CN115460346A - Data acquisition device capable of automatically adjusting angle - Google Patents
Data acquisition device capable of automatically adjusting angle Download PDFInfo
- Publication number
- CN115460346A CN115460346A CN202210991818.9A CN202210991818A CN115460346A CN 115460346 A CN115460346 A CN 115460346A CN 202210991818 A CN202210991818 A CN 202210991818A CN 115460346 A CN115460346 A CN 115460346A
- Authority
- CN
- China
- Prior art keywords
- data
- angle
- steering engine
- rotating disc
- servo motor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012545 processing Methods 0.000 claims abstract description 52
- 230000001815 facial effect Effects 0.000 claims abstract description 50
- 230000007246 mechanism Effects 0.000 claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims description 39
- 238000000034 method Methods 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 17
- 238000007789 sealing Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000007619 statistical method Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000017525 heat dissipation Effects 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 2
- 238000002955 isolation Methods 0.000 claims description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000009987 spinning Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Life Sciences & Earth Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Control Of Position Or Direction (AREA)
Abstract
The invention discloses a data acquisition device capable of automatically adjusting an angle, which belongs to the technical field of intelligent office, and aims to solve the technical problems of realizing the automatic adjustment of a data acquisition device and an angle between an operator, improving the acquisition quality of facial image data and improving the operability and efficiency of data acquisition, wherein the technical scheme is as follows: the structure of the device comprises an equipment supporting structure, a rotating disc structure and a rotating base, wherein a rotating mechanism is arranged between the rotating base and the rotating disc structure; an angle adjusting mechanism is arranged between the rotating disc structure and the equipment supporting structure; the equipment supporting mechanism comprises a main body supporting frame, a rear cover is arranged on one side surface of the main body supporting frame, and a binocular camera, a fingerprint identifier, a bar code gun and a touch screen processing terminal are arranged on the other side surface of the main body supporting frame; the rotating mechanism comprises a steering engine and a steering engine seat, the base body end of the steering engine is installed on the steering engine seat, the steering engine seat is installed on the rotating base, and the output end of the steering engine is rotatably connected with the rotating disc structure.
Description
Technical Field
The invention relates to the technical field of intelligent office work, in particular to a data acquisition device capable of automatically adjusting an angle.
Background
With the development of automatic intelligent technology and the requirement of modern equipment, self-service terminals are more intelligent and popular. Self-service terminals have been widely used in intensive service industries such as hospital services and tax services. In self-service tax staff, the angle of a camera or the angle of operation of an operator when the face of a person collects information is difficult to be ideal due to the personal or office.
Therefore, how to realize the automatic adjustment of the data acquisition equipment and the angle between the data acquisition equipment and an operator, improve the acquisition quality of facial image data, and simultaneously improve the operability and efficiency of data acquisition is a technical problem to be solved urgently at present.
Disclosure of Invention
The technical task of the invention is to provide a data acquisition device capable of automatically adjusting the angle, so as to solve the problems of how to realize the automatic adjustment of the angle between the data acquisition device and an operator, improve the acquisition quality of facial image data, and improve the operability and efficiency of data acquisition.
The technical task of the invention is realized in the following way, the data acquisition device capable of automatically adjusting the angle comprises an equipment supporting structure, a rotating disc structure and a rotating base, wherein a rotating mechanism is arranged between the rotating base and the rotating disc structure, and the relative angle between the equipment supporting structure and an operator is controlled by controlling the relative angle between the rotating disc structure and the equipment supporting structure, so that the optimal proper angle between the equipment supporting structure and the operator is achieved, and the use by the operator is facilitated; an angle adjusting mechanism is arranged between the rotating disc structure and the equipment supporting structure;
the equipment supporting mechanism comprises a main body supporting frame, a rear cover is arranged on one side surface of the main body supporting frame, and a binocular camera, a fingerprint identifier, a bar code gun and a touch screen processing terminal are arranged on the other side surface of the main body supporting frame;
the rotating mechanism comprises a steering engine and a steering engine seat, the base body end of the steering engine is installed on the steering engine seat, the steering engine seat is installed on the rotating base, and the output end of the steering engine is rotatably connected with the rotating disc structure.
Preferably, the angle adjusting mechanism comprises a servo motor and an angle adjusting rotating shaft, the base body end of the servo motor is located on the rotating disc structure, the output end of the servo motor is rotatably connected with the angle adjusting rotating shaft, and the angle adjusting rotating shaft is hinged with the edge end of the main body supporting frame.
Preferably, a wiring groove is arranged at the joint of the main body support frame and the rear cover, and a plurality of heat dissipation holes are uniformly distributed on the rear cover;
the main body support frame is provided with the connecting block with the angle adjusting rotating shaft junction.
Preferably, the touch screen processing terminal is located at the middle position of the main body support frame, the binocular camera is located above the touch screen processing terminal, and the fingerprint identification instrument and the bar code gun are located below the touch screen processing terminal.
Preferably, the rotating base is provided with spherical bearings distributed circumferentially, and the spherical bearings are used for supporting the rotating disc structure, so that the friction force between the rotating base and the rotating disc structure is reduced while the rotating base is supported.
More preferably, the rotating disc structure includes rotating disc main part frame, is provided with shrouding on the disc on the rotating disc main part frame, and shrouding and rotating disc main part frame form the disc cavity on the disc, and servo motor is located one side department in the disc cavity, still is provided with control circuit board in the disc cavity, and control circuit board is used for controlling steering wheel and servo motor's rotation angle volume.
Preferably, the upper sealing plate of the disc is provided with a sliding rail which is in a ring shape, and the ring-shaped sliding rail is in sliding fit with the spherical bearing.
Preferably, the control circuit board is electrically connected with a host, and the host comprises a main control module, a graphic processing module and a local image processing module;
the master control module is used for issuing a facial image data acquisition instruction, acquiring facial images of an operator by the binocular camera after the instruction is issued, and uploading the data to a local database for storage; in the process of uploading the facial image data, the master control module has no right to interfere the uploading and storing actions of the binocular camera; after the data are uploaded, an independent local image processing module independently judges the image acquisition quality, and after judgment, the local image processing module sends an instruction and a main control module to determine whether to acquire the data again; after the acquisition is finished, the main control module stops the process of the acquisition process;
the image processing module is used for driving the binocular camera to collect facial image data of an operator, processing the collected data through self-contained images, determining fine adjustment amount of the binocular self-lens, and uploading the collected data to a database of the main control module; through the graphic processing of the main control module, the increment of the rotation angle of the steering engine and the servo motor is calculated, the optimal position and angle between the equipment carried by the equipment supporting structure and an operator are achieved by adjusting the angle of the steering engine and the angle of the motor, and meanwhile, the binocular camera is finely adjusted again, so that the facial data of the operator are ensured to be completely within the acquisition range;
the local image processing module is used for being activated when image data are uploaded at the binocular, performing tasks of image storage and image quality judgment, and sending a result instruction to the main control module after the tasks are judged; when the data acquisition is successful, the main control module sends age group data of a face image data owner to the local image processing module, the local image processing module is provided with an age group to store the face image data, and the isolation between the locally stored image data and a network is ensured so as to ensure the safety of the data; when reading data, a special communication network is needed for reading.
More preferably, the control quantity of the main machine comprises a rotation angle omega of the servo motor e And the rotation angle omega of the steering engine d Angle of rotation omega of servo motor e And the rotation angle omega of the steering engine d Controlled by a control circuit board, wherein the control circuit board stores the rotation angle omega of the servo motor e And the rotation angle omega of the steering engine d Initial angle ω of e0 And ω d0 After each startup, the control circuit board drives the servo motor and the steering engine to run to an initial angle, and waits for the instruction of the main control module after the initial angle is reached;
when the initial angle of the neural network is optimized, statistical analysis is carried out on data collected on the same day after work on the same day is completed; when statistical analysis is performed, the data processing process is specifically as follows:
s1, counting data omega of the day ei And omega di Wherein i =1,2, \8230, n;
s2, solving a data mean value, wherein the formula is as follows:
s3, solving the standard deviation of the data, wherein the formula is as follows:
s4, in order to judge whether the acquired data is data of ordinary people or not and reject some special data (for example, a person intentionally uses a limit position to acquire the data), data cleaning is required according to the variance: setting variance limit s based on usage statistics emm And s dm The method comprises the following steps:
when s is e And s d Are respectively less than s emm And s dm If so, the acquired data is considered as normal data, and the next calculation is carried out;
when s is e And s d One or both of the values of (a) is greater than s emm And s dm If so, cleaning the group of data larger than the set of data;
when s is e ＞s em Then from data ω ei Removing
Maximum data, and making variance s by newly calculating standard variance e ＜s em 。
When s is d ＞s dm Then from data ω di Removing
Maximum data, and making variance s by newly calculating standard variance d ＜s dm 。
S5, counting
And
performing network generalization of the neural network as an expected value of the neural network; and averaging the sampled data of the current day
The standard deviations se and sd (standard deviations of the cleaned data) are the difference values of the characteristic values as training input data, and the formula is as follows:
Δs e ＝s e -s e0 ；
Δs d ＝s d -s d0 ；
wherein the training input
Training input needs to be normalized by an extreme method before input;
training output
S6, the neural network adopts a small multilayer network topological structure: the neural network structure adopts a multi-input and dual-output structure (for example, a common BP neural network is adopted, the structure adopts a three-layer neural network and two data outputs of four input parameters) or adopts a self-coding model (Auto-Encoder) with the same output as the original input;
in the network design, the η learning rate is designed to adopt different stage values according to the change rate of each output error, and the specific steps are as follows:
when the temperature is higher than the set temperature
When in use
Wherein a, A and B are specific numerical values;
s7, after the network training is finished, the angle variation is obtained, and the method specifically comprises the following steps:
inputting an input quantity IN (0 0) into the network;
the output quantity OUT (Δ ω) e Δω d )；
S8, solving a new angle variable, wherein the formula is as follows:
ω e1 ＝ω e0 +Δω e ；
ω d1 ＝ω d0 +Δω d ；
s9, outputting a set value to a control circuit board: will omega e1 And ω d1 And writing the initial value into the circuit control board.
More preferably, the working process of the device is as follows:
(1) After the power is switched on, the circuit control board controls the steering engine and the servo motor to rotate to a set initial position; the binocular camera collects facial images of an operator, and after image processing, whether the collected facial images meet requirements is judged:
(1) if the collected facial image meets the requirements, uploading the data to a host independent database, and executing the step (4) in the next step;
(2) if the collected face image does not meet the requirement, executing the step (2);
(2) The relative position of binocular camera and operator is adjusted through the fine motion structure of binocular camera self, reacquires facial image again to again through judging whether the image of gathering requires:
(1) if the collected face image meets the requirements, uploading the data to a host independent database, and executing the step (4) in the next step;
(2) if the collected face image does not meet the requirement, executing the step (3);
(3) The host control module controls the control circuit board 5 to rotate the steering engine 6 and the servo motor 9, so that the relative position of the equipment supporting structure and the face of an operator is adjusted; after the adjustment is finished, the binocular camera acquires the facial image of the operator again, and judges whether the facial image meets the requirements again:
(1) if the collected face image meets the requirements, uploading the data to a host independent database, and executing the step (4) in the next step;
(2) if the facial image data do not meet the requirements, repeating the step (2) and the step (3) until the facial image data acquisition meets the requirements;
(4) After the binocular camera finishes the acquisition of the facial image, the equipment supporting structure and the rotating disc structure are in relatively ideal relative positions with an operator, so that the operator can conveniently perform the next operation; at the moment, the equipment supporting structure and the rotating disc structure lock the position of the equipment supporting structure and the rotating disc structure until an operator finishes all operations;
(5) After the operator finishes all operations, the main control module of the host sends an instruction to the control circuit board and the binocular camera, the control circuit board drives the steering engine and the servo motor to return to the initial position, the binocular camera returns to the initial position, and the equipment supporting structure and the rotating disc structure are adjusted to the original positions;
(6) After the acquisition task is completed, the control circuit board uploads the recorded locking angle value omega to a main control module of the host, the main control module of the host periodically counts the angle omega, extracts a characteristic value and uses the characteristic value as a neural network training target value, trains a neural network periodically, and predicts a value omega of the initial angle of the neural network angle to be a target value omega e0 And omega d0 The angle is used as the initial angle of a steering engine and a servo motor in the control circuit board;
(7) And the host periodically updates the initial angles of the steering engine and the servo motor in the control circuit board so as to improve the data acquisition efficiency.
The data acquisition device capable of automatically adjusting the angle has the following advantages:
the invention relates to a self-service terminal which judges the position of an operator through a binocular camera or other cameras, and further automatically adjusts the relative position of an operation platform and the operator and the relative angle between the camera and the face of the operator;
the invention solves the problem of angle adjustment between the data acquisition equipment and an operator through a three-degree-of-freedom automatic adjustment structure, and improves the quality of the acquired facial image data;
thirdly, the data acquisition and operation platforms are integrated into one platform, so that the data acquisition efficiency is improved, and the operability and the working comfort of the system are improved;
the simple neural network system is introduced into the host to adjust the initial angle of the data acquisition system, so that the data acquisition system can adapt to different areas, the adjustment time of the data acquisition system is shortened, and the efficiency is improved;
the invention introduces a simple neural network system so as to be capable of independently operating on a microcomputer or an industrial personal computer, thereby increasing the portability of the system;
the approximate position of an operator can be judged through the binocular camera, the optimal angle between the camera and the operator is achieved through rotation of various structures and micro-motion of the camera, and therefore comprehensive and high-definition facial graphic data of the operator are collected;
in the process of image acquisition, the invention achieves rapid positioning and rapid movement by changing the movement of three degrees of freedom of the equipment supporting structure and the rotating disc structure so as to rapidly capture the facial data of an operator, therefore, the invention has rapid correspondence;
the invention not only carries binocular camera and other equipment, but also simultaneously carries personal terminal for office operation, bar code gun for collecting bar code data, fingerprint instrument for collecting fingerprint and other equipment, has various data collecting functions, and is highly integrated equipment.
Therefore, the invention has the characteristics of reasonable design, simple structure, easy processing, small volume, convenient use, multiple purposes and the like, thereby having good popularization and use values.
Drawings
The invention is further described below with reference to the accompanying drawings.
FIG. 1 is a schematic perspective view of a data acquisition device with an automatic angle adjustment;
FIG. 2 is a schematic structural diagram of a data acquisition device capable of automatically adjusting an angle;
FIG. 3 is a schematic structural view of a rotating base;
FIG. 4 is a schematic perspective view of a rotary disk structure;
FIG. 5 is a schematic perspective view of another face of the rotating disk structure;
FIG. 6 is a schematic perspective view of the equipment support structure;
fig. 7 is a schematic flow chart of the working process of the data acquisition device for automatically adjusting the angle.
In the figure: 1. the device comprises a device supporting structure, 1-1 parts of connecting blocks, 1-2 parts of binocular cameras, 1-3 parts of touch screen processing terminals, 1-4 parts of fingerprint identification devices, 1-5 parts of bar code guns, 1-6 parts of rear covers, 1-7 parts of main body supporting frames, 1-8 parts of heat dissipation holes, 1-9 parts of wiring grooves; 2. 2-1 parts of a rotary disc structure, 2-2 parts of a rotary disc main body frame, 2-2 parts of a disc upper sealing plate, 2-3 parts of a sliding rail, 2-4 parts of a disc cavity; 3. the device comprises a rotating base, 4 an angle adjusting rotating shaft, 5 a control circuit board, 6 a steering engine, 7 a spherical bearing, 8 a steering engine seat, 9 a servo motor.
Detailed Description
An automatic angle adjustment data acquisition device according to the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description. And are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1:
as shown in fig. 1 and 2, the present embodiment provides a data acquisition device capable of automatically adjusting an angle, the structure of the data acquisition device includes an apparatus supporting structure 1, a rotating disc structure 2 and a rotating base 3, a rotating mechanism is installed between the rotating base 3 and the rotating disc structure 2, and the relative angle between the apparatus supporting structure 1 and an operator is controlled by controlling the relative angle between the rotating disc structure 2 and the apparatus supporting structure 1, so that the optimum suitable angle between the apparatus supporting structure 1 and the operator is achieved, and the data acquisition device is convenient for the operator to use; an angle adjusting mechanism is arranged between the rotating disc structure 2 and the equipment supporting structure 1, the rotating disc structure 2 and the rotating base 3 can move relatively.
As shown in fig. 3, the rotating base 3 in this embodiment is provided with spherical bearings 7 distributed circumferentially, and the spherical bearings 7 are used for supporting the rotating disc structure 2, so as to reduce the friction between the rotating base 3 and the rotating disc structure 2. Install spherical bearing 7 near the edge part between spinning disk structure 2 and rotating base 3, spherical bearing 7 mainly plays the effect of support, guarantees simultaneously that spinning disk structure 2 and rotating base 3 atress are even in service, avoids rocking.
As shown in fig. 4 and 5, the rotating disc structure 2 includes a rotating disc main body frame 2-1, an upper disc sealing plate 2-2 is mounted on the rotating disc main body frame 2-1, a disc cavity 2-4 is formed by the upper disc sealing plate 2-2 and the rotating disc main body frame 2-1, the servo motor 9 is located at one side of the disc cavity 2-4, a control circuit board 5 is further mounted in the disc cavity 2-4, and the control circuit board 5 is used for controlling rotation angle measurement of the steering engine 6 and the servo motor 9. The upper sealing plate 2-2 of the disc is provided with a sliding rail 2-3, the sliding rail 2-3 is annular, and the annular sliding rail 2-3 is in sliding fit with the spherical bearing 7.
As shown in fig. 6, the device supporting mechanism 1 in this embodiment includes a main body supporting frame 1-7, a rear cover 1-6 is installed on one side surface of the main body supporting frame 1-7, and a binocular camera 1-2, a fingerprint identifier 1-4, a barcode gun 1-5, and a touch screen processing terminal 1-3 are installed on the other side surface of the main body supporting frame 1-7; the touch screen processing terminal 1-3 is located in the middle of the main body support frame 1-7, the binocular camera 1-2 is located above the touch screen processing terminal 1-3, and the fingerprint identification device 1-4 and the bar code gun 1-5 are located below the touch screen processing terminal 1-3. The connection part of the main body support frame 1-7 and the rear cover 1-6 is provided with a wiring groove 1-9, the rear cover 1-6 is provided with a plurality of heat dissipation holes 1-8 which are uniformly distributed, and the heat dissipation holes 1-8 can form various shapes, thereby enhancing the aesthetic property of the appearance while dissipating heat; the connecting block 1-1 is arranged at the joint of the main body support frame 1-7 and the angle adjusting rotating shaft 4.
The slewing mechanism in this embodiment includes steering wheel 6 and rudder frame 8, and the base member end of steering wheel 6 is installed on rudder frame 8, and rudder frame 8 is installed at rotating base 3, and the output of steering wheel 6 rotates and connects rotating disc structure 2.
The angle adjusting mechanism in the embodiment comprises a servo motor 9 and an angle adjusting rotating shaft 4, wherein the base body end of the servo motor 9 is positioned on the rotating disc structure 2, the output end of the servo motor 9 is rotatably connected with the angle adjusting rotating shaft 4, and the angle adjusting rotating shaft 4 is hinged with the edge ends of the main body supporting frames 1-7.
The control circuit board 5 in the embodiment is electrically connected with a host, and the host comprises a main control module, a graphic processing module and a local image processing module;
the master control module is used for issuing a facial image data acquisition instruction, acquiring facial images of an operator by the binocular camera after the instruction is issued, and uploading the data to a local database for storage; in the process of uploading the facial image data, the master control module has no right to interfere the uploading and storing actions of the binocular camera; after the data are uploaded, an independent local image processing module independently judges the image acquisition quality, and after judgment, the local image processing module sends an instruction and a main control module to determine whether to acquire the data again; after the acquisition is finished, the main control module stops the process of the acquisition process;
the image processing module is used for driving the binocular camera to collect facial image data of an operator, processing the collected data through self-contained images, determining fine adjustment amount of the binocular self-lens, and uploading the collected data to a database of the main control module; through the graphic processing of the main control module, the increment of the rotation angle of the steering engine and the servo motor is calculated, the optimal position and angle between the equipment carried by the equipment supporting structure and an operator are achieved by adjusting the angle of the steering engine and the angle of the motor, and meanwhile, the binocular camera is finely adjusted again, so that the facial data of the operator are ensured to be completely within the acquisition range;
the local image processing module is used for being activated when image data are uploaded at the binocular, performing tasks of image storage and image quality judgment, and sending a result instruction to the main control module after the tasks are judged; when the data acquisition is successful, the main control module sends age group data of a face image data owner to the local image processing module, the local image processing module is provided with an age group to store the face image data, and the image data kept locally is isolated from a network to ensure the safety of the data; when reading data, a special communication network is needed for reading.
The host control system comprises a neural network system besides a main control module for controlling the data acquisition system, wherein the neural system is of a type without limitation, BP or MFFNN. The neural network system mainly takes a single-machine small neural network as a main type so as to improve the adaptability of the data acquisition system in various environments.
The control module of the invention has the optimized steering engine 6 initial angle omega e0 And the initial angle omega of the servo motor 9 d0 And generalizing a new initial angle using a neural network system such as BP (pre-feedback neural network), MFFNN (multi-layer forward neural network), and storing the generalized result in the control circuit board 5 to replace the previous data. After a period of data acquisition, the local image processing program performs feature statistics on the acquired images, such as eye distance, eye-nose distance and the like in the facial data of the acquired data according to age stages. When the neural network system is generalized, the interocular distance and the original initial angle of each age group in the latest period of time are used as input values, and the position angle omega of the steering engine 6 in the same period of time is used e Position angle omega of servo motor 9 d0 The statistical average value of (a) is used as a judgment value. Obtaining a new initial angle omega after the neural net is slightly generalized e0 And ω d0 。
After a period of time, the acquisition amount of facial image data of each age group needs to be manually detected, and facial image data statistics of the age group with particularly little data are removed, so that the input amount in the neural network generalization process is reduced, and the neural network generalization time is saved.
The control amount of the main machine in the present embodiment includes the rotation angle ω of the servo motor 9 e And the rotation angle omega of the steering engine 6 d Angle of rotation omega of the servomotor 9 e And the rotation angle omega of the steering engine 6 d Controlled by a control circuit board 5, wherein the control circuit board 5 stores a rotation angle omega of a servo motor 9 e And the rotation angle omega of the steering engine 6 d Initial angle ω of e0 And ω d0 After each startup, the control circuit board 5 drives the servo motor 9 and the steering engine 6 to run to an initial angle, and waits for the instruction of the main control module after the initial angle is reached;
when the initial angle of the neural network is optimized, statistical analysis is carried out on data collected on the same day after work on the same day is completed; when statistical analysis is performed, the data processing process is specifically as follows:
s1, counting data omega of the day ei And ω di Wherein, i =1,2, \8230;, n;
s2, solving a data mean value, wherein the formula is as follows:
s3, solving the standard deviation of the data, wherein the formula is as follows:
s4, in order to judge whether the collected data are data of common people or not and reject some special data (for example, people intentionally use the limit positions to collect the data), the data are required to be collectedData cleaning is performed according to variance: setting variance limit s based on usage statistics emm And s dm The method comprises the following steps:
when s is e And s d Are respectively less than s emm And s dm If so, the acquired data is considered as normal data, and the next calculation is carried out;
when s is e And s d One or both of the values of (a) is greater than s emm And s dm If so, cleaning the group of data larger than the set of data;
when s is e ＞s em Then from data ω ei Removing
Maximum data, and making variance s from new standard variance calculation e ＜s em 。
When s is d ＞s dm Then from data ω di Removing
Maximum data, and making variance s by newly calculating standard variance d ＜s dm 。
S5, counting
And
performing network generalization of the neural network as an expected value of the neural network; and averaging the sampled data of that day
Standard deviations se and sd (standard deviations of the cleaned data) are used as training input data as differences of the respective characteristic values, the formula is as follows:
Δs e ＝s e -s e0 ；
Δs d ＝s d -s d0 ；
wherein the training input
Training input needs to be normalized by an extreme method before input;
training output
S6, the neural network adopts a small multilayer network topological structure: the neural network structure adopts a multi-input and dual-output structure (for example, a common BP neural network is adopted, the structure adopts a three-layer neural network and two data outputs of four input parameters) or adopts a self-coding model (Auto-Encoder) with the same output as the original input;
in the network design, the η learning rate is designed to adopt different stage values according to the change rate of each output error, and the specific steps are as follows:
when in use
When in use
Wherein a, A and B are specific numerical values;
s7, after the network training is finished, the variable quantity of the angle is obtained, and the method specifically comprises the following steps:
inputting an input quantity IN (0 0) into the network;
the output quantity OUT (Δ ω) e Δω d )；
S8, solving a new angle variable, wherein the formula is as follows:
ω e1 ＝ω e0 +Δω e ；
ω d1 ＝ω d0 +Δω d ；
s9, outputting a set value to a control circuit board: will omega e1 And ω d1 And writing the initial value into the circuit control board.
As shown in fig. 7, the working process of the device is as follows:
(1) After the power is switched on, the circuit control board 5 controls the steering engine 6 and the servo motor 9 to rotate to a set initial position; the binocular camera 1-2 collects facial images of an operator, and after image processing, whether the collected facial images meet requirements is judged:
(1) if the collected face image meets the requirements, uploading the data to a host independent database, and executing the step (4) in the next step;
(2) if the collected face image does not meet the requirement, executing the step (2);
(2) Adjusting the relative positions of the binocular camera 1-2 and an operator through a micro-motion structure of the binocular camera 1-2, re-collecting the facial image, and judging whether the collected image requires again:
(1) if the collected face image meets the requirements, uploading the data to a host independent database, and executing the step (4) in the next step;
(2) if the collected face image does not meet the requirement, executing the step (3);
(3) The host control module controls the control circuit board 5 to rotate the steering engine 6 and the servo motor 9, so that the relative position of the equipment supporting structure 1 and the face of an operator is adjusted; after the adjustment is finished, the binocular camera 1-2 acquires the facial image of the operator again, and judges whether the facial image meets the requirements again:
(1) if the collected face image meets the requirements, uploading the data to a host independent database, and executing the step (4) in the next step;
(2) if the facial image data do not meet the requirements, repeating the step (2) and the step (3) until the facial image data acquisition meets the requirements;
(4) After the binocular camera 1-2 finishes the acquisition of the facial image, the equipment supporting structure 1 and the rotating disc structure 2 are in ideal relative positions with an operator, so that the operator can conveniently perform the next operation; at this point, the equipment support structure 1 and the rotating disc structure 2 lock their position until the operator has completed all the operations;
(5) After the operator finishes all operations, the main control module of the host sends an instruction to the control circuit board 5 and the binocular camera 1-2, the control circuit board 5 drives the steering engine 6 and the servo motor 9 to return to the initial position, the binocular camera 1-2 returns to the initial position, and the equipment supporting structure 1 and the rotating disc structure 2 are adjusted to the initial positions;
(6) After the collection task is completed, the control circuit board 5 uploads the recorded locking angle value omega to a main control module of the host, the main control module of the host periodically counts the angle omega, extracts a characteristic value, uses the characteristic value as a neural network training target value, trains a neural network periodically, and predicts a neural network angle initial angle predicted value omega e0 And ω d0 As the initial angle of the steering engine 6 and the servo motor 9 in the control circuit board;
(7) And the host computer periodically updates the initial angles of the steering engine 6 and the servo motor 9 in the control circuit board so as to improve the data acquisition efficiency.
Example 2:
the invention can be matched with a self-service terminal to be used as a data acquisition device of the terminal, and the host of the invention can be coupled to the host of the self-service terminal or other matched equipment. Once the two cameras are coupled, the self-service terminal can adjust the relative positions of the binocular cameras 1-2 and an operator by controlling the movement of the servo motor 9 steering engine 6 through the control circuit board 5 by a host of the self-service terminal, so that the relative positions of the touch screen processing terminal 1-3 and the operator are ensured, and the operator can conveniently work.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A data acquisition device capable of automatically adjusting angles is characterized by comprising an equipment supporting structure, a rotating disc structure and a rotating base, wherein a rotating mechanism is arranged between the rotating base and the rotating disc structure; an angle adjusting mechanism is arranged between the rotating disc structure and the equipment supporting structure;
the equipment supporting mechanism comprises a main body supporting frame, a rear cover is arranged on one side surface of the main body supporting frame, and a binocular camera, a fingerprint identifier, a bar code gun and a touch screen processing terminal are arranged on the other side surface of the main body supporting frame;
the rotating mechanism comprises a steering engine and a steering engine seat, the base body end of the steering engine is installed on the steering engine seat, the steering engine seat is installed on the rotating base, and the output end of the steering engine is rotatably connected with the rotating disc structure.
2. The data collecting device for automatically adjusting the angle of claim 1, wherein the angle adjusting mechanism comprises a servo motor and an angle adjusting shaft, the base end of the servo motor is located on the rotating disc structure, the output end of the servo motor is rotatably connected with the angle adjusting shaft, and the angle adjusting shaft is hinged with the edge end of the main body supporting frame.
3. The data acquisition device for automatically adjusting the angle according to claim 1 or 2, wherein a wiring groove is arranged at the joint of the main body supporting frame and the rear cover, and a plurality of heat dissipation holes are uniformly distributed on the rear cover;
the main body support frame is provided with the connecting block with the angle adjusting rotating shaft junction.
4. The data acquisition device for automatically adjusting the angle of claim 3, wherein the touch screen processing terminal is located at the middle position of the main body support frame, the binocular camera is located above the touch screen processing terminal, and the fingerprint recognizer and the barcode gun are located below the touch screen processing terminal.
5. The data acquisition device for automatically adjusting the angle as claimed in claim 4, wherein the rotating base is provided with a plurality of spherical bearings distributed circumferentially, the spherical bearings are used for supporting the rotating disc structure, and the friction between the rotating base and the rotating disc structure is reduced while the supporting function is performed.
6. The automatic angle adjustment data acquisition device according to claim 5, wherein the rotating disc structure comprises a rotating disc main body frame, an upper disc sealing plate is arranged on the rotating disc main body frame, a disc cavity is formed by the upper disc sealing plate and the rotating disc main body frame, the servo motor is located at one side in the disc cavity, and a control circuit board is further arranged in the disc cavity and used for controlling the rotating angle of the steering engine and the servo motor.
7. The automatic angle adjustment data acquisition device as claimed in claim 6, wherein the upper sealing plate of the disc is provided with a sliding rail, the sliding rail is in a ring shape, and the ring-shaped sliding rail is slidably engaged with the spherical bearing.
8. The data acquisition device for automatically adjusting the angle according to claim 1, wherein the control circuit board is electrically connected with a host computer, and the host computer comprises a main control module, a graphic processing module and a local image processing module;
the master control module is used for issuing a facial image data acquisition instruction, acquiring facial images of an operator by the binocular camera after the instruction is issued, and uploading the data to a local database for storage; in the process of uploading the facial image data, the master control module has no right to interfere the uploading and storing actions of the binocular camera; after the data are uploaded, an independent local image processing module independently judges the image acquisition quality, and after judgment, the local image processing module sends an instruction and a main control module to determine whether to acquire the data again; after the acquisition is finished, the main control module stops the process of the acquisition process;
the image processing module is used for driving the binocular camera to collect facial image data of an operator, processing the collected data through self-contained images, determining fine adjustment amount of the binocular self-lens, and uploading the collected data to a database of the main control module; through the graphic processing of the main control module, the increment of the rotation angle of the steering engine and the servo motor is calculated, the optimal position and angle between the equipment carried by the equipment supporting structure and an operator are achieved by adjusting the angle of the steering engine and the angle of the motor, and meanwhile, the binocular camera is finely adjusted again, so that the facial data of the operator are ensured to be completely within the acquisition range;
the local image processing module is used for being activated when image data are uploaded at the binocular, performing tasks of image storage and image quality judgment, and sending a result instruction to the main control module after the tasks are judged; when the data acquisition is successful, the main control module sends age group data of a face image data owner to the local image processing module, the local image processing module is provided with an age group to store the face image data, and the isolation between the locally stored image data and a network is ensured so as to ensure the safety of the data; when reading data, a special communication network is needed for reading.
9. The data acquisition device for automatically adjusting the angle of claim 8, wherein the control quantity of the host comprises a rotation angle ω of a servo motor e And the rotation angle omega of the steering engine d Angle of rotation omega of servo motor e And the rotation angle omega of the steering engine d Controlled by a control circuit board, wherein the rotation angle omega of the servo motor is stored in the control circuit board e And the rotation angle omega of the steering engine d Initial angle ω of e0 And ω d0 At each start-upThen, the control circuit board drives the servo motor and the steering engine to run to an initial angle, and after the initial angle is reached, the control circuit board waits for an instruction of the main control module;
when the initial angle of the neural network is optimized, statistical analysis is carried out on data collected on the same day after work on the same day is completed; when statistical analysis is performed, the data processing process is specifically as follows:
s1, counting data omega of the day ei And ω di Wherein i =1,2, \8230, n;
s2, solving a data mean value, wherein the formula is as follows:
s3, solving the standard deviation of the data, wherein the formula is as follows:
s4, cleaning data according to the variance: setting variance limit s based on usage statistics em And s dm The method comprises the following steps:
when s is e And s d Are respectively less than s em And s dm If so, the acquired data is considered as normal data, and the next calculation is carried out;
when s is e And s d One or both of the values of (b) are greater than s em And s dm If so, cleaning the group of data larger than the set of data;
when s is e ＞s em Then the slave dataω ei Removing
Maximum data, and making variance s from new standard variance calculation e ＜s em 。
When s is d ＞s dm Then from data ω di Rejecting
Maximum data, and making variance s by newly calculating standard variance d ＜s dm 。
S5, counting
And
performing network generalization of the neural network as an expected value of the neural network; and averaging the sampled data of the current day
Standard deviation s e And s d The Russian characteristic data serving as training input data are difference values of all characteristic values, and the formula is as follows:
Δs e ＝s e -s e0 ；
Δs d ＝s d -S d0 ；
wherein the training input
Training input needs to be normalized by an extreme method before input;
training output
S6, the neural network adopts a small multilayer network topological structure: the neural network structure adopts a multi-input and dual-output structure or a self-coding model with the same output as the original input;
in the network design, the η learning rate is designed to adopt different stage values according to the change rate of each output error, which is as follows:
when in use
When in use
Wherein a, A and B are specific numerical values;
s7, after the network training is finished, the angle variation is obtained, and the method specifically comprises the following steps:
inputting an input quantity IN (0000) into the network;
the output quantity OUT (Δ ω) e Δω d )；
S8, solving a new angle variable, wherein the formula is as follows:
ω e1 ＝ω e0 +Δω e ；
ω d1 ＝ω d0 +Δω d ；
s9, outputting a set value to a control circuit board: will omega e1 And ω d1 And writing the initial value into the circuit control board.
10. The data acquisition device for automatically adjusting the angle according to claim 8 or 9, wherein the device specifically works as follows:
(1) After the power is switched on, the circuit control board controls the steering engine and the servo motor to rotate to a set initial position; the binocular camera collects facial images of an operator, and after image processing, whether the collected facial images meet requirements is judged:
(1) if the collected face image meets the requirements, uploading the data to a host independent database, and executing the step (4) in the next step;
(2) if the collected face image does not meet the requirement, executing the step (2);
(2) The relative position of binocular camera and operator is adjusted through the fine motion structure of binocular camera self, reacquires facial image again to again through judging whether the image of gathering requires:
(1) if the collected facial image meets the requirements, uploading the data to a host independent database, and executing the step (4) in the next step;
(2) if the collected face image does not meet the requirement, executing the step (3);
(3) The host control module controls the control circuit board 5 to rotate the steering engine 6 and the servo motor 9, so that the relative position of the equipment supporting structure and the face of an operator is adjusted; after the adjustment is finished, the binocular camera acquires the facial image of the operator again, and judges whether the facial image meets the requirements again:
(1) if the collected face image meets the requirements, uploading the data to a host independent database, and executing the step (4) in the next step;
(2) if the facial image data do not meet the requirements, repeating the step (2) and the step (3) until the facial image data acquisition meets the requirements;
(4) After the binocular camera finishes the acquisition of the facial image, the equipment supporting structure and the rotating disc structure are in relatively ideal relative positions with an operator, so that the operator can conveniently perform the next operation; at the moment, the equipment supporting structure and the rotating disc structure lock the position of the equipment supporting structure and the rotating disc structure until an operator finishes all operations;
(5) After the operator finishes all operations, the main control module of the host sends an instruction to the control circuit board and the binocular camera, the control circuit board drives the steering engine and the servo motor to return to the initial position, the binocular camera returns to the initial position, and the equipment supporting structure and the rotating disc structure are adjusted to the original positions;
(6) After the acquisition task is completed, the control circuit board uploads the recorded locking angle value omega to a main control module of the host, the main control module of the host periodically counts the angle omega, extracts a characteristic value and uses the characteristic value as a neural network training target value, trains a neural network periodically, and predicts a neural network angle initial angle predicted value omega e0 And omega d0 The angle is used as the initial angle of a steering engine and a servo motor in the control circuit board;
(7) And the host periodically updates the initial angles of the steering engine and the servo motor in the control circuit board so as to improve the data acquisition efficiency.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210991818.9A CN115460346B (en) | 2022-08-17 | 2022-08-17 | Automatic angle-adjusting data acquisition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210991818.9A CN115460346B (en) | 2022-08-17 | 2022-08-17 | Automatic angle-adjusting data acquisition device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115460346A true CN115460346A (en) | 2022-12-09 |
| CN115460346B CN115460346B (en) | 2024-01-23 |
Family
ID=84297786
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210991818.9A Active CN115460346B (en) | 2022-08-17 | 2022-08-17 | Automatic angle-adjusting data acquisition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115460346B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110738984A (en) * | 2019-05-13 | 2020-01-31 | 苏州闪驰数控系统集成有限公司 | Artificial intelligence CNN, LSTM neural network speech recognition system |
| CN110811564A (en) * | 2019-12-06 | 2020-02-21 | 南京中医药大学 | Intelligent face image and tongue image acquisition terminal system and face image and tongue image acquisition method |
| CN110851957A (en) * | 2019-10-15 | 2020-02-28 | 南京航空航天大学 | Atmospheric data sensing system resolving method based on deep learning |
| CN210351404U (en) * | 2019-09-18 | 2020-04-17 | 广州林智智能科技有限公司 | High-definition video conference communication system |
| CN210777093U (en) * | 2019-11-15 | 2020-06-16 | 江苏德亚智能科技股份有限公司 | Intelligent security system based on face recognition |
| US20210049403A1 (en) * | 2019-03-30 | 2021-02-18 | Beijing Sensetime Technology Development Co., Ltd. | Method and device for image processing, electronic device, and storage medium |
| CN112422826A (en) * | 2020-11-17 | 2021-02-26 | 娄底职业技术学院 | Tunnel surface crack image acquisition device based on artificial intelligence and use method |
| CN213579337U (en) * | 2020-12-17 | 2021-06-29 | 慧猿教育科技(山东)有限责任公司 | Visual collection system based on deep neural network training |
| CN113091768A (en) * | 2021-03-12 | 2021-07-09 | 南京理工大学 | MIMU integral dynamic intelligent calibration compensation method |
| US20210248442A1 (en) * | 2020-02-11 | 2021-08-12 | Distech Controls Inc. | Computing device and method using a neural network to predict values of an input variable of a software |
| CN216486465U (en) * | 2022-03-21 | 2022-05-10 | 湖南捷亿信科技有限公司 | Intelligent surface label terminal |
-
2022
- 2022-08-17 CN CN202210991818.9A patent/CN115460346B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210049403A1 (en) * | 2019-03-30 | 2021-02-18 | Beijing Sensetime Technology Development Co., Ltd. | Method and device for image processing, electronic device, and storage medium |
| CN110738984A (en) * | 2019-05-13 | 2020-01-31 | 苏州闪驰数控系统集成有限公司 | Artificial intelligence CNN, LSTM neural network speech recognition system |
| CN210351404U (en) * | 2019-09-18 | 2020-04-17 | 广州林智智能科技有限公司 | High-definition video conference communication system |
| CN110851957A (en) * | 2019-10-15 | 2020-02-28 | 南京航空航天大学 | Atmospheric data sensing system resolving method based on deep learning |
| CN210777093U (en) * | 2019-11-15 | 2020-06-16 | 江苏德亚智能科技股份有限公司 | Intelligent security system based on face recognition |
| CN110811564A (en) * | 2019-12-06 | 2020-02-21 | 南京中医药大学 | Intelligent face image and tongue image acquisition terminal system and face image and tongue image acquisition method |
| US20210248442A1 (en) * | 2020-02-11 | 2021-08-12 | Distech Controls Inc. | Computing device and method using a neural network to predict values of an input variable of a software |
| CN112422826A (en) * | 2020-11-17 | 2021-02-26 | 娄底职业技术学院 | Tunnel surface crack image acquisition device based on artificial intelligence and use method |
| CN213579337U (en) * | 2020-12-17 | 2021-06-29 | 慧猿教育科技(山东)有限责任公司 | Visual collection system based on deep neural network training |
| CN113091768A (en) * | 2021-03-12 | 2021-07-09 | 南京理工大学 | MIMU integral dynamic intelligent calibration compensation method |
| CN216486465U (en) * | 2022-03-21 | 2022-05-10 | 湖南捷亿信科技有限公司 | Intelligent surface label terminal |
Non-Patent Citations (2)
| Title |
|---|
| BIN WU: "A Neural Network-Based On-line Monitoring Model of Process Mean and Variance Shifts", 2010 INTERNATIONAL CONFERENCE ON E-BUSINESS AND E-GOVERNMENT * |
| 冯一诺: "基于模糊神经网络理论的异构无线网络接入选择研究", 中国优秀硕士学位论文全文数据库 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115460346B (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10489932B2 (en) | Intelligent shooting training management system | |
| CN111016181B (en) | Printing monitoring system and method | |
| WO1998002778A1 (en) | Device for controlling, regulating and monitoring a motion-picture camera | |
| CN102196171A (en) | Imaging control device, subject detection method, and program | |
| CN110362090A (en) | A kind of crusing robot control system | |
| CN104660973B (en) | The Remote Device Control management module system of view-based access control model information identification | |
| CN102196173A (en) | Imaging control device and imaging control method | |
| CN108028884A (en) | Camera system and camera shooting control method | |
| CN101649952A (en) | Locking tracking servo console with two degrees of freedom | |
| CN210414522U (en) | Photography robot and control system thereof | |
| CN2916770Y (en) | Automatic positioning face recognition device | |
| CN115329676A (en) | Digital twin virtual-real synchronous terminal equipment and system | |
| CN115460346A (en) | Data acquisition device capable of automatically adjusting angle | |
| CN107958205B (en) | Shooting training intelligent management system | |
| CN110798613B (en) | Face camera equipment that many visual angles were gathered | |
| CN208806912U (en) | Image capture device | |
| CN102967375A (en) | Infrared thermal imaging instrument and method capable of implementing presetting function based on stepping motor | |
| CN210745352U (en) | Green plum single-angle image acquisition device | |
| CN209297326U (en) | Two axle The Cloud Terraces iris face acquisition device | |
| CN112866583B (en) | Data acquisition system, method, device, electronic equipment and storage medium | |
| CN113689130A (en) | Vision-based goods management device and system for e-commerce and goods management method | |
| CN212541476U (en) | Three-in-one self-service integrated machine | |
| CN115314630A (en) | Intelligent regulating and controlling management system for wedding photo shooting and camera shooting based on image recognition and analysis technology | |
| CN209525684U (en) | Identification device is used in one kind acquisition Internet-based | |
| CN209265463U (en) | Iris capturing equipment with distance measurement feedback |
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 |