CN112205961A - Central control machine and vision detection device - Google Patents
Central control machine and vision detection device Download PDFInfo
- Publication number
- CN112205961A CN112205961A CN202011190552.5A CN202011190552A CN112205961A CN 112205961 A CN112205961 A CN 112205961A CN 202011190552 A CN202011190552 A CN 202011190552A CN 112205961 A CN112205961 A CN 112205961A
- Authority
- CN
- China
- Prior art keywords
- face
- central control
- control machine
- key point
- main control
- 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.)
- Pending
Links
- 230000004438 eyesight Effects 0.000 title claims abstract description 102
- 238000001514 detection method Methods 0.000 title claims abstract description 80
- 230000036760 body temperature Effects 0.000 claims description 25
- 230000001939 inductive effect Effects 0.000 claims description 12
- 230000001954 sterilising effect Effects 0.000 claims description 6
- 238000004659 sterilization and disinfection Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 52
- 238000000034 method Methods 0.000 abstract description 20
- 230000008569 process Effects 0.000 abstract description 9
- 230000002567 autonomic effect Effects 0.000 abstract 1
- 238000012549 training Methods 0.000 description 23
- 230000003068 static effect Effects 0.000 description 10
- 238000012790 confirmation Methods 0.000 description 8
- 238000002372 labelling Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 6
- 230000004304 visual acuity Effects 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 210000000887 face Anatomy 0.000 description 4
- 230000004308 accommodation Effects 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000036544 posture Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000005389 magnetism Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000001491 myopia Diseases 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001012 protector Effects 0.000 description 1
- 238000013102 re-test Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/02—Subjective types, i.e. testing apparatus requiring the active assistance of the patient
- A61B3/028—Subjective types, i.e. testing apparatus requiring the active assistance of the patient for testing visual acuity; for determination of refraction, e.g. phoropters
- A61B3/032—Devices for presenting test symbols or characters, e.g. test chart projectors
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/0016—Operational features thereof
- A61B3/0033—Operational features thereof characterised by user input arrangements
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
- A61B3/0016—Operational features thereof
- A61B3/0041—Operational features thereof characterised by display arrangements
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/107—Measuring physical dimensions, e.g. size of the entire body or parts thereof
- A61B5/1072—Measuring physical dimensions, e.g. size of the entire body or parts thereof measuring distances on the body, e.g. measuring length, height or thickness
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2560/00—Constructional details of operational features of apparatus; Accessories for medical measuring apparatus
- A61B2560/02—Operational features
- A61B2560/0223—Operational features of calibration, e.g. protocols for calibrating sensors
Abstract
The application provides well accuse machine and eyesight detection device, this well accuse machine include the casing, install the display screen on the casing to and install sensor unit and the main control unit in the casing respectively. In the vision testing process, when the vision testing icon is displayed on the display screen, the tester identifies the vision testing icon, the inductor unit detects the identification signal and transmits the identification signal to the main control unit, and the main control unit converts the identification signal into a vision testing result and stores the vision testing result. Subsequently, the main control unit controls the display screen to automatically switch the vision detection icon, and the inspector identifies the vision detection icon. Through the repeated operation, the eyesight of the examiner can be intuitively and accurately analyzed and judged, and the eyesight result of the examiner is stored for next comparison and analysis. This well accuse machine need not medical personnel and assists, just can realize independently detecting the autonomic independence of examiner's eyesight, can realize intelligent operation, and adaptability is good.
Description
Technical Field
The application belongs to the technical field of vision detection, and more particularly relates to a vision detection device of a central control machine and the central control machine.
Background
The vision detection device is important test equipment for human vision detection, and can judge the vision condition of a detector most intuitively and accurately.
In the vision test, generally, a medical staff designates a vision test icon on a display screen at will, and then analyzes and judges the vision of the examiner according to the result fed back by the examiner. However, the current vision detection device needs real-time cooperation of medical personnel in the detection process, which leads to high labor cost of the vision detection device, failure to realize intelligent operation and poor adaptability.
Disclosure of Invention
An object of the embodiment of the application is to provide a well accuse machine and vision detection device to solve the vision detection device that exists among the correlation technique and need medical personnel coordination, the cost of labor is high, can't realize intelligent operation, problem that adaptability is poor.
In order to achieve the above purpose, the embodiment of the present application adopts the following technical solutions:
in one aspect, a central control machine is provided, which includes:
the casing comprises a casing body and a door plate, one end of the door plate is hinged to the casing body, a containing groove for containing an external object is formed in the casing body, and the door plate covers the containing groove; the other end of the door plate is provided with a magnetic attraction piece, and an electromagnetic lock which is in magnetic attraction connection with the magnetic attraction piece is correspondingly arranged on the inner side wall of the accommodating groove;
the display screen is arranged on the shell and used for displaying the eyesight detection icons;
the sensor unit is arranged in the shell and used for receiving signals sent by a detector when the detector identifies the vision detection mapping mark;
the main control unit is arranged in the shell and used for controlling the display screen to switch the vision detection icon, receiving a signal of the sensor unit, comparing the signal with the direction of the vision detection icon to obtain a vision detection result and storing the vision detection result;
the electromagnetic lock, the display screen and the sensor unit are respectively electrically connected with the main control unit.
Adopt above-mentioned structure, this application is through installing display screen, inductor element and main control unit on the casing respectively. In the vision testing process, when the vision testing icon is displayed on the display screen, the tester identifies the vision testing icon, the inductor unit detects the identification signal and transmits the identification signal to the main control unit, and the main control unit converts the identification signal into a vision testing result and stores the vision testing result. Subsequently, the main control unit controls the display screen to automatically switch the vision detection icon, and the inspector identifies the vision detection icon. Through the repeated operation, the eyesight of the examiner can be intuitively and accurately analyzed and judged, and the eyesight result of the examiner is stored for next comparison and analysis. Therefore, this well accuse machine need not medical personnel's assistance, just can realize independently detecting the independence of examiner's eyesight, can realize intelligent operation, and adaptability is good. Through the cooperation of magnetism piece and electromagnetic lock of inhaling, can realize the automatic switch of door plant.
In one embodiment, an inductive switch is installed on an inner side wall of the accommodating groove, and the inductive switch is electrically connected with the main control unit; and the door panel is correspondingly provided with a touch panel for touching the inductive switch.
In one embodiment, an elastic member for elastically pushing the door panel is mounted on an inner side wall of the accommodating groove.
In one embodiment, the central control machine further comprises a disinfection lamp for sterilizing the accommodating groove; the disinfection lamp is arranged in the containing groove and electrically connected with the main control unit.
In one embodiment, the accommodating groove includes a first card groove, a second card groove spaced apart from the first card groove, and a third card groove connecting the first card groove and the second card groove; the first clamping groove is used for allowing one end of the external object to extend into the first clamping groove, the second clamping groove is used for allowing the other end of the external object to extend into the second clamping groove, and the third clamping groove is used for corresponding arrangement with the middle position of the external object.
In one embodiment, the central control machine further comprises a card reader for identifying the identity information of the detector; the card reader is arranged on the shell and electrically connected with the main control unit.
In one embodiment, the central control machine further comprises an in-place detector for detecting whether an external object is accommodated in the accommodating groove; the in-place detector is mounted on the shell and electrically connected with the main control unit.
In one embodiment, the central control computer further comprises a camera for performing face recognition on the detector; the camera is installed on the casing, the camera with main control unit electric connection.
In one embodiment, the central control computer further comprises a body temperature sensor for detecting the body temperature of the examinee, a distance sensor for measuring the distance between the examinee and the display screen, and a height sensor for detecting the height of the examinee; the body temperature sensor, the distance sensor and the height sensor are respectively installed on the shell, and the body temperature sensor, the distance sensor and the height sensor are respectively electrically connected with the main control unit.
In another aspect, a vision testing apparatus is provided, which includes the above-mentioned central control machine. By adopting the vision detection device of the central control machine, the vision test operation of a detector can be independently and autonomously carried out, the accompanying of medical personnel is not needed, and the labor cost is reduced; the intellectualization of vision detection is realized, and the adaptability is good.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or exemplary technical descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a central control machine provided in an embodiment of the present application;
FIG. 2 is an exploded view of FIG. 1;
fig. 3 is a schematic structural diagram of a central control machine provided in the embodiment of the present application, after a door panel is removed;
FIG. 4 is an enlarged schematic view at A in FIG. 3;
FIG. 5 is a schematic structural diagram of a door panel according to an embodiment of the present disclosure;
FIG. 6 is an exploded view of a vision testing device according to an embodiment of the present application;
fig. 7 is a schematic structural view of the vision testing apparatus provided in the embodiment of the present application, with a door panel removed;
FIG. 8 is an enlarged schematic view at B of FIG. 7;
fig. 9 is a schematic structural view of an eye shield according to an embodiment of the present disclosure;
FIG. 10 is an exploded view of FIG. 9;
fig. 11 is a functional equivalent schematic diagram of a vision testing apparatus according to an embodiment of the present application.
Wherein, in the drawings, the reference numerals are mainly as follows:
1-a central control machine; 10-an inductor unit;
11-a housing; 111-a housing; 112-a door panel; 1121-magnetic attracting piece; 1122-touch pad; 113-a receiving groove; 114-a first card slot; 115-a second card slot; 116-a third card slot; 117-charging coil; 118-an electromagnetic lock; 119-a sensing switch;
12-a display screen; 13-a master control unit; 131-an acquisition module; 132-a keypoint prediction module; 133-labeling module; 134-a training module; 135-a processing module;
14-a sensor unit; 141-a camera; 142-a height sensor; 143-body temperature sensor; 144-a distance sensor;
15-a loudspeaker; 16-an antenna; 17-a power switch; 18-an interface; 19-a card reader;
2-an eye shield; 21-a housing; 211-occult eyes; 212-a hand-held part; 213-a bottom shell; 2131-hook; 2132-reference plate; 2133-limit baffle; 214-upper cover; 2140-an opening; 22-a control panel; 221-directional contact; 23-a power supply; a 24-directional key; 241-anti-slip salient points; 25-a confirmation key; 26-magnet.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present application clearer, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, fig. 2 and fig. 11, a center control machine 1 according to an embodiment of the present application will now be described. The central control machine 1 includes a casing 11, a display 12 installed on the casing 11, and a sensor unit 10 and a main control unit 13 respectively installed in the casing 11. The display 12 and the sensor unit 10 are electrically connected to the main control unit 13. The casing 11 is installed on the wall, and then the installation of realization well accuse machine 1 is fixed in on the wall. The display screen 12 is used for displaying a vision test icon, which is generally a letter E arranged in four directions, namely, up, down, left and right, so as to meet the national standard vision test requirement.
The sensor unit 10 is used for receiving signals emitted by the examiner when identifying the vision detection icon, and the signals can be understood as the following situations: 1. and the examiner gives the limb movement when recognizing the vision detection icon. For example, when the letter E is displayed on the display 12, the examiner performs recognition confirmation by the action of the arm pointing up or down. Alternatively, when the letter E to the left is displayed on the display screen 12, the examiner performs recognition confirmation by unfolding the left hand. Or, when the letter E to the right is displayed on the display 12, the examiner performs recognition confirmation by unfolding the right hand; the sensor unit 10 receives the above signals as the body movements of the examiner, and realizes gesture recognition.
2. The examiner recognizes the voice uttered when the eyesight is inspected. For example, the examiner performs recognition and judgment through the voices of "up", "down", "left" and "right" according to the direction of the eyesight detection icon; the sensor unit 10 receives the voice of the detector as the signal, and realizes voice recognition;
3. the detector sends out signals by means of an external terminal. For example, the external terminal is in communication connection with the central control machine 1, the external terminal is provided with a direction key 24, and the examiner can identify the vision detection icon by pressing different direction keys 24; the sensor unit 10 receives the indication signal sent by the external terminal, which is the signal. In the embodiment of the application, the eye shade 2 is used as an external terminal to realize communication connection with the central control machine 1.
The main control unit 13 is used for controlling the display 12 to switch the vision test icon, receiving the signal of the sensor unit 10, comparing the signal with the direction of the vision test icon to obtain a vision test result, and storing the vision test result. It can be understood that, when the examiner performs the visual acuity test, after the first visual acuity test icon is displayed on the display screen 12, the main control unit 13 switches the visual acuity test icons at equal intervals, for example, after 3s, 4s, 5s, etc., the next visual acuity test icon is displayed on the display screen 12. The above steps are repeated in a circulating way until the vision detection is finished. Sensor unit 10 transmits the signal that sends out when the map is examined with the discernment eyesight of the person who receives the detection for main control unit 13, and main control unit 13 carries out the positive misjudgment to this signal through inside design procedure to carry out the storage record to the vision test result, and compare according to national eyesight test table and compare, with the eyesight of approving the person who detects. The algorithm for converting the signal transmitted from the sensor unit 10 into the vision test result by the main control unit 13 can adopt the conventional technical means in the field, and is not described in detail herein.
With this structure, the present application is provided by mounting the display 12, the sensor unit 10, and the main control unit 13 on the cabinet 11, respectively. In the vision testing process, when the vision testing icon is displayed on the display screen 12, the tester identifies the vision testing icon, the sensor unit 10 detects the identification signal and transmits the identification signal to the main control unit 13, and the main control unit 13 converts the identification signal into a vision testing result and stores the vision testing result. Subsequently, the main control unit 13 controls the display screen 12 to automatically switch the optotype icon, and the examiner recognizes the optotype icon again. Through the repeated operation, the eyesight of the examiner can be intuitively and accurately analyzed and judged, and the eyesight result of the examiner is stored for next comparison and analysis. Therefore, this well accuse machine 1 need not medical personnel's assistance, just can realize independently detecting the independence of examiner's eyesight, can realize intelligent operation, and adaptability is good.
Referring to fig. 6, a vision testing apparatus provided in the embodiment of the present application will now be described. The vision detection device comprises an eye shielding device 2 for shielding eyes of a person to be detected and the central control machine 1. Wherein, be communication connection between eye shade 2 and the well control machine 1. Here, the communication connection may be a wire connection, a wireless lan connection, a bluetooth connection, etc., and is not limited herein. By adopting the structure, the vision detection device adopts the central control machine 1, so that the vision test operation can be independently and autonomously performed by a detector without accompanying by medical personnel, and the labor cost is reduced; the intellectualization of vision detection is realized, and the adaptability is good.
In one embodiment, when eye shield 2 is in the active state and bluetooth is not connected, eye shield 2 continuously broadcasts a bluetooth connection message. And after the Bluetooth connection is successful, the Bluetooth module is uniquely bound with the central control machine 1. When the central control machine 1 and the eye shielding device 2 are both in working states, Bluetooth connection is automatically established. When the eye shielding device 2 is in a dormant state, the Bluetooth connection with the central control machine 1 is disconnected.
In one embodiment, referring to fig. 2 and 6, the housing 11 includes a housing 111 and a door 112 mounted on the housing 111; the housing 111 is provided with a receiving groove 113 for receiving an external object, and the door 112 covers the receiving groove 113. Here, the external object may be the eye mask 2 provided in the embodiment of the present application, and is not limited thereto. With this structure, the accommodation groove 113 can be used for accommodating the eye mask 2, thereby facilitating storage of the eye mask 2.
In one embodiment, referring to fig. 9 and 10, eye shield 2 includes a housing 21, a control board 22 and a power supply 23 mounted in housing 21, respectively, and a direction key 24 and a confirmation key 25 mounted on housing 21, respectively; the direction key 24 and the confirmation key 25 are electrically connected to the control board 22, the power supply 23 is electrically connected to the control board 22, and the control board 22 is communicatively connected to the main control unit 13. Here, the communication connection may be a wire connection, a wireless lan connection, a bluetooth connection, etc., and is not limited herein. This structure, eye protector 2 can realize communication connection with well accuse machine 1, and the inspector can select the direction of the visual acuity test icon that shows on display screen 12 according to direction key 24 to transmit the result of selecting to well accuse machine 1 through confirm key 25 and carry out the analysis and judge, and generate final visual acuity test result and save, realize the independent mesh of independently testing.
In one embodiment, referring to fig. 4, 8 and 9, one end of the housing 21 is an eye shielding portion 211, and the other end is a handheld portion 212. The eye shielding portion 211 may have a circular structure, and the handle portion 212 may have a cylindrical structure. Here, the round eye shielding part 211 is not easy to cause measurement misalignment due to the deflection of the position of the vision detection device, which is beneficial to accurately measuring the distance between the center control machine 1 and the eye shielding device 2. The bottom of the accommodating groove 113 is provided with a first clamping groove 114 for accommodating the eye shielding part 211, a second clamping groove 115 for accommodating one end of the handheld part 212 far away from the eye shielding part 211, and a third clamping groove 116 for connecting the first clamping groove 114 and the second clamping groove 115; the eye shield 211 of the eye shield 2 may be placed in the first slot 114, the end of the hand grip 212 of the eye shield 2 may be placed in the second slot 115, and the middle of the eye shield 2 is located in the third slot 116. With the structure, the two ends of the eye shade 2 can be clamped and fixed through the first clamping groove 114 and the second clamping groove 115, and the third clamping groove 116 facilitates taking and placing of the eye shade 2.
In one embodiment, referring to fig. 4, 8 and 9, the depth of the second card slot 115 is greater than the depth of the first card slot 114, and the depth of the third card slot 116 is greater than the depth of the second card slot 115. This structure, the clamping-force at the both ends of hiding eye ware 2 is different, improves the installation steadiness that hides eye ware 2, effectively prevents to hide the droing of eye ware 2. The middle position of the eye shielding device 2 is opposite to the third clamping groove 116, and a space exists between the eye shielding device 2 and the bottom surface of the third clamping groove 116, so that the hand of a detector can extend into the space, and the eye shielding device 2 can be conveniently taken and placed.
In one embodiment, referring to fig. 6 and 10, a wireless charging module (not shown) is installed on the control board 22, and a charging coil 117 for cooperating with the wireless charging module to wirelessly charge the power supply 23 is correspondingly installed in the housing 11. With the structure, when the eye shade 2 is installed in the accommodating groove 113, the central control machine 1 can wirelessly charge the power supply 23, so as to improve the cruising ability of the eye shade 2.
In one embodiment, when the eye mask 2 is stored in the storage slot 113, the eye mask 2 is in a power-off or sleep state. When the eye shade 2 is taken out or triggered by a key, the eye shade 2 is in a working state. When the eye shielding device 2 is not triggered by the key for ten minutes continuously, the eye shielding device 2 enters a dormant state; and triggering the key again to enter a working state. When the central control machine 1 is in an open state, the automatic power-off protection can be carried out after the eye shielding device 2 is fully charged. When well accuse machine 1 is in the bluetooth connection state with eye-shade device 2, eye-shade device 2 sends the electric quantity information of power 23 to well accuse machine 1 every three minutes to realize well accuse machine 1 to the real time monitoring of eye-shade device 2 electric quantity, and can show the electric quantity information of eye-shade device 2 to the person who detects in real time.
In one embodiment, eye shield 2 has indicator lights mounted thereon. The indicator light can emit colored lights of three colors, and can respectively indicate different working states of the eye shielding device 2. When the eye shade 2 is connected with the Bluetooth of the central control machine 1, the eye shade 2 is in a working state, and the indicating lamp displays white and is normally on. When the electric quantity of the eye shielding device 2 is lower than the set value, the indicator lamp displays red and flickers to remind that charging is needed. When the eye shielding device 2 is not connected with the central control machine 1 through Bluetooth or the eye shielding device 2 breaks down, the indicating lamp is turned off. When the eye shield 2 is in the charging state, the indicator light is displayed in red and is normally on. When charging of the eye shield 2 is completed, the indicator lamp is displayed green and always on. Of course, in other embodiments, the color of the indicator light can be adjusted as desired, and is not limited herein.
In one embodiment, an in-place detector for detecting whether an external object is received in the receiving groove 113 is mounted on the housing 11, and the in-place detector is electrically connected to the main control unit 13. Specifically, when eye shade 2 is accommodated in accommodating groove 113, the in-place detector can detect the storage information of eye shade 2, and transmit the storage information to main control unit 13, and after main control unit 13 acquires the storage information, it is determined that eye shade 2 is placed in accommodating groove 113, so as to facilitate the subsequent charging operation of eye shade 2.
In one embodiment, the in-place detector may include a hall sensor for sensing a change in magnetic pole of the magnet 26 to generate a sensing signal, and the magnet 26, and the main control unit 13 detects whether the eye shield 2 is placed in the receiving groove 113 according to the sensing signal. When the indicator light is turned on, it indicates that the eye shield 2 is placed back in the accommodation groove 113. In some embodiments, the position detector may be a light sensor, a distance sensor, a limit switch, a magnetic sensor, or the like, and is not limited herein.
In one embodiment, referring to fig. 10, the housing 21 includes a bottom shell 213 and an upper cover 214 connected to the bottom shell 213, a receiving cavity is defined between the bottom shell 213 and the upper cover 214, and the control board 22, the power supply 23 and the magnet 26 are respectively disposed in the receiving cavity, so as to effectively improve waterproof and dustproof performances. The upper cover 214 is provided with an opening 2140, and the direction key 24 is movably mounted in the opening 2140, so that quick mounting is facilitated. The direction key 24 may have a cross-shaped configuration, and the cross-sectional configuration of the opening 2140 corresponds to the configuration of the direction key 24. The top surfaces of the four protruding end portions of the direction key 24 are respectively provided with anti-slip convex points 241, on one hand, the anti-slip convex points 241 can form indication marks in four directions of up, down, left and right, and even in an environment with low illumination intensity, the vision detection icon can be identified through the anti-slip convex points 241; on the other hand, the anti-skid rubber belt plays a certain anti-skid role. The bottom case 213 is provided with a reference plate 2132 at a position opposite to the eye shielding portion 211, and the reference plate 2132 can be used as a reference object of the center control machine 1, so as to improve the accuracy of distance measurement between the center control machine 1 and the eye shielding device 2.
In one embodiment, the control board 22 has four direction contacts 221 corresponding to the four protruding ends of the direction key 24, respectively, and each direction contact 221 is electrically connected to the control board 22. By pressing the different projecting end portions of the direction keys 24, contact with the corresponding direction contacts 221 can be achieved.
In an embodiment, referring to fig. 10, two limiting baffles 2133 are disposed in the bottom shell 213 at intervals, and the power supply 23 is disposed between the two limiting baffles 2133, so as to limit and fix the power supply 23.
In an embodiment, referring to fig. 10, a plurality of hooks 2131 are disposed at intervals on an inner circumferential surface of the bottom shell 213, a plurality of fastening holes (not shown) are correspondingly disposed on the upper cover 214, and each hook 2131 can be fastened into a corresponding fastening hole, so as to realize a fastening connection between the bottom shell 213 and the upper cover 214, thereby facilitating a detachment between the bottom shell 213 and the upper cover 214, and facilitating a maintenance of the eye shade 2.
In one embodiment, referring to fig. 2, 4 and 5, one end of the door panel 112 is hinged to the housing 111, and the other end of the door panel 112 is mounted with a magnetic attraction part 1121; an electromagnetic lock 118 for magnetically connecting with the magnetic attraction piece 1121 is correspondingly installed on an inner side wall of the accommodation groove 113, and the electromagnetic lock 118 is electrically connected with the main control unit 13. The magnetic element 1121 may be a magnet block. With the structure, when the electromagnetic lock 118 is powered off or charged in the forward direction, the magnetism of the electromagnetic lock 118 is opposite to that of the magnetic attraction piece 1121, and the electromagnetic lock 118 and the magnetic attraction piece 1121 attract each other to achieve automatic closing of the door panel 112; when the electromagnetic lock 118 is charged reversely, the magnetic property of the electromagnetic lock 118 is the same as that of the magnetic attraction piece 1121, and the electromagnetic lock 118 and the magnetic attraction piece 1121 repel each other, so that the door panel 112 is automatically opened and closed, and the operation is convenient and fast.
In one embodiment, an indicator light for displaying the opening and closing state of the door panel 112 is installed on the housing 111. For example, when the door 112 is closed, the indicator light displays a color; when the door panel 112 is open, the indicator light displays another color; the opening and closing state of the door panel 112 is indicated by the change of color.
In an embodiment, referring to fig. 2, 4 and 5, an inductive switch 119 is installed on an inner side wall of the accommodating groove 113, and the inductive switch 119 is electrically connected to the main control unit 13; a touch panel 1122 for touching the touch sensing switch 119 is correspondingly mounted on the door panel 112. With the structure, when the door panel 112 is closed, the touch panel 1122 touches the inductive switch 119, the inductive switch 119 transmits a touch signal to the main control unit 13, the main control unit 13 sends an instruction to the indicator light, and the indicator light is turned on to prompt that the door panel 112 is in a closed state; when the door panel 112 is opened, the touch pad 1122 is separated from the inductive switch 119, the inductive switch 119 transmits a separation signal to the main control unit 13, and the main control unit 13 sends an instruction to the indicator light, and the indicator light is turned on to prompt that the door panel 112 is in an open state. Through the cooperation of the inductive switch 119 and the touch pad 1122, the opening and closing safety and reliability of the door panel 112 can be improved.
In one embodiment, an elastic member (not shown) for elastically pushing the door panel 112 is installed on an inner sidewall of the receiving groove 113. With the structure, when the door panel 112 is closed, the door panel 112 extrudes the elastic element, and the elastic element is compressed and deformed by external force; when the door panel 112 is opened, the elastic member pushes against the door panel 112 under the effect of the resilient force, so that the door opening efficiency and reliability of the door panel 112 can be improved. The elastic member may be a spring plate or a spring, and the like, which is not limited herein.
In one embodiment, the central control machine 1 further includes a sterilizing lamp (not shown) for sterilizing the accommodating groove 113; the sterilizing lamp is installed in the accommodating groove 113 and electrically connected to the main control unit 13. With the structure, the disinfection lamp can disinfect and sterilize the eye shield 2 installed in the accommodating groove 113, and the use safety of the eye shield 2 is improved. When the eye shield 2 is placed in the accommodating groove 113 and the door plate 112 is closed, the sterilizing lamp works after 3min, and automatically closes after 15 min.
In one embodiment, referring to fig. 11, the central control machine 1 further includes a sensor unit 14 for monitoring physical characteristics of the person to be detected; the sensor unit 14 is mounted on the housing 11, and the sensor unit 14 is electrically connected to the main control unit 13. According to the structure, the physical information of the detector can be detected through the sensor unit 14, and on one hand, the physical information can be used for storing the data information of the detector, so that the central control machine 1 can conveniently verify the identity of the detector and repeatedly detect the identity of the detector subsequently, and the comparison and analysis are convenient; on the other hand, the function diversity of the vision detection device can be improved.
In one embodiment, referring to fig. 6 and 11, the sensor unit 14 includes a camera 141 for performing face recognition on the examinee, a body temperature sensor 143 for performing body temperature detection on the examinee, a distance sensor 144 for measuring a distance between the examinee and the display screen 12, and a height sensor 142 for performing height detection on the examinee; the camera 141, the body temperature sensor 143, the distance sensor 144 and the height sensor 142 are respectively mounted on the housing 11, and the camera 141, the body temperature sensor 143, the distance sensor 144 and the height sensor 142 are respectively electrically connected to the main control unit 13. With this configuration, the camera 141 can collect face information of the examiner for data storage and face recognition registration. The body temperature sensor 143 can be used to detect the body temperature of the subject. The distance sensor 144 may be used to measure the distance between the examiner and the display screen 12 and may correct the vision value according to the distance. The height sensor 142 may be used to measure the height of the examiner. Of course, in other embodiments, the sensor unit 14 may be adjusted according to actual needs, and is not limited herein.
The specific steps of testing the body temperature of the examinee through the body temperature sensor 143 are as follows:
1. clicking a button for entering body temperature detection on a home page of the display screen 12, and enabling the central control machine 1 to enter a body temperature detection process;
2. the interface of the central control machine 1 displays the face contour, and adjusts the face into the contour by matching with the text guide; after the camera 141 detects a face and identifies the identity, the distance sensor 144 guides the detector to adjust the distance to 40cm-50cm forwards or backwards according to the distance of the face; then, the body temperature sensor 143 is started to detect and record the body temperature data of the detector;
3. the examiner can perform subsequent operations based on the body temperature detected by the body temperature sensor 143. For example, when the body temperature is normal, the examiner may choose to continue the test or end the test. When the body temperature is higher (higher than 37.3 degrees) or lower (lower than 35 degrees), the examiner can choose to retest, or can choose to continue or end the test, and the body temperature is based on the data measured for the second time. When the test is selected to be continued or retested, the central control machine 1 returns to the second step and restarts.
In one embodiment, referring to fig. 2, the central controller 1 further includes a speaker 15 mounted on the housing 11; the speaker 15 is electrically connected to the main control unit 13. With the structure, the loudspeaker 15 can realize the voice playing function of the central control machine 1 so as to clearly and accurately transmit instructions and related detection information to a detector.
In one embodiment, referring to fig. 2, the central control machine 1 further includes an antenna 16 mounted on the housing 11, and the antenna 16 is electrically connected to the main control unit 13. With the structure, the stability and the reliability of the connection between the central control machine 1 and the eye shielding device 2 can be improved through the antenna 16.
In one embodiment, referring to fig. 2, the central control machine 1 further includes a power switch 17 and a plurality of interfaces 18 respectively mounted on the casing 11. With the structure, the power switch 17 can control the opening and closing of the central control machine 1. The plurality of interfaces 18 may include a network cable interface, a data transmission interface, a USB (Universal Serial Bus) interface, and the like, and may be used for data interaction with an external terminal.
In one embodiment, referring to fig. 2, the central control unit 1 further includes a card reader 19 mounted on the housing 11, and the card reader 19 is electrically connected to the main control unit 13. With this configuration, the card reader 19 can be used to identify the identity information of the examiner. And only after passing the identity authentication, the user can enter the operating system of the central control machine 1 to perform subsequent operation.
The vision detection device that this application embodiment provided is applicable to and establishes the refraction archives for the student of school, and through the mode of independently detecting, reduces medical personnel's work load, improves the whole eyesight of student and detects frequency and independently detect the frequency, in time corrects the treatment to student's eyesight, effectively reduces national teenagers ' near-sighted rate.
The embodiment of the application provides a visual detection device's specific visual detection step as follows:
1. information entry: and uniformly inputting student information by the background of the administrator.
2. And (3) binding the equipment: the administrator swipes the card to enter the system of the central control machine 1, selects a scanning button, and the central control machine 1 scans the Bluetooth equipment; and then selecting a Bluetooth signal corresponding to the ID number of the eye shielding device 2 to realize Bluetooth connection between the central control machine 1 and the eye shielding device 2. After binding is successful, when the Bluetooth device is started next time, the Bluetooth device can automatically carry out connection communication with the Bluetooth device connected last time.
3. Face inputting: the administrator selects the "set" button, selects a person, and enters face information by the camera 141.
4. Taking the eye shielding device 2: (1) the inspector selects a vision detection button on the home page of the central control machine 1 to enter an identity verification process, and the inspector realizes identity verification through face recognition or swiping a card and enters the system of the central control machine 1. The one-card-swiping identification refers to identifying the operation of the magnetic card through the card reader 19; (2) the electromagnetic lock 118 is charged reversely, the electromagnetic lock 118 is separated from the magnetic attraction part 1121, and the door panel 112 is opened.
5. Test point guiding: the display screen 12 of the central control machine 1 displays position guide information, prompts a detector to stand to a designated area through voice, and presses a confirmation key 25 on the eye shielding device 2 for confirmation.
6. Identity authentication and identification: the central control machine 1 performs face acquisition through the camera 141 and confirms the identity of the detector.
7. Preparation before visual detection: (1) the display screen 12 displays the basic information of the examiner, such as name, school number, grade, class and the like; (2) the central control computer 1 prompts by voice that the eye shielding device 2 is required to shield the left eye or the eye shielding device 2 is required to shield the right eye; (3) the central control machine 1 calculates the distance between the detector and the display screen 12 according to the distance sensor 144; (4) and prompting the user to start detection and please keep the state of the eye shielding device 2 by voice, and monitoring the state of the eye shielding device 2 shielding the eyes in real time.
8. And (3) vision detection process: (1) the examiner confirms the opening direction of the visual detection icon E displayed on the display screen 12 through the four direction keys 24 "up", "down", "left" and "right" on the eye shade 2; (2) after the examiner presses the enter key 25, the display 12 switches different vision test icons E; (3) repeating the steps until the minimum visual target which can be identified by the detected eye is detected, and recording the vision value of the eye; (4) the actual vision value is corrected based on the distance between the examiner and the display screen 12 measured by the distance sensor 144. Wherein, the actual vision value is the test vision value + e, and e is a constant. The vision correction chart is as follows:
9. and (3) outputting a test result: the display screen 12 displays the vision data of the person who is detected this time and the curve of the test data of nearly 10 times.
10. And (4) finishing the test: the inspector puts the eye shade 2 into the accommodating groove 113, the electromagnetic lock 118 is charged in the forward direction, the electromagnetic lock 118 is magnetically connected with the magnetic piece 1121, and the door panel 112 is closed; and the central control machine 1 charges the eye shade 2 three minutes later and returns to the first page.
The application provides a vision detection device can realize the training of people's face key point detection model, and its concrete training step is as follows:
101. the method comprises the steps of obtaining a plurality of sample face video streams, wherein one sample face video stream comprises a plurality of video frames of a face, and the sample face video streams are collected when the face is kept in a static state. Specifically, the multiple sample face video streams may be obtained, and the still video streams of faces of different people may be collected in advance, where each of the video streams of each person may include more than dozens of face video frames, where each of the faces may be at different angles, but the face in each of the video streams needs to be kept still.
102. And performing key point prediction on each video frame of each sample face video stream in the plurality of sample face video streams by adopting a first face key point model to obtain a predicted face key point of each video frame. Specifically, the first face keypoint model may be any pre-trained model that can be used for keypoint detection. Generally, in order to build a face keypoint detection model, a large number of face images (including different expressions and poses of multiple persons) marked with feature points are required as training data. The feature points may be marked on the outer contour of the face and the edges of the organs. The keypoints can be identified by using keypoint identifiers, and it should be noted that the order of the respective index points needs to be consistent among the images in the training set. The first face keypoint model in the embodiment of the application may include a face keypoint detection model trained using labeled face keypoint data. The above-mentioned keypoint prediction, i.e. face keypoint detection, positioning or face alignment, refers to that given face image, the positions of key regions of the face, such as eyebrows, eyes, nose, mouth, face contour, etc., are positioned. And performing key point prediction on each video frame by using the first face key point model to obtain a predicted face key point of each video frame, wherein the predicted face key point specifically comprises each key point coordinate.
In one embodiment, the step 102 may include:
using a face detection algorithm to perform face detection on each video frame of each sample face video stream in the plurality of sample face video streams to obtain a face detection frame in each video frame;
and predicting the face key points of the face detection frame in each video frame by adopting the first face key point model to obtain the predicted face key points of each video frame.
Specifically, any commonly used face detection algorithm may be used to perform face detection on each frame in the sample face video stream to obtain a face frame corresponding to each video frame, where the face detection algorithm may use, for example, dlib, MTCNN (Multi-task masked simplified connected Network), ResNet10-SSD, and the like, which is not limited in this embodiment. And then, according to the face detection frames, the trained first face key point model is used for predicting the face key points of each detection frame.
103. And determining a group of face key point coordinates corresponding to each sample face video stream according to the predicted face key point of each video frame of each sample face video stream, wherein the group of face key point coordinates corresponding to one sample face video stream are used for representing the face key point position of each video frame of the sample face video stream. And a group of key point coordinates corresponding to each sample face video stream correspond to a group of face key points, wherein the group of face key points refer to key points which are detected in a key point detection mode and used for representing all positions in the face. It can be understood that, for one sample face video stream, each video frame in the sample face video stream corresponds to the same set of face key point coordinates.
Specifically, for a face of a video stream, a set of face key point coordinates may be determined according to predicted face key points of video frames in the video stream to represent the position of the face key point of each video frame of the sample face video stream, for example, a set of face key point coordinates is calculated according to a preset rule or face key point coordinates of a frame is selected from all frames as a set of face key point coordinates corresponding to the sample face video stream. This step can be understood as labeling each video stream, and for different video frames in one of the video streams, labeling each video frame by the same set of face key point coordinates.
In an optional implementation manner, the determining a set of coordinates of the face key point corresponding to each sample face video stream according to the predicted face key point of each video frame of each sample face video stream includes:
averaging the coordinates of the predicted face key points corresponding to the same key point identifier in all videos of the sample face video stream to obtain an average coordinate value corresponding to each key point identifier in all the videos;
and determining an average coordinate value corresponding to each key point identifier in all the videos as a group of face key point coordinates corresponding to the sample face video stream to obtain a group of face key point coordinates corresponding to each sample face video stream.
The method shows that for a sample face video stream, the average value of the face key point coordinates of all video frames in each video stream can be obtained and used as the face key point label of each frame of the video stream. It can be understood that, if the key points represented by the same key point identifier in the face image are key points at the same face position, the predicted face key point coordinates corresponding to the same key point identifier in all the videos may be averaged to obtain an average coordinate value corresponding to each key point identifier in all the videos, and the obtained average coordinate value corresponding to each key point identifier is a group of face key point coordinates corresponding to the sample face video stream. By processing each sample face video stream through the steps, a group of face key point coordinates corresponding to each sample face video stream can be obtained.
By using the trained face key point model to predict a video stream with a static face and using the face key point mean coordinates as the label of each frame in the video stream, each frame in the video stream can have the same key point and each key point of different people has consistency.
In an optional implementation manner, the determining, according to the predicted face keypoint of each video frame of each sample face video stream, a face keypoint coordinate corresponding to each sample face video stream may include:
taking an intermediate value from predicted face key point coordinates corresponding to the same key point identifier in all videos of the sample face video stream to obtain an intermediate coordinate value corresponding to each key point identifier in all videos;
and determining the middle coordinate value corresponding to each key point identifier in all the videos as a group of face key point coordinates corresponding to the sample face video stream to obtain a group of face key point coordinates corresponding to each sample face video stream.
The middle coordinate value corresponding to each key point identifier in all the videos refers to selecting key point coordinates with proper size from all key points with the same key point identifier, analyzing the aggregation degree of the key point coordinates with the same identifier, and selecting the key point coordinate in the middle. Or respectively taking the median values of the abscissa and the ordinate of all the key points with the same key point identification to obtain the middle coordinate value of the key point corresponding to each key point identification, and taking the middle coordinate value as a group of face key point coordinates corresponding to the sample face video stream. By processing each sample face video stream through the steps, a group of face key point coordinates corresponding to each sample face video stream can be obtained. Optionally, a group of face key point coordinates corresponding to each sample face video stream may also be determined in other manners, which is not limited in this embodiment of the application.
104. And training the first face key point model according to the sample face video streams and the face key point coordinates corresponding to each sample face video stream to obtain a second face key point model.
After a group of face key point coordinates corresponding to each sample face video stream is determined, labeled video stream data is obtained, and the labeled video stream data can be used as a training sample to train a model. And retraining the first face key point model by using the marked sample face video stream to obtain a model for predicting the non-jitter face key points when the face is still.
In an alternative embodiment, before step 102, the method further includes:
acquiring sample face data, wherein the sample face data comprises a plurality of face images of a plurality of figures, the face images are provided with corresponding face key point marks, and the plurality of face images of each figure in the plurality of figures comprise faces with different postures;
and performing key point model training by using the sample face data to obtain the first face key point model.
Specifically, as described above, the first face keypoint model may be trained by using a face image labeled with keypoint information as a sample. And performing key point model training by using the labeled sample face data of different face postures to obtain the first face key point model.
Further optionally, the step 104 may include: and training the first face key point model according to the sample face video streams, the face key point coordinates corresponding to each sample face video stream and the sample face data to obtain the second face key point model.
In the embodiment of the present application, when the first face keypoint model is retrained, artificially labeled face keypoint data may also be added, that is, in addition to the labeled sample face video stream obtained in the foregoing step, the sample face data (sample data used for training to obtain the first face keypoint model) obtained by partially or completely labeling the face image may also be included.
105. The method comprises the steps of obtaining a face video stream, wherein the face video stream comprises a plurality of video frames of a face, and the face video stream is collected when the face is kept in a static state. Specifically, the face key point detection device may acquire a video including a face through the camera 141, that is, acquire the face video stream, where the face video stream includes a plurality of video frames of a face. It should be noted that the face video stream is acquired while the face remains still.
106. And performing key point prediction on a plurality of video frames in the face video stream by adopting a second face key point model to obtain face key point coordinates corresponding to the face video stream, and taking the face key point coordinates corresponding to the face video stream as the face key point coordinates of each video frame in the face video stream.
Due to the fact that the labeling data of the face static video stream are adopted for training, the trained second face key point model conducts key point prediction on the face static video stream, and the problem of key point shaking in the scene is solved. The trained second face key point model can predict key points corresponding to the face video stream, namely a group of face key point coordinates corresponding to the face video stream can be obtained and used as the face key point coordinates of each video frame in the face video stream, and the stability of the predicted key points can be kept.
The training method for the face key point detection model in the embodiment of the application can obtain the model with better jitter removal effect, and jitter removal can be established after face key point prediction, so that the problems that a large amount of video stream data are difficult to label and difficult to accurately label are solved. The method can be applied to various human face key point detection scenes, such as human face recognition, various human face image processing and the like, is not limited, can reduce the key point shaking problem, improves the operation accuracy processed according to the key points, and enables the processing effect to be better.
Generally speaking, the method of the embodiment of the application mainly includes the steps of performing key point model training by using labeled human face key point data of different people in different postures to obtain a pre-training model 1, performing key point prediction on a video stream image by using the pre-training model 1 to obtain key point labels of the video stream image, obtaining key point labels of the video stream image, and performing fine adjustment on the pre-training model 1 based on the key point labels of the video stream to obtain a final key point model 2.
In the embodiment of the application, a plurality of sample face video streams are obtained, one sample face video stream comprises a plurality of video frames of a face, the sample face video stream is collected when the face is kept in a static state, a first face key point model is adopted to carry out key point prediction on each video frame of each sample face video stream in the plurality of sample face video streams to obtain a predicted face key point of each video frame, the face key point coordinate corresponding to each sample face video stream is determined according to the predicted face key point of each video frame of each sample face video stream, the face key point coordinate corresponding to one sample face video stream is used for representing the face key point position of each video frame of the sample face video streams, and according to the sample face video streams and the face key point coordinate corresponding to each sample face video stream, training the first face key point model to obtain a second face key point model; predicting a sample face video stream by using a trained first face key point model to obtain key point labels of each frame in the video stream, and determining the key point label of one video stream according to the obtained key point label of each frame to ensure that each frame of one video stream has the same key point and each key point of different people has consistency; the model is trained by the re-labeled video stream of the face in a static state, so that the trained model can learn the consistency of key points of each frame of face image in the video stream, the stability of predicting the key points can be kept in the video stream for detecting the static face, and the jitter is eliminated. The method does not need to depend on a large amount of manual labeling sample data, reduces labor cost, does not need to remove jitter by combining key points of front and back frames in the video stream in some methods, and is simpler and more effective in processing.
Based on the above description of the embodiment of the face keypoint detection model, the main control unit 13 provided in the embodiment of the present application may include:
an obtaining module 131, configured to obtain a plurality of sample face video streams, where a sample face video stream includes a plurality of video frames of a face, and the sample face video stream is collected when the face remains in a static state;
a key point prediction module 132, configured to perform key point prediction on each video frame of each sample face video stream in the multiple sample face video streams by using a first face key point model, so as to obtain a predicted face key point of each video frame;
an annotation module 133, configured to determine a set of face key point coordinates corresponding to each sample face video stream according to a predicted face key point of each video frame of each sample face video stream, where the set of face key point coordinates corresponding to one sample face video stream is used to represent a face key point position of each video frame of the sample face video stream;
and the training module 134 is configured to train the first face keypoint model according to the sample face video streams and the face keypoint coordinates corresponding to each sample face video stream, so as to obtain a second face keypoint model.
Optionally, the labeling module 133 is specifically configured to:
averaging the coordinates of the predicted face key points corresponding to the same key point identifier in all videos of the sample face video stream to obtain an average coordinate value corresponding to each key point identifier in all the videos;
and determining an average coordinate value corresponding to each key point identifier in all the videos as a group of face key point coordinates corresponding to the sample face video stream to obtain a group of face key point coordinates corresponding to each sample face video stream.
Optionally, the labeling module 133 is further specifically configured to:
taking an intermediate value from predicted face key point coordinates corresponding to the same key point identifier in all videos of the sample face video stream to obtain an intermediate coordinate value corresponding to each key point identifier in all videos;
and determining the middle coordinate value corresponding to each key point identifier in all the videos as a group of face key point coordinates corresponding to the sample face video stream to obtain a group of face key point coordinates corresponding to each sample face video stream.
Optionally, the keypoint prediction module 132 is specifically configured to:
using a face detection algorithm to perform face detection on each video frame of each sample face video stream in the plurality of sample face video streams to obtain a face detection frame in each video frame;
and predicting the face key points of the face detection frame in each video frame by adopting the first face key point model to obtain the predicted face key points of each video frame.
Optionally, the obtaining module 131 is further configured to obtain sample face data before the keypoint prediction module 132 performs keypoint prediction on each video frame of each sample face video stream in the multiple sample face video streams by using a first face keypoint model, where the sample face data includes multiple face images of multiple people, the face images have corresponding face keypoint marks, and the multiple face images of each of the multiple people include faces in different poses;
the training module 134 is further configured to perform a key point model training using the sample face data to obtain the first face key point model.
Optionally, the training module 134 is specifically configured to:
and training the first face key point model according to the sample face video streams, the face key point coordinates corresponding to each sample face video stream and the sample face data to obtain the second face key point model.
Optionally, the main control unit 13 further includes a processing module 135;
the obtaining module 131 is further configured to obtain a face video stream after the second face keypoint model is obtained, where the face video stream includes a plurality of video frames of a face, and the face video stream is collected when the face remains in a static state;
the processing module 135 is configured to perform key point prediction on multiple video frames in the face video stream by using the second face key point model, obtain face key point coordinates corresponding to the face video stream, and use the face key point coordinates corresponding to the face video stream as the face key point coordinates of each video frame in the face video stream.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. Well accuse machine, its characterized in that includes:
the casing comprises a casing body and a door plate, one end of the door plate is hinged to the casing body, a containing groove for containing an external object is formed in the casing body, and the door plate covers the containing groove; the other end of the door plate is provided with a magnetic attraction piece, and an electromagnetic lock which is in magnetic attraction connection with the magnetic attraction piece is correspondingly arranged on the inner side wall of the accommodating groove;
the display screen is arranged on the shell and used for displaying the eyesight detection icons;
the sensor unit is arranged in the shell and used for receiving signals sent by a detector when the detector identifies the vision detection mapping mark;
the main control unit is arranged in the shell and used for controlling the display screen to switch the vision detection icon, receiving a signal of the sensor unit, comparing the signal with the direction of the vision detection icon to obtain a vision detection result and storing the vision detection result;
the electromagnetic lock, the display screen and the sensor unit are respectively electrically connected with the main control unit.
2. The central control machine of claim 1, wherein: an inductive switch is arranged on the inner side wall of the accommodating groove and is electrically connected with the main control unit; and the door panel is correspondingly provided with a touch panel for touching the inductive switch.
3. The central control machine of claim 1, wherein: and an elastic part used for elastically pushing the door panel is arranged on the inner side wall of the accommodating groove.
4. The central control machine of claim 1, wherein: the central control machine also comprises a disinfection lamp for sterilizing the accommodating groove; the disinfection lamp is arranged in the containing groove and electrically connected with the main control unit.
5. The central control machine of claim 1, wherein: the accommodating groove comprises a first clamping groove, a second clamping groove and a third clamping groove, wherein the second clamping groove is arranged at an interval with the first clamping groove, and the third clamping groove is used for connecting the first clamping groove with the second clamping groove; the first clamping groove is used for allowing one end of the external object to extend into the first clamping groove, the second clamping groove is used for allowing the other end of the external object to extend into the second clamping groove, and the third clamping groove is used for corresponding arrangement with the middle position of the external object.
6. The central control machine according to any one of claims 1 to 5, characterized in that: the central control machine also comprises a card reader for identifying the identity information of the detector; the card reader is arranged on the shell and electrically connected with the main control unit.
7. The central control machine according to any one of claims 1 to 5, characterized in that: the central control machine also comprises an in-place detector for detecting whether an external object is accommodated in the accommodating groove; the in-place detector is mounted on the shell and electrically connected with the main control unit.
8. The central control machine according to any one of claims 1 to 5, characterized in that: the central control machine also comprises a camera for carrying out face recognition on the detector; the camera is installed on the casing, the camera with main control unit electric connection.
9. The central control machine according to any one of claims 1 to 5, characterized in that: the central control machine also comprises a body temperature sensor for detecting the body temperature of the examinee, a distance sensor for measuring the distance between the examinee and the display screen and a height sensor for detecting the height of the examinee; the body temperature sensor, the distance sensor and the height sensor are respectively installed on the shell, and the body temperature sensor, the distance sensor and the height sensor are respectively electrically connected with the main control unit.
10. Eyesight detection device, its characterized in that: comprising a central control machine according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011190552.5A CN112205961A (en) | 2020-10-30 | 2020-10-30 | Central control machine and vision detection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011190552.5A CN112205961A (en) | 2020-10-30 | 2020-10-30 | Central control machine and vision detection device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112205961A true CN112205961A (en) | 2021-01-12 |
Family
ID=74057678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011190552.5A Pending CN112205961A (en) | 2020-10-30 | 2020-10-30 | Central control machine and vision detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112205961A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN206968799U (en) * | 2017-06-22 | 2018-02-06 | 赵泉鑫 | A kind of express delivery car compartment |
| CN108882843A (en) * | 2016-03-23 | 2018-11-23 | 维尤姆技术有限公司 | Eyesight exam method, vision tester and store the eyesight exam method program download server |
| CN110309706A (en) * | 2019-05-06 | 2019-10-08 | 深圳市华付信息技术有限公司 | Face critical point detection method, apparatus, computer equipment and storage medium |
| CN110353622A (en) * | 2018-10-16 | 2019-10-22 | 武汉交通职业学院 | A kind of vision testing method and eyesight testing apparatus |
| CN110584589A (en) * | 2019-09-30 | 2019-12-20 | 深圳和而泰家居在线网络科技有限公司 | Vision detection device |
| CN111281361A (en) * | 2020-03-09 | 2020-06-16 | 康瑞健康管理(杭州)有限公司 | Student health monitoring system based on big data |
| CN111345794A (en) * | 2020-03-18 | 2020-06-30 | 深圳澳蓝智康爱特科技发展有限公司 | Intelligent health examination integrated machine |
| CN211298940U (en) * | 2019-12-03 | 2020-08-21 | 程文波 | Domestic intelligent wardrobe based on image recognition |
-
2020
- 2020-10-30 CN CN202011190552.5A patent/CN112205961A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108882843A (en) * | 2016-03-23 | 2018-11-23 | 维尤姆技术有限公司 | Eyesight exam method, vision tester and store the eyesight exam method program download server |
| CN206968799U (en) * | 2017-06-22 | 2018-02-06 | 赵泉鑫 | A kind of express delivery car compartment |
| CN110353622A (en) * | 2018-10-16 | 2019-10-22 | 武汉交通职业学院 | A kind of vision testing method and eyesight testing apparatus |
| CN110309706A (en) * | 2019-05-06 | 2019-10-08 | 深圳市华付信息技术有限公司 | Face critical point detection method, apparatus, computer equipment and storage medium |
| CN110584589A (en) * | 2019-09-30 | 2019-12-20 | 深圳和而泰家居在线网络科技有限公司 | Vision detection device |
| CN211298940U (en) * | 2019-12-03 | 2020-08-21 | 程文波 | Domestic intelligent wardrobe based on image recognition |
| CN111281361A (en) * | 2020-03-09 | 2020-06-16 | 康瑞健康管理(杭州)有限公司 | Student health monitoring system based on big data |
| CN111345794A (en) * | 2020-03-18 | 2020-06-30 | 深圳澳蓝智康爱特科技发展有限公司 | Intelligent health examination integrated machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3275163B1 (en) | Expanding capabilities of mobile computing devices | |
| US20210264210A1 (en) | Learning data collection device, learning data collection system, and learning data collection method | |
| CN103839054A (en) | Multi-functional mobile intelligent terminal sensor supporting iris recognition | |
| CN110353622A (en) | A kind of vision testing method and eyesight testing apparatus | |
| EP3434172B1 (en) | Eyesight examination method, eyesight examination device, and downloader server for storing program of eyesight examination method | |
| CN109300528B (en) | Cognitive rehabilitation training system and method | |
| CN111857355A (en) | Reading state monitoring feedback system | |
| KR102268759B1 (en) | The device using skin condition measuring and care, and the system comprising thereof | |
| CN213940690U (en) | Vision detection device | |
| CN109460743A (en) | A kind of key motion recognition system | |
| CN112205961A (en) | Central control machine and vision detection device | |
| CN109998487A (en) | Monitoring of respiration method, apparatus, equipment and medium for image scan | |
| CN112190226A (en) | Vision detection device | |
| CN213802426U (en) | Call control system and intelligent car | |
| CN212066690U (en) | Skin detector | |
| CN111210438A (en) | Mirror | |
| CN209103322U (en) | A kind of key action recognition device | |
| CN213458082U (en) | Iris collecting and identifying device | |
| CN208709899U (en) | A kind of medical intelligent headring | |
| CN114359953A (en) | Method and device for indicating auscultation position | |
| CN110584589A (en) | Vision detection device | |
| CN215937320U (en) | Intelligent vision detection device | |
| CN213458083U (en) | Controller and iris acquisition and recognition device | |
| CN213458081U (en) | Controller and iris acquisition and recognition device | |
| CN111839452A (en) | Vision detection system |
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 |