart rate data, blood oxygen concentration data, and body surface temperature data.
Specifically, sign data acquisition module includes heart rate data acquisition unit, blood oxygen concentration data acquisition unit and body surface temperature data acquisition unit, and heart rate data acquisition unit is used for gathering heart rate value data, and blood oxygen concentration data acquisition unit is used for gathering blood oxygen concentration value data, and body surface temperature data acquisition unit is used for gathering body surface temperature data.
In specific implementation, the intelligent sensor scheduling system module is used for acquiring and processing user motion data and physical sign data at regular time, and sending the data to the data transmission base station module in a UWB or LoRa communication mode in a self-adaptive manner.
Specifically, the intelligent sensor scheduling system module is configured to: the data collected by the inertial data collection module and the physical sign data collection module are read regularly, and the heart rate value and the blood oxygen concentration value are calculated according to the data; the UWB data receiving and sending unit and the LoRa data receiving and sending unit are used for sending detection packets to the outside to detect the current network environment; formatting the read inertial data and the physical sign information into fixed frame format data according to the current network environment; and sending the formatted data to a data transmission base station module according to the current network environment.
As a specific implementation manner, the intelligent sensor scheduling system module comprises a sensor data cache scheduling submodule, a data frame format processing submodule and an adaptive data transceiving submodule;
the self-adaptive data transceiver module is used for sensing the network state; if both UWB and LoRa networks are present, then UWB networks are preferred;
the intelligent sensor scheduling system module comprises a sensor data caching scheduling submodule and a data caching module, wherein the sensor data caching scheduling submodule is used for packaging user motion data and sign data which are acquired at regular time into a UWB or LoRa data frame format according to the network state and caching the data into a corresponding first-in first-out queue;
the data frame format processing submodule is used for analyzing the UWB or LoRa data frame format;
and the self-adaptive data transceiving submodule is used for sending the analyzed data frame to the data transmission base station module based on the network state. Specifically, the data frame format processing module includes a UWB data frame format parsing unit and a LoRa data frame format parsing unit.
In specific implementation, the sensor data timing acquisition submodule includes an inertial sensor buffer unit and a physical sign data buffer unit, which are First-in First-out (FIFO) queues with fixed sizes, and are used for buffering inertial data and physical sign data.
In this embodiment, the adaptive data transceiving submodule includes a UWB data transceiving unit and an LoRa data transceiving unit, and the process of the adaptive data transceiving submodule sensing the network state is as follows:
firstly, a UWB data transceiver unit is used for sending a detection packet to the outside, when the UWB host station is in a UWB network, the UWB host station replies a confirmation mark, when the confirmation mark is not received, the LoRa data transceiver unit is used for sending a detection packet to the outside, and if the UWB host station is in a LoRa network, the LoRa base station replies a confirmation mark. Based on the received acknowledgement flag, either the UWB transmission mode or the LoRa transmission mode is automatically selected.
In one embodiment, the format of the UWB data frame is 32 bytes of data, the data frame is defined as shown in FIG. 4, the first byte represents the data frame type, and the two states, including or not including the positioning data, are defined as 0xA1 and 0xA2, respectively, and the upper four bits are designated as A to represent the UWB mode. The second byte is the base station type, the master station is defined as 0xFF, and the slave station is defined as 0 xFE. The third and fourth bytes are user label ID bits, and the total capacity is 65535. The fifth byte represents the data frame number and represents the number of data returned in TWR positioning mode. The sixth byte is a data number, and when data are continuously transmitted, the data numbers are accumulated once in order to ensure data continuity, so that the server side can conveniently confirm data continuity. The seventh byte is a command type that is used to specify the command type when returning data in TWR positioning mode. The eighth byte is selected as a positioning mode and comprises one-dimensional positioning, two-dimensional positioning and three-dimensional positioning, the ninth and the cross sections are distances from the UWB base station during the one-dimensional positioning, the eleventh to the sixteenth bytes represent the distances from the three slave base stations during the three-dimensional positioning, if the two-dimensional positioning is adopted, the fifteenth and the sixteenth bits are 0, the data representing the third slave base station is 0, and only two slave base stations are effective. The seventeenth to twenty-eighth bytes are inertial data, the twenty-ninth byte is a heart rate value, the thirty-third byte is a blood oxygen concentration value, the thirty-third byte is a body surface temperature value, and the thirty-second byte is a CRC8 check value.
And the inertia data and the physical sign data are packaged into a UWB data frame format and are sent to a UWB base station along with a UWB data packet.
The LoRa data frame definition is shown in fig. 5: the total length is 190 bytes, the first byte table data frame type, defined as 0xB0, the upper four bits B representing LoRa mode. The second byte is a data length bit representing the length of the packet of data, the third and fourth bytes represent the user tag ID, the fifth and sixth bytes represent the data number, and the seventh to the one hundred eighty-sixth bytes represent the inertia data of 15 times. The one hundred eighty seven bytes are heart rate values, the one hundred eighty eight bytes are blood oxygen concentration values, the one hundred eighty nine bytes are body surface temperature values, and the one hundred ninety bytes are CRC8 check values.
Because the network delay of the LoRa network is large, the LoRa network is not suitable for sending data for multiple times, and under the LoRa network, the user tag caches the inertial data 15 times each time and sends the inertial data to the LoRa base station at one time.
In this embodiment, the inertial data collection module, the physical sign data collection module, and the intelligent sensor scheduling system module are collectively referred to as a user tag.
As shown in fig. 3, the specific workflow of the user tag is as follows:
firstly, a user tag independently opens a thread for regularly acquiring information acquired by an inertial sensor and a physical sign sensor and storing the information into a preset FIFO.
Secondly, the user tag detects whether a detection packet needs to be sent or not in the current environment to detect the network environment. The user tag sends a UWB detection packet and waits for receiving a confirmation signal, if the UWB detection packet is confirmed, the UWB detection packet is currently in a UWB network, if the confirmation fails, the user tag sends a LoRa detection packet to the environment through the LoRa and waits for receiving the confirmation signal, if the UWB detection packet is confirmed, the LoRa detection packet is currently in the LoRa network, and if the confirmation fails, the UWB detection packet is currently not in the UWB network.
Under the UWB network mode, the user tag reads inertial data and physical sign data from the FIFO, packs the data according to UWB data frames, and transmits the data through the UWB module. User-defined timeout TtIf T istIf the confirmation signal sent by the UWB base station is not received within a second (for example, 10 seconds), the UWB connection is disconnected, and the user tag will re-detect the network.
Under the loRa network mode, the user tag reads inertial data and sign data from FIFO to according to loRa data frame with data packing, then go out data transmission through the loRa module. If T is specifiedtIf the confirmation signal sent by the UWB base station is not received within (for example, 10 seconds), the UWB connection is disconnected, and the user tag will detect the network again.
In a specific implementation, the data transfer base station module is configured to forward the received data to the server-side processing program module.
The data transmission base station module is divided into a UWB data transmission base station submodule and a LoRa data transmission base station submodule.
The UWB data transmission base station submodule is used for: and receiving data sent by the user tag in the UWB network, positioning the user tag by the assistance of the UWB from the base station, and finally sending the behavior identification data and the position information data together through the Ethernet.
The LoRa data transmission base station submodule is used for: and receiving data sent by the user tag in the LoRa network and forwarding the data through the Ethernet module.
As a specific implementation manner, the UWB data transmission base station sub-module comprises a UWB positioning master base station and three UWB positioning slave base stations, the UWB positioning master base station is responsible for ranging with the intelligent sensor scheduling system module, ranging with the UWB positioning slave base stations, integrating data, and sending the data to the server processing program module through the ethernet data transceiver module, and the UWB positioning slave base station is responsible for measuring the distance with the intelligent sensor scheduling system module.
In specific implementation, the server-side processing program module is used for resolving data sent by the data transmission base station, storing the resolved data, performing human behavior recognition by using the resolved data and the human behavior recognition model, and outputting the user position information and the behavior type information together if the resolved data contains positioning information.
Specifically, if the positioning data is contained, if the hardware resolves the position information, the distance between the user tag and the UWB master station and the distance between the user tag and the UWB slave station are directly obtained. If the software calculates the position information, the coordinates of the user are calculated according to a Two Way Ranging (TWR) positioning algorithm through the original data.
The TWR positioning algorithm, as shown in fig. 6, specifically includes the following steps:
(1) since both the user tag and the base station are likely to be the initiating end in the positioning process, the tag and the base station are not distinguished, and are represented by a device a and a device B, and the UWB data frame includes: 1. positioning data, 2, inertial data, 3, physical sign data.
(2) The device A initiates the exchange, sends a fixed-length positioning data frame, for example, 32 bytes, to the device B, and accurately records the sending timestamp information according to the local clock after the sending is completed;
(3) and the device B responds to the exchange, and accurately records the receiving timestamp information according to the local clock after receiving the positioning data frame sent by the device A.
(4) And after the device B receives the positioning data frame of the device A, delaying for a fixed time, and analyzing the positioning data frame data in the delaying process.
(5) Device B sends back a positioning data frame to device a. The difference between the time when the device B sends back the positioning data frame and the time when the device A receives the positioning data frame is Treply1，
(6) DeviceAnd A receives the positioning data frame sent back by the device B and records the receiving time. The difference between the time when the device A receives the data frame of the device B and the time when the device A sends the signal is Tround1。
(7) After the device A receives the positioning data frame of the device B, the fixed time is delayed, and the positioning data frame data is analyzed in the delay process.
(8) Device a sends back a positioning data frame to device B. The difference between the time when the device A sends back the positioning data frame and the time when the device B receives the positioning data frame is Treply2，
(9) And the device B receives the positioning data frame sent back by the device A and records the receiving time. The time difference between the time when the device B receives the positioning data frame of the device A and the time when the device B sends the signal is Tround2. The time of flight of the signal between device a and device B is then:
Figure BDA0002874272600000131
distance between device a and device B:
d＝Tprop×c (2)
where c is the speed of light.
In specific implementation, the server-side processing program module comprises a data receiving and caching sub-module, a positioning data frame analyzing and calculating sub-module, a data frame calculating sub-module, a human behavior identification information processing sub-module and a behavior/position information display sub-module.
The data receiving and caching submodule caches data received from the Ethernet into the memory. And the positioning data frame analyzing and calculating submodule reads data from the received data caching submodule and calculates the position information according to a positioning algorithm. The human behavior information processing submodule applies a deep learning algorithm, inputs inertial data and physiological data into a trained network architecture model (behavior recognition model), and realizes behavior recognition through the network architecture model. The behavior/position information display submodule is used for displaying all information of the user, including position map information, current behavior type information and user basic information.
In a specific implementation, the behavior recognition model of the embodiment, that is, the network architecture includes a convolutional layer, a pooling layer, a full-link layer, and an output layer;
the main function of a Convolution Layer (CL) is to extract a feature map of input data by means of a plurality of Convolution kernels. The specific operation is as follows:
(1) each filter is locally connected with the characteristic diagram of the previous layer, and the corresponding connection weight is weighted and summed with local input;
(2) a bias term is added and then a nonlinear activation function is applied to the output of the filter.
The calculation mode of the convolution unit is as follows:
Figure BDA0002874272600000141
where u (-) is the output of the feature map of the previous layer at the specified position, x and y are the abscissa and the ordinate of the current input point, f is a non-Linear activation function, typically a Sigmoid function or a Linear rectification function (ReLU); b represents a bias term; w is anmRepresents the weight of the convolution kernel at the (n, m) position; n and M are the length and width of the convolution kernel, respectively.
The Pooling Layer (PL) is another important component of the convolutional neural network, and its principle is to simulate the human visual system and perform dimensionality reduction and abstraction on the input data. Pooling layers are typically inserted between convolutional layers of the CNN to reduce the size of each input feature map. The main functions of the pooling layer are three points: keeping the features undeformed, reducing the amount of data, and preventing overfitting to some extent.
A Full Connected Layer (FCL) follows the convolutional and pooling layers, and maps the hidden features resulting from the convolution and pooling to the label space of the sample by connecting to each neuron in the Layer preceding it. The output of the full connection layer is connected with the classifier.
The Output Layer (OL) is typically a Softmax classifier, by which the probability that the current sample is of each class can be calculated, and the predicted class is finally Output.
In the process of behavior identification, analyzing according to the data frame received by the Ethernet, and mainly analyzing the triaxial acceleration, the triaxial angular velocity, the heart rate value, the blood oxygen concentration value and the body surface temperature value. If the information center contains position information, x-axis, y-axis and z-axis coordinates of the sitting position are analyzed. And storing all analyzed data into different data tables according to the data types.
The Min-Max standardization method scales all data to [0,1] by linear transformation of the analyzed original data without changing the distribution of the data]In the meantime. Let the input sequence be x '═ x'1,x'2,...,x'i,...,x'n]TThe output sequence after normalization is y '═ y'1,y'2,...,y'i,...,y'n]TThe processing procedure is shown in the following formula:
Figure BDA0002874272600000151
wherein, x'maxAnd x'minRespectively the maximum and minimum of all samples in the input sequence x'.
It should be noted that, in other embodiments, other existing packet normalization methods may be used to normalize the parsed raw data.
The data standardization zooms the sensor data of different dimensions and different dimension units to the same magnitude, so that the identification accuracy can be effectively improved.
Since the sensor data for behavior recognition is a continuous signal based on time periods, the behavior data is stored in the form of discrete points, and each behavior usually takes a certain time to complete, generally several seconds to several minutes. In order to facilitate subsequent classification identification, a sliding window is adopted to segment the data. And finally, training and testing the segmented data set through CNN to obtain a trained network for human behavior recognition.
It should be noted here that in other embodiments, the behavior recognition model may also be implemented by using a Support Vector Machine (SVM), a Long Short-Term Memory network (LSTM), and the like.
The embodiment provides a relatively optimized system in four aspects of transmission technology, positioning technology, information processing and behavior recognition, innovatively combines the indoor positioning technology and the human behavior recognition technology and can adaptively switch the transmission mode, so that the system is suitable for indoor and outdoor multi-scenes.
The working principle of the self-adaptive human behavior data acquisition and identification system based on UWB and LoRa of the embodiment is as follows:
sensing user motion data and user sign data;
sensing a network state;
packaging user motion data and user physical sign data into a UWB or LoRa data frame format;
analyzing and buffering the data frame in the UWB or LoRa data frame format; judging whether the analyzed data contains positioning information or not for the UWB data frame format;
transmitting the parsed data based on the corresponding network state;
resolving and storing the resolved data, recognizing the human behavior by using the resolved data and the human behavior recognition model, and outputting the user position information and the behavior category information together if the resolved data contains positioning information.
Specifically, as shown in fig. 2, the working method of the UWB and LoRa based adaptive human behavior data acquisition and behavior recognition system includes the following specific steps:
step S01: perceiving user information
According to the minimum requirement of the human behavior recognition network on the original data, the sensor is specified to output the acquired information at a fixed time, and the mainly acquired information comprises three-axis acceleration information, three-axis angular velocity information, heart rate information, blood oxygen concentration information and body surface temperature information.
Step S02: sensing network state
The module for acquiring the inertial data and the physical sign data of the user is defined as a user tag, the user tag has three functions, the first function is to acquire the inertial data and the physical sign data of the user, the microcontroller is provided with a timer to acquire the inertial data and the heart rate data at regular time, and the acquired information is sequentially stored in the FIFO queue according to the serial number; the second function is to carry out distance measurement according to positioning data sent by a UWB base station; the third function is to sense the current network state.
In idle condition, the user tag sends a detection packet to outside by using UWB data transceiver unit, and when in UWB network, UWB host station will reply a confirmation mark. When the user tag does not receive the confirmation mark, the LoRa data transceiver unit is used for sending a detection packet to the outside, and if the user tag is in the LoRa network, the LoRa base station replies a confirmation mark. According to the received confirmation flag, the UWB transmission mode is automatically selected to proceed to step S03, or the LoRa transmission mode proceeds to step S04.
Step S03: encapsulating data according to UWB data frame format
The format of the UWB data frame is 32 bytes of data, and the definition of the data frame is shown in FIG. 4. And packaging the inertia data and the physical sign data into a UWB data frame format, sending the UWB data frame format to a UWB base station along with a UWB data packet, and proceeding to step S05.
Step S04: encapsulating data according to LoRa data frame format
The LoRa data frame definition is shown in fig. 5: the total length is 190 bytes. Because the network delay of the LoRa network is large and is not suitable for sending data for multiple times, in the LoRa network, the user tag caches the inertial data 15 times at a time, and sends the inertial data to the LoRa base station at one time, and the process proceeds to step S06.
Step S05: parsing and buffering UWB data frames
After receiving the data frame, the UWB base station parses the inertial data and the physical sign data in the data frame, caches the inertial data and the physical sign data in the memory according to a certain format, and then proceeds to step S07.
Step S06: parsing and buffering LoRa data frames
For design convenience, after receiving the data, the LoRa base station also parses and buffers the data according to the buffer format of the UWB base station, and then the process proceeds to step S09.
Step S07: judging whether the positioning information is contained
The UWB packet may include not only inertial data and physical sign data but also positioning data, and the UWB base station determines the UWB packet according to the type of the seventh byte in step S03, returns data to the user tag when the positioning data is included, and proceeds to step S08.
Step S08: returning data containing positioning information
In the TWR positioning mode, the positioning method is bidirectional data transmission, so that after the UWB base station resolves the positioning command, the UWB base station returns data including positioning information to the user tag, and the process proceeds to step S09.
Step S09: ethernet transmission data
For convenient deployment, the data transmission from the base station to the server side is ethernet data transmission. The UWB base station and the LoRa base station are integrated with an Ethernet transmission module, when the base station caches data to a certain amount, the data is sent to the server end through the Ethernet transmission module at one time, and when the data is transmitted through the Ethernet, a TCP (transmission control protocol) protocol or a UDP (user datagram protocol) protocol can be selected to adapt to different scenes.
Step S10: receiving network data
And the server side receives the data transmitted in the step S09 through the Socket monitoring port, and then caches the behavior data and the positioning data in the memory respectively.
Step S11: judging whether the data contains positioning information
If the received data is transmitted from the UWB base station, the received data includes positioning data, and the process proceeds to step S12. If the location data is transmitted from the LoRa base station, the process proceeds to step S13 without including the location data.
Step S12: if the positioning data is contained, if the hardware is used for resolving the position information, the distance between the user tag and the UWB host station and the distance between the user tag and the UWB slave base station are directly obtained. If the software calculates the position information, the coordinates of the user are calculated according to the TWR positioning algorithm through the original data.
Step S13: parsing data frame data
And analyzing according to the data frame received by the Ethernet, wherein the analysis is mainly to analyze the triaxial acceleration, the triaxial angular velocity, the heart rate value, the blood oxygen concentration value and the body surface temperature value. If the information center contains position information, x-axis, y-axis and z-axis coordinates of the sitting position are analyzed.
Step S14: saving data to a database
All the data analyzed in the storing step S13 are stored in different data tables according to the data type.
Step S15: data normalization
In this embodiment, the Min-Max normalization method is adopted to scale all data between [0,1] without changing the distribution of the data by linear transformation of the analyzed original data.
It should be noted that, in other embodiments, other existing packet normalization methods may be used to normalize the parsed raw data.
The data standardization zooms the sensor data of different dimensions and different dimension units to the same magnitude, so that the identification accuracy can be effectively improved.
Step S16: data partitioning
Since the sensor data for behavior recognition is a continuous signal based on time periods, the behavior data is stored in the form of discrete points, and each behavior usually takes a certain time to complete, generally several seconds to several minutes. In order to facilitate subsequent classification identification, a sliding window is adopted to segment the data.
Step S17: human behavior recognition
And training and testing the segmented data set through the CNN to obtain a trained network for human behavior recognition. And reading the data segmented in the step S16 into the trained CNN network to obtain the current user behavior.
Step S18: behavior/location information display
And displaying the user position information obtained in the step S12 and the user behavior obtained in the step S17 on the same interface, wherein the interface comprises characteristics such as user information, label information, user current position information and user current behavior state.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. 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 (10)

1. The utility model provides an adaptive human behavior data acquisition and identification system based on UWB and loRa which characterized in that includes:
the inertial data acquisition module is used for sensing user motion data;
the physical sign data acquisition module is used for sensing physical sign data of a user;
the intelligent sensor scheduling system module is used for acquiring and processing user motion data and sign data at regular time and sending the data to the data transmission base station module in a UWB or LoRa communication mode in a self-adaptive manner;
the data transmission base station module is used for forwarding the received data to the server-side processing program module;
and the server-side processing program module is used for resolving the data sent by the data transmission base station, storing the resolved data, identifying the human behavior by using the resolved data and the human behavior identification model, and outputting the user position information and the behavior category information together if the resolved data contains positioning information.
2. The UWB and LoRa-based adaptive human behavior data acquisition and identification system according to claim 1, wherein the intelligent sensor scheduling system module comprises a sensor data cache scheduling submodule, a data frame format processing submodule and an adaptive data transceiver submodule;
the self-adaptive data transceiver module is used for sensing the network state; if both UWB and LoRa networks are present, then UWB networks are preferred;
the intelligent sensor scheduling system module comprises a sensor data caching scheduling submodule and a data caching module, wherein the sensor data caching scheduling submodule is used for packaging user motion data and sign data which are acquired at regular time into a UWB or LoRa data frame format according to the network state and caching the data into a corresponding first-in first-out queue;
the data frame format processing submodule is used for analyzing the UWB or LoRa data frame format;
and the self-adaptive data transceiving submodule is used for sending the analyzed data frame to the data transmission base station module based on the network state.
3. The UWB and LoRa-based adaptive human behavior data acquisition and recognition system according to claim 2, wherein the adaptive data transceiver sub-module comprises a UWB data transceiver unit and an LoRa data transceiver unit, and the process of sensing the network state by the adaptive data transceiver sub-module is as follows:
firstly, a UWB data transceiver unit is used for sending a detection packet to the outside, when the UWB host station is in a UWB network, the UWB host station replies a confirmation mark, when the confirmation mark is not received, the LoRa data transceiver unit is used for sending a detection packet to the outside, and if the UWB host station is in a LoRa network, the LoRa base station replies a confirmation mark.
4. The UWB and LoRa-based adaptive human behavior data acquisition and identification system of claim 2 wherein the UWB data frame format is 32 bytes of data; the first byte represents the data frame type, and the total of the two states comprises positioning data or no positioning data; the second byte is the base station type; the third and fourth bytes are user label ID bits; the fifth byte represents the data frame number; the sixth byte is a data number; the seventh byte is a command type; the eighth byte is selected as a positioning mode; the ninth and the sixteenth bytes are 0 if the two-dimensional positioning is performed, the data representing the third slave base station is 0, only two slave base stations are valid, the seventeenth to the twenty eighth bytes are inertial data, the twenty ninth byte is a heart rate value, the thirty th byte is a blood oxygen concentration value, the thirty eleventh byte is a body surface temperature value, and the thirty second byte is a CRC8 check value.
5. The UWB and LoRa-based adaptive human behavior data acquisition and identification system of claim 2, wherein the LoRa data frame format is 190 bytes, the first byte represents a data frame type, the second byte is data length bits, the third and fourth bytes represent a user tag ID, the fifth and sixth bytes represent a data number, the seventh to the one hundred eighty six bytes represent inertial data for 15 times, the one hundred eighty seven byte is a heart rate value, the one hundred eighty eight byte is a blood oxygen concentration value, the one hundred eighty nine byte is a body surface temperature value, and the one hundred ninety byte is a CRC8 check value.
6. The UWB and LoRa-based adaptive human behavior data acquisition and recognition system according to claim 1, wherein the data transmission base station module comprises a UWB data transmission base station sub-module and a LoRa data transmission base station sub-module, the UWB data transmission base station sub-module comprises a UWB transceiving unit and a first ethernet data transceiving unit, and the LoRa data transmission base station sub-module comprises a LoRa transceiving unit and a second ethernet data transceiving unit.
7. The UWB and LoRa-based adaptive human behavior data acquisition and identification system according to claim 6, wherein the UWB data transmission base station sub-module comprises a UWB positioning master base station and three UWB positioning slave base stations, the UWB positioning master base station is responsible for ranging with the intelligent sensor scheduling system module, ranging with the UWB positioning slave base stations, integrating data and sending to the server-side processing program module through the Ethernet data transceiver module, and the UWB positioning slave base stations are responsible for measuring distances with the intelligent sensor scheduling system module.
8. The UWB and LoRa-based adaptive human behavior data acquisition and recognition system according to claim 1, wherein in the server-side processing program module, if the resolved data contains positioning information, the process of resolving the positioning information is: and the hardware calculates the position information and directly obtains the distance between the user tag and the UWB host station and the distance between the user tag and the UWB slave base station.
9. The UWB and LoRa-based adaptive human behavior data acquisition and recognition system according to claim 1, wherein in the server-side processing program module, if the resolved data contains positioning information, the process of resolving the positioning information is: and the software calculates the position information, and calculates the coordinates of the user according to the two-way ranging positioning algorithm through the original data.
10. An operating method of the UWB and LoRa based adaptive human behavior data acquisition and identification system according to any one of claims 1 to 9, comprising the steps of:
step S01: sensing user information;
step S02: sensing a network state; automatically selecting the UWB transmission mode according to the received confirmation flag to proceed to step S03, or the LoRa transmission mode to proceed to step S04;
step S03: encapsulating data according to the UWB data frame format, sending the encapsulated data to a UWB base station along with a UWB data packet, and entering step S05;
step S04: packaging data according to the LoRa data frame format, sending the data to the LoRa base station at one time, and entering step S06;
step S05: analyzing and buffering the UWB data frame, and proceeding to step S07;
step S06: analyzing and buffering the LoRa data frame, and entering the step S09;
step S07: judging whether the analyzed UWB data packet contains positioning information, and if so, entering step S08;
step S08: returning the data including the positioning information, and proceeding to step S09;
step S09: transmitting data through Ethernet;
step S10: receiving network data;
step S11: determining whether the received data includes positioning information, and if the received data includes positioning data transmitted by the UWB base station, entering step S12; if the location data is transmitted from the LoRa base station, the process goes to step S13, if the location data is not included;
step S12: if the hardware resolves the position information, directly obtaining the distance between the user tag and the UWB host station and the distance between the user tag and the UWB slave base station; if the software calculates the position information, calculating the coordinate of the user according to a TWR positioning algorithm through the original data;
step S13: analyzing data frame data;
step S14: storing the data in a database;
step S15: data standardization;
step S16: data segmentation;
step S17: recognizing human body behaviors; reading the data segmented in the step S16 into the trained CNN network to obtain the current user behavior;
step S18: behavior/location information display; the user position information obtained in step S12 and the user behavior obtained in step S17 are displayed on the same interface.
CN202011622869.1A 2020-12-30 2020-12-30 Self-adaptive human behavior data acquisition and identification system and method based on UWB and LoRa Active CN112770251B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011622869.1A CN112770251B (en) 2020-12-30 2020-12-30 Self-adaptive human behavior data acquisition and identification system and method based on UWB and LoRa

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011622869.1A CN112770251B (en) 2020-12-30 2020-12-30 Self-adaptive human behavior data acquisition and identification system and method based on UWB and LoRa

Publications (2)

Publication Number Publication Date
CN112770251A true CN112770251A (en) 2021-05-07
CN112770251B CN112770251B (en) 2022-04-29

Family

ID=75698630

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011622869.1A Active CN112770251B (en) 2020-12-30 2020-12-30 Self-adaptive human behavior data acquisition and identification system and method based on UWB and LoRa

Country Status (1)

Country Link
CN (1) CN112770251B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102256239A (en) * 2011-07-05 2011-11-23 华为终端有限公司 Multimode terminal and data processing method for multimode terminal
CN102772211A (en) * 2012-08-08 2012-11-14 中山大学 Human movement state detection system and detection method
CN103561480A (en) * 2013-10-21 2014-02-05 广东明创软件科技有限公司 Data transmission method
WO2017167306A1 (en) * 2016-04-01 2017-10-05 成都精位科技有限公司 Method of synchronizing signals in uwb high-precision positioning system, and system
CN107393283A (en) * 2017-08-31 2017-11-24 重庆市通信建设有限公司 A kind of data acquisition unit and data collecting system
CN108171278A (en) * 2018-01-25 2018-06-15 武汉中体智美科技有限公司 A kind of recognizing model of movement method and system based on training data
CN108462984A (en) * 2018-01-25 2018-08-28 青岛海信移动通信技术股份有限公司 A kind of method and terminal carrying out access network management
CN109951815A (en) * 2019-01-15 2019-06-28 杭州赛鲁班网络科技有限公司 A kind of indoor sport health data collection system and method
CN110794364A (en) * 2019-09-09 2020-02-14 河南工业大学 UWB indoor positioning method
WO2020212723A1 (en) * 2019-04-19 2020-10-22 Bespoon Sas Ultra-wideband indoor location system and method

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102256239A (en) * 2011-07-05 2011-11-23 华为终端有限公司 Multimode terminal and data processing method for multimode terminal
CN102772211A (en) * 2012-08-08 2012-11-14 中山大学 Human movement state detection system and detection method
CN103561480A (en) * 2013-10-21 2014-02-05 广东明创软件科技有限公司 Data transmission method
WO2017167306A1 (en) * 2016-04-01 2017-10-05 成都精位科技有限公司 Method of synchronizing signals in uwb high-precision positioning system, and system
CN107393283A (en) * 2017-08-31 2017-11-24 重庆市通信建设有限公司 A kind of data acquisition unit and data collecting system
CN108171278A (en) * 2018-01-25 2018-06-15 武汉中体智美科技有限公司 A kind of recognizing model of movement method and system based on training data
CN108462984A (en) * 2018-01-25 2018-08-28 青岛海信移动通信技术股份有限公司 A kind of method and terminal carrying out access network management
CN109951815A (en) * 2019-01-15 2019-06-28 杭州赛鲁班网络科技有限公司 A kind of indoor sport health data collection system and method
WO2020212723A1 (en) * 2019-04-19 2020-10-22 Bespoon Sas Ultra-wideband indoor location system and method
CN110794364A (en) * 2019-09-09 2020-02-14 河南工业大学 UWB indoor positioning method

Also Published As

Publication number Publication date
CN112770251B (en) 2022-04-29

Similar Documents

Publication Publication Date Title
WO2019136918A1 (en) Indoor positioning method, server and positioning system
Ghasemzadeh et al. Physical movement monitoring using body sensor networks: A phonological approach to construct spatial decision trees
CN105686833A (en) Wearable multinode three dimensional motion monitoring system based on wireless body area network
Chen et al. A support infrastructure for the smart kindergarten
Frank et al. Reliable real-time recognition of motion related human activities using MEMS inertial sensors
CN107343052A (en) The physical distribution monitoring system that a kind of WSN is combined with RFID
CN203039726U (en) Human body three-dimensional posture identifying system
WO2011033504A1 (en) Method to reduce database load in real time location systems
CN104467866A (en) Angle-based track data compression method and device
WO2013078735A1 (en) Spatial motion sensor
CN112770251B (en) Self-adaptive human behavior data acquisition and identification system and method based on UWB and LoRa
CN117055004A (en) Three-dimensional human skeleton estimation method based on millimeter wave radar sparse point cloud
Bastwesy et al. Deep learning sign language recognition system based on wi-fi csi
WO2023051390A1 (en) Trajectory estimation model training method, trajectory estimation method, and device
CN109766798A (en) Gesture data processing method, server and awareness apparatus based on experience small echo
CN109388669A (en) The acquisition of internet-of-things terminal motion state and analysis system and method
CN105517018B (en) A kind of method and device obtaining location information
CN111141284A (en) Intelligent building personnel thermal comfort level and thermal environment management system and method
CN113577651A (en) Motion state identification method for intelligent barbell
CN108827293B (en) Three-dimensional positioning system based on inertia measurement element
CN106595647B (en) Behavior state monitoring method, device and system
CN111039118A (en) UWB-based elevator operation monitoring method, medium, terminal and device
CN110236560A (en) Six axis attitude detecting methods of intelligent wearable device, system
CN113031761B (en) Multi-sensing data high-speed synchronous sampling method of data glove
CN206270980U (en) A kind of motion capture gloves for gesture identification

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