CN111967550B - Non-contact temperature detector based on artificial intelligence and detection method thereof - Google Patents
Non-contact temperature detector based on artificial intelligence and detection method thereof Download PDFInfo
- Publication number
- CN111967550B CN111967550B CN202010749287.3A CN202010749287A CN111967550B CN 111967550 B CN111967550 B CN 111967550B CN 202010749287 A CN202010749287 A CN 202010749287A CN 111967550 B CN111967550 B CN 111967550B
- Authority
- CN
- China
- Prior art keywords
- gesture
- image
- skin color
- hand
- body temperature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 34
- 238000001514 detection method Methods 0.000 title claims abstract description 28
- 230000036760 body temperature Effects 0.000 claims abstract description 88
- 238000004659 sterilization and disinfection Methods 0.000 claims description 22
- 238000000034 method Methods 0.000 claims description 18
- 239000013589 supplement Substances 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 230000000249 desinfective effect Effects 0.000 claims description 8
- 230000001954 sterilising effect Effects 0.000 claims description 8
- 230000001502 supplementing effect Effects 0.000 claims description 6
- 230000007547 defect Effects 0.000 description 7
- 238000009529 body temperature measurement Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000005259 measurement Methods 0.000 description 5
- 206010011409 Cross infection Diseases 0.000 description 3
- 206010029803 Nosocomial infection Diseases 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000007872 degassing Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001815 facial effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 240000007651 Rubus glaucus Species 0.000 description 1
- 235000011034 Rubus glaucus Nutrition 0.000 description 1
- 235000009122 Rubus idaeus Nutrition 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
- G01J5/0025—Living bodies
-
- 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
- G06V40/107—Static hand or arm
-
- 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)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Engineering & Computer Science (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to a non-contact temperature detector based on artificial intelligence and a detection method thereof, wherein the non-contact temperature detector comprises a shell, a microcomputer arranged in the shell, a hand groove arranged on the front side of the shell, a display device and a human face image acquisition device; a gesture image acquisition device and an infrared body temperature sensor are arranged in the hand groove; the microcomputer is used for identifying the face image to obtain the face complexion characteristic and the identity information; recognizing the gesture image to obtain gesture skin color characteristics and gesture positioning information; judging whether the face skin color characteristic is consistent with the gesture skin color characteristic, and acquiring body temperature data corresponding to the identity information by using an infrared body temperature sensor based on gesture positioning information when the face skin color characteristic is consistent with the gesture skin color characteristic; the display device is used for displaying the body temperature data. The invention is based on artificial intelligence, detects the body temperature data matched with the human face, the gesture and the identity information of the detected person in real time, does not need the contact between the detected person and the detected person, and has high reliability of the measured body temperature data.
Description
Technical Field
The invention relates to the technical field of artificial intelligence and body temperature detection, in particular to a non-contact temperature detector based on artificial intelligence and a detection method thereof.
Background
In many times, the body temperature needs to be measured so as to help grasp the health condition of the human body, and a body temperature detector is a common instrument for detecting the body temperature of the human body.
For a traditional body temperature detector, a detection person usually needs to hold the body temperature detector to detect a detected person, and the detection person usually needs to be in close contact with the detected person to obtain body temperature data; because the body temperature detector is operated manually, different detection personnel measure different positions of the human body, so that the body temperature detected by the same detection personnel is different, and the reliability of the body temperature is lower.
In order to overcome the defects of a contact type body temperature detector, a non-contact type infrared body temperature detector is also available in the market, and the problem of low measurement reliability cannot be avoided because the body temperature detector generally needs manual operation.
Therefore, there is a need for a non-contact temperature measuring device that does not require manual operation and can effectively improve the reliability of body temperature measurement.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a non-contact temperature detector based on artificial intelligence and a detection method thereof, aiming at the defects of the prior art, so that the contact between a detector and a detected person is not needed, and the reliability of measured body temperature data is high.
The technical scheme for solving the technical problems is as follows:
a non-contact temperature detector based on artificial intelligence comprises a shell, a microcomputer arranged in the shell, a hand groove arranged on the front side of the shell, a display device arranged on the front side of the shell and a human face image acquisition device;
a gesture image acquisition device and an infrared body temperature sensor are arranged in the hand groove;
the microcomputer is respectively electrically connected with the display device, the human face image acquisition device, the gesture image acquisition device and the infrared body temperature sensor;
the face image acquisition device is used for acquiring a face image of a detected person;
the gesture image acquisition device is used for acquiring a gesture image of the detected person;
the microcomputer is used for:
identifying the face image to obtain face complexion characteristics and identity information;
recognizing the gesture image to obtain gesture skin color characteristics and gesture positioning information;
judging whether the face skin color feature is consistent with the gesture skin color feature, and acquiring body temperature data corresponding to the identity information by using the infrared body temperature sensor based on the gesture positioning information when the face skin color feature is consistent with the gesture skin color feature;
and the display device is used for displaying the body temperature data.
According to another aspect of the present invention, there is provided a non-contact temperature detecting method based on artificial intelligence, wherein the non-contact temperature detecting method using the non-contact temperature detector based on artificial intelligence comprises the following steps:
step 1: acquiring a face image of a detected person, and identifying the face image to obtain face complexion characteristics and identity information;
and 2, step: acquiring a gesture image of the detected person, and identifying the gesture image to obtain a gesture skin color characteristic and gesture positioning information;
and step 3: judging whether the face skin color feature is consistent with the gesture skin color feature, if so, acquiring and displaying body temperature data corresponding to the identity information according to the gesture positioning information; if not, returning to the step 1.
The non-contact temperature detector based on artificial intelligence and the detection method thereof have the beneficial effects that: the human face image of the person to be detected is obtained through the human face image acquisition device, after the identification of the person to be detected is carried out by the microcomputer, on one hand, the identity information of the person to be detected can be identified, the detected body temperature data can be conveniently matched with the person to be detected of the identity information subsequently, the binding of the body temperature data and the person is realized, on the other hand, the human face skin color characteristic of the face of the person to be detected can be identified, the subsequent matching with the hand back skin color in the gesture is convenient, and due to the fact that the human face skin color of the same person is basically consistent with the hand back skin color, the gesture image and the human face image can be further confirmed to be the same person to be detected through the human face skin color characteristic, and the matching of the body temperature data, the human face and the gesture is ensured; the gesture image of the person to be detected is acquired through the gesture image acquisition device, the gesture skin color feature and the gesture positioning information can be respectively identified after the identification of the microcomputer, the gesture skin color feature is used for being matched with the face skin color feature, the gesture and the face are ensured to be the same person to be detected, the gesture positioning information is convenient for an infrared body temperature sensor to acquire the body temperature of the same detection position every time body temperature data are detected, for example, the palm temperature of the person to be detected is acquired every time body temperature data are measured; finally, body temperature data corresponding to the identity information is displayed through a display device, and the body temperature completely matched with the tested person can be mastered in real time;
the non-contact temperature detector and the detection method thereof can detect the body temperature data matched with the human face, the gesture and the identity information of the detected person in three-in-one mode in real time without manual operation based on human face recognition, gesture recognition and other artificial intelligence technologies, do not need to arrange that the measuring person is in direct or indirect contact with the detected person, really realize non-contact measurement, ensure that the same position is detected when each detected person is detected, and greatly improve the reliability of body temperature measurement.
Drawings
Fig. 1 is a schematic front view of a non-contact temperature detector based on artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an internal structure of a hand tank according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of an electrical connection structure of a non-contact temperature detector based on artificial intelligence according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a backside structure of a non-contact temperature detector based on artificial intelligence according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart illustrating a non-contact temperature detection method based on artificial intelligence according to a second embodiment of the present invention;
fig. 6 is a schematic view of a complete process of a non-contact temperature detection method based on artificial intelligence in the second embodiment of the present invention.
In the drawings, the components represented by the respective reference numerals are listed below:
100. the casing, 200, hand groove, 1, display device, 2, face image acquisition device, 3, gesture image acquisition device, 4, infrared body temperature sensor, 5, human sensor, 6, degassing unit, 7, voice prompt, 8, fan, 31, first camera, 32, second camera, 33, first light filling lamp, 34, second light filling lamp.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
The present invention will be described with reference to the accompanying drawings.
In a first embodiment, as shown in fig. 1 to 3, a non-contact temperature detector based on artificial intelligence includes a casing 100, a microcomputer disposed inside the casing 100, a hand slot 200 disposed at the front side of the casing 100, a display device 1 disposed at the front side of the casing 100, and a human face image acquisition device 2;
a gesture image acquisition device 3 and an infrared body temperature sensor 4 are arranged in the hand groove 200;
the microcomputer is respectively and electrically connected with the display device 1, the face image acquisition device 2, the gesture image acquisition device 3 and the infrared body temperature sensor 4;
the face image acquisition device 2 is used for acquiring a face image of a person to be detected;
the gesture image acquisition device 3 is used for acquiring a gesture image of the detected person;
the microcomputer is used for:
identifying the face image to obtain face complexion characteristics and identity information;
recognizing the gesture image to obtain gesture skin color characteristics and gesture positioning information;
judging whether the face skin color feature is consistent with the gesture skin color feature, and when the face skin color feature is consistent with the gesture skin color feature, acquiring body temperature data corresponding to the identity information by using the infrared body temperature sensor 4 based on the gesture positioning information;
the display device 1 is used for displaying the body temperature data.
The human face image of the detected person is obtained through the human face image acquisition device, after the identification of the microcomputer, on one hand, the identity information of the detected person can be identified, the detected body temperature data can be conveniently matched with the detected person of the identity information subsequently, the binding of the body temperature data and the person is realized, on the other hand, the human face skin color characteristic of the face of the detected person can be identified, the subsequent matching with the hand back skin color in the gesture is convenient, and as the human face skin color of the same person is basically consistent with the hand back skin color, the matching of the body temperature data, the human face and the gesture can be ensured by further confirming that the gesture image and the human face image are the same detected person through the human face skin color characteristic; the gesture image of the person to be detected is acquired through the gesture image acquisition device, the gesture skin color feature and the gesture positioning information can be respectively identified after the identification of the microcomputer, the gesture skin color feature is used for being matched with the face skin color feature, the gesture and the face are ensured to be the same person to be detected, the gesture positioning information is convenient for an infrared body temperature sensor to acquire the body temperature of the same detection position every time body temperature data are detected, for example, the palm temperature of the person to be detected is acquired every time body temperature data are measured; finally, body temperature data corresponding to the identity information is displayed through a display device, and the body temperature completely matched with the tested person can be mastered in real time;
the non-contact temperature detector and the detection method thereof of the embodiment are based on artificial intelligence technologies such as face recognition and gesture recognition, can detect the body temperature data matched with the face, the gesture and the identity information of the detected person in three-in-one mode in real time without manual operation, do not need to arrange the direct or indirect contact of the measuring person and the detected person, really achieve non-contact measurement, can ensure that the same position is detected when each detected person is detected, and greatly improve the reliability of body temperature measurement.
Preferably, as shown in fig. 2 and 3, a human body sensor 5 is further disposed in the hand groove 200, and the human body sensor 5 is electrically connected to the microcomputer;
the microcomputer is further configured to:
after the face skin color feature and the identity information are obtained, displaying prompt information for placing standard gestures in the hand slot 200 by using the display device 1;
the human body sensor 5 is used for detecting whether the standard gesture is placed in the hand slot 200;
the gesture image acquisition device 3 is specifically configured to acquire the gesture image when the human body sensor 5 detects that the standard gesture is placed in the hand slot 200.
Because every surveyed personnel when placing the gesture in the hand groove, the gesture can be different, consequently, when facial image acquisition device gathers the face image, and after microcomputer discernment face complexion characteristic and identity information, the tip message of placing the standard gesture is shown through display device, be convenient for remind surveyed personnel all to place the gesture according to same standard gesture, after the user places the gesture according to the suggestion, can detect whether the gesture has been placed in the hand groove on the one hand through human sensor, ensure that gesture image acquisition can normally go on, on the other hand can ensure that the gesture that surveyed personnel placed is the standard gesture, be convenient for follow-up effectively discern the gesture image, obtain more accurate gesture complexion characteristic and gesture locating information, and then ensure to obtain the body temperature data that the reliability is higher and with surveyed personnel assorted.
Preferably, the standard gesture is specifically that the back of the hand is tiled and the direction is upward, or the palm of the hand is tiled and the direction is downward;
as shown in fig. 2 and 3, the gesture image capturing device 3 includes a first camera 31 and a second camera 32, the first camera 31 is disposed on the upper side inside the hand slot 200, the second camera 32 is disposed on the lower side inside the hand slot 200, and the infrared body temperature sensor 4 is disposed at the center of the lower side inside the hand slot 200; the first camera 32 and the second camera 32 are respectively electrically connected with the microcomputer;
the first camera 31 is configured to acquire a hand back image in the gesture image;
the second camera 32 is configured to acquire a palm image in the gesture image;
the microcomputer is further specifically configured to:
identifying the hand back image to obtain the gesture skin color feature;
judging whether the face skin color feature is consistent with the gesture skin color feature, when the face skin color feature is consistent with the gesture skin color feature, identifying the palm image to obtain the gesture positioning information, and acquiring the body temperature data corresponding to the identity information by using the infrared body temperature sensor 4 based on the gesture positioning information;
the gesture positioning information is specifically palm positioning information.
The gesture comprises a hand back and a palm, and the hand back and the palm are two planes with different orientations respectively, so that a hand back image is collected through the first camera, the hand back image is convenient to identify, the skin color feature of the hand back is obtained, namely the gesture skin color feature, and whether the face and the gesture placed in the hand groove are the same person to be detected can be accurately judged through the comparison of the skin color feature of the hand back and the face skin color feature, so that the mutual matching of the gesture, the face and the identity information is ensured; the palm image is collected through the second camera, so that the palm in the palm image can be conveniently positioned to obtain palm positioning information, the infrared body temperature sensor can conveniently collect body temperature data at a position corresponding to the palm positioning information, the body temperature at the same position can be measured during each measurement, and the reliability of the body temperature data is greatly improved; wherein, the image quality of collection can be further effectively improved to the position that sets up of above-mentioned first camera and second camera, and the accuracy of body temperature data can further effectively be improved to infrared body temperature sensor's the position that sets up.
Specifically, the microcomputer of the present embodiment is implemented by using the recognition and analysis program built in the microcomputer when recognizing the face image, the palm image, and the back image.
The process of identifying the face image and obtaining the identity information is as follows:
1. calling an OpenCV function to detect a face image and identifying identity characteristics;
2. matching the identity characteristics with the large database, and searching out identity information which is registered in the large database and is matched with the tested person;
the algorithm flow adopted for identifying the face image and obtaining the face complexion characteristics is as follows:
1. constructing a cascade strong classifier model; setting parameters such as the number of layers, the detection rate, the false detection rate and the like of the multi-layer cascade strong classifier;
2. training a cascade strong classifier model by using an AdaBoost iteration method to obtain a face skin color space model;
3. detecting and segmenting the skin color of the face image by using an HSV color space model;
4. and detecting the skin color detection and the segmented face image by using a face skin color space model, detecting a reliable face region, marking the pixels with the pixel values meeting the threshold condition in the face region as skin color pixels, and marking the pixels without meeting the threshold condition as non-skin color pixels. Wherein the threshold condition is obtained from a priori knowledge. The face region marked as the skin color pixel and the corresponding skin color pixel are the face skin color feature.
The algorithm for recognizing the hand back image and obtaining the gesture skin color feature is similar to the algorithm of the human face skin color feature, and is not repeated here.
The algorithm flow adopted for identifying the palm image and obtaining the gesture positioning information (namely the palm positioning information) is as follows:
1. preprocessing the palm image by adopting processing methods such as image smoothing, denoising, graying, binarization, morphology and the like;
2. detecting the preprocessed palm image by adopting a three-frame interframe difference method and an 8-neighborhood method respectively, and detecting the maximum outline of the motion gesture in the image, namely the palm outline image with clear and non-overlapped edge outlines;
3. performing convex hull and convex defect detection on the palm contour image with clear edge contour based on a gesture convex hull and convex defect detection method of Graham scanning, and judging an inter-finger defect point and a fingertip according to a convex defect depth setting threshold;
4. and finding a point set of the minimum circumcircle of the groove points among the fingers from the detected finger defect points and the detected finger tips, realizing dynamic palm real-time positioning by adopting a real-time palm detection method based on the minimum circumcircle of the groove points among the fingers, and calculating specific palm positioning.
Preferably, as shown in fig. 2 and 3, the gesture image capturing device 3 further includes a first supplementary lighting lamp 33 and a second supplementary lighting lamp 34, the first supplementary lighting lamp 33 is disposed on the upper side inside the hand slot 200 near the first camera 31, and the second supplementary lighting lamp 34 is disposed on the lower side inside the hand slot 200 near the second camera 32; the first light supplement lamp 33 and the second light supplement lamp 34 are electrically connected to the microcomputer respectively;
the first supplementary lighting lamp 33 is used for supplementing lighting for the process of acquiring the hand back image by the first camera 31;
and the second light supplement lamp 34 is used for supplementing light for the process of acquiring the palm image by the second camera 32.
Through the first light supplement lamp, the light brightness in the process can be supplemented when the light for collecting the hand back image is poor, so that the quality of the hand back image is effectively improved, the subsequent identification and analysis of the hand back image are facilitated, and the identification accuracy is improved; similarly, through the second light filling lamp, the quality of the palm image can be effectively improved, the subsequent identification and analysis of the palm image are facilitated, and the identification accuracy is improved.
Preferably, as shown in fig. 2 and 3, a disinfecting device 6 is further arranged in the hand tank 200, and the disinfecting device 6 is arranged on the inner wall of the hand tank 200; the sterilizing device 6 is electrically connected with the microcomputer;
the disinfecting device 6 is used for disinfecting the inner space of the hand tank 200 before and/or after the gesture image acquisition device 3 acquires the gesture image.
In a special period (such as a severe epidemic period), if the same body temperature detector is adopted to detect the body temperatures of different detected persons, cross infection is easily caused, and if the detected persons are arranged to disinfect the detector, the risk of infection of the detected persons is easily increased; if each person to be tested is assigned a body temperature detector, the cost is too high; through the degassing unit that sets up in this embodiment in hand groove inside, can disinfect to the hand groove before acquireing the gesture image (promptly by survey personnel before placing the gesture), and/or, disinfect to the hand groove (this moment still including placing the gesture in hand groove inside) after acquireing the gesture image (promptly by survey personnel after placing the gesture), can effectively avoid cross infection, still need not additionally to arrange personnel to disinfect the body temperature detector simultaneously, possess the function of automatically cleaning and self-sterilizer, really accomplish unmanned operation, the cost is lower. The disinfection is performed before the gesture image is acquired or after the gesture image is acquired, the disinfection can be set according to actual conditions, and disinfection steps can be set before and after the gesture image is acquired.
Specifically, the present embodiment sets a first sterilization for a duration of 5s before the gesture image is acquired, and sets a second sterilization for a duration of 7s after the gesture image is acquired.
Specifically, the disinfecting device of the embodiment is further used for disinfecting the inner space of the hand groove after the body temperature data is displayed.
The third disinfection process is adopted, namely after the whole body temperature measurement process is finished, the hand groove is disinfected again, the whole body temperature detector is further disinfected, cross infection is further avoided, and the disinfection device is particularly suitable for special environments such as major epidemic situations.
Specifically, in this embodiment, after the display displays the body temperature data, the disinfection device is turned on to perform the third disinfection for a duration of 7 s.
Preferably, as shown in fig. 2, the sterilizing device 6 includes a plurality of ultraviolet sterilizing lamps uniformly distributed on the inner wall of the hand tank 200;
each ultraviolet disinfection lamp is respectively and electrically connected with the microcomputer.
Through a plurality of ultraviolet ray disinfection lamps of evenly distributed at hand inslot wall, can effectively improve disinfection effect, and can not cause the influence to the collection of gesture image, can not cause the pollution to other parts of hand inslot portion, influence normal work, disinfection effect is good.
Preferably, as shown in fig. 1 and 3, the device further comprises a voice prompter 7 disposed on the housing 100;
the voice prompter 7 is electrically connected with the microcomputer.
Through voice prompt, pronunciation can be broadcast at whole body temperature measurement's in-process, for example, after gathering surveyed personnel's facial image, send the speech information of "please place the gesture according to the diagram", when surveyed personnel do not place the correct standard gesture, send the speech information of "gesture mistake, please adjust the gesture according to the diagram", intelligent degree is higher, effectively promotes user's experience.
Preferably, as shown in fig. 4, the air conditioner further comprises a fan 8 disposed at the rear side of the housing 100;
the fan 8 is electrically connected with the microcomputer.
Through the fan of casing rear side, can realize the heat dissipation of whole body temperature detector, can effectively prolong the life of instrument.
Specifically, the microcomputer in this embodiment is raspberry pi 4B, which has built-in Broadcom BCM2711 chip and a quad Cortex-A72/64 SOC CPU; the display device is a 7-inch capacitive touch display screen, the face image acquisition device is a ZBS-8010 model 800 ten thousand-pixel high-definition camera, the second camera and the third camera are 500 ten thousand-pixel cameras, the photosensitive chip in the second camera and the third camera is OV5647, the first light supplement lamp and the second light supplement lamp are 5V LED light source plates, the human body sensor comprises a 3F-DS30C4 model photoelectric sensor, and the infrared body temperature sensor is an infrared temperature sensor of a ZTP-148SR model. Other parts can all select the models which are commonly used in the market according to actual conditions.
In a second embodiment, based on the first embodiment, as shown in fig. 5, the present embodiment further discloses a non-contact temperature detection method based on artificial intelligence, which includes the following steps:
s1: acquiring a face image of a detected person, and identifying the face image to obtain face complexion characteristics and identity information;
s2: acquiring a gesture image of the detected person, and identifying the gesture image to obtain a gesture skin color characteristic and gesture positioning information;
s3: judging whether the face skin color feature is consistent with the gesture skin color feature, if so, acquiring and displaying body temperature data corresponding to the identity information according to the gesture positioning information; if not, return is made to S1.
The body temperature detection method of the embodiment is based on artificial intelligence technologies such as face recognition and gesture recognition, manual operation is not needed, body temperature data matched with the face, the gesture and the identity information of a detected person in three-in-one mode can be detected in real time, a measuring person is not needed to be directly or indirectly contacted with the detected person, non-contact measurement is really achieved, the same position can be detected when each detected person is detected, and the reliability of body temperature measurement is greatly improved.
Preferably, the following steps are further included after S1:
displaying prompt information for placing standard gestures in the hand slots;
and detecting whether the standard gesture is placed in the hand slot, if so, acquiring the gesture image, and if not, repeatedly displaying the prompt message.
Preferably, the standard gesture is specifically that the back of the hand is tiled and the direction is upward, or the palm of the hand is tiled and the direction is downward;
the specific steps of S2 include:
respectively collecting a hand back image and a palm image in the gesture image, and identifying the hand back image to obtain the gesture skin color characteristic;
judging whether the face skin color feature is consistent with the gesture skin color feature, when the face skin color feature is consistent with the gesture skin color feature, identifying the palm image to obtain the gesture positioning information, and acquiring the body temperature data corresponding to the identity information according to the gesture positioning information;
the gesture positioning information is specifically palm positioning.
Preferably, the step of S2 further comprises:
and supplementing light in the process of collecting the hand back image, and supplementing light in the process of collecting the palm image.
Preferably, the step of S2 further comprises:
disinfecting an interior space of the hand slot before and/or after acquiring the gesture image.
Specifically, as shown in fig. 6, the complete flow of the non-contact temperature detection method based on artificial intelligence in this embodiment is as follows:
(1) acquiring a face image (loading the face image into a corresponding program in a microcomputer for preprocessing);
(2) prompting information such as 'gesture is placed according to the diagram' and the like on the display;
(3) starting a human body sensor to detect whether a standard gesture is placed in the hand groove within 3s after the prompt information is displayed on the display; if the sensing is not carried out within 4s, returning to the previous step, otherwise, carrying out the next step;
(4) after the standard gesture is detected, starting the disinfection device for the first time, wherein the duration time is 5 s;
(5) after disinfection, a first light supplement lamp is turned on, and a first camera is turned on at the same time for analyzing the hand back image;
(6) after the hand back image is analyzed, the first light supplement lamp is turned off, and the second light supplement lamp and the second camera are turned on simultaneously for analyzing the palm image;
(7) after the palm image analysis is finished, starting the infrared body temperature sensor to analyze and collect the body temperature of the human body, and simultaneously uploading the collected body temperature data to the microcomputer for analysis and processing;
(8) starting the disinfection device for the second time for a duration of 7 s;
(9) the microcomputer displays the processed body temperature data back to the display;
(10) starting the disinfection device for the third time for 7 s;
(11) after the disinfection device is closed, the display prompts a gesture of taking out;
(12) the flow ends.
Details of the non-contact temperature detector based on artificial intelligence in this embodiment are described in detail in the first embodiment and fig. 1 to 4, and are not repeated herein.
The reader should understand that in the description of this specification, reference to the description of the terms "one embodiment," "some embodiments," "an example," "a specific example" or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Moreover, various embodiments or examples and features of various embodiments or examples described in this specification can be combined and combined by one skilled in the art without being mutually inconsistent.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (10)
1. A non-contact temperature detector based on artificial intelligence is characterized by comprising a shell (100), a microcomputer arranged in the shell (100), a hand groove (200) arranged on the front side of the shell (100), a display device (1) arranged on the front side of the shell (100) and a human face image acquisition device (2);
a gesture image acquisition device (3) and an infrared body temperature sensor (4) are arranged in the hand groove (200);
the microcomputer is respectively and electrically connected with the display device (1), the face image acquisition device (2), the gesture image acquisition device (3) and the infrared body temperature sensor (4);
the face image acquisition device (2) is used for acquiring a face image of a detected person;
the gesture image acquisition device (3) is used for acquiring a gesture image of the detected person;
the microcomputer is used for:
identifying the face image to obtain face complexion characteristics and identity information;
recognizing the gesture image to obtain gesture skin color characteristics and gesture positioning information;
judging whether the face skin color feature is consistent with the gesture skin color feature, and when the face skin color feature is consistent with the gesture skin color feature, acquiring body temperature data corresponding to the identity information by using the infrared body temperature sensor (4) based on the gesture positioning information;
the display device (1) is used for displaying the body temperature data.
2. The artificial intelligence-based non-contact temperature detector according to claim 1, wherein a human body sensor (5) is further disposed in the hand groove (200), and the human body sensor (5) is electrically connected to the microcomputer;
the microcomputer is further configured to:
after the face skin color characteristics and the identity information are obtained, the display device (1) is used for displaying prompt information for placing standard gestures in the hand slot (200);
the human body sensor (5) is used for detecting whether the standard gesture is placed in the hand groove (200);
the gesture image acquisition device (3) is specifically used for acquiring the gesture image when the human body sensor (5) detects that the standard gesture is placed in the hand slot (200).
3. The artificial intelligence-based non-contact temperature monitor of claim 2, wherein the standard gesture is specifically one of a back of hand lying flat and facing upward, or a palm lying flat and facing downward;
the gesture image acquisition device (3) comprises a first camera (31) and a second camera (32), the first camera (31) is arranged on the upper side inside the hand groove (200), the second camera (32) is arranged on the lower side inside the hand groove (200), and the infrared body temperature sensor (4) is arranged at the central position of the lower side inside the hand groove (200); the first camera (31) and the second camera (32) are respectively electrically connected with the microcomputer;
the first camera (31) is used for acquiring a hand back image in the gesture image;
the second camera (32) is used for acquiring a palm image in the gesture image;
the microcomputer is further specifically configured to:
identifying the hand back image to obtain the gesture skin color characteristic;
judging whether the face skin color feature is consistent with the gesture skin color feature, when the face skin color feature is consistent with the gesture skin color feature, identifying the palm image to obtain gesture positioning information, and acquiring the body temperature data corresponding to the identity information by using the infrared body temperature sensor (4) based on the gesture positioning information;
the gesture positioning information is specifically palm positioning information.
4. The artificial intelligence based non-contact temperature detector according to claim 3, wherein the gesture image capturing device (3) further comprises a first supplementary lighting lamp (33) and a second supplementary lighting lamp (34), the first supplementary lighting lamp (33) is disposed at an upper side inside the hand slot (200) near the first camera (31), and the second supplementary lighting lamp (34) is disposed at a lower side inside the hand slot (200) near the second camera (32); the first light supplement lamp (33) and the second light supplement lamp (34) are respectively electrically connected with the microcomputer;
the first light supplement lamp (33) is used for supplementing light for the process of acquiring the hand back image by the first camera (31);
and the second light supplement lamp (34) is used for supplementing light for the process of acquiring the palm image by the second camera (32).
5. The artificial intelligence based non-contact temperature detector according to claim 1, wherein a disinfection device (6) is further disposed in the hand tank (200), and the disinfection device (6) is disposed on an inner wall of the hand tank (200); the sterilizing device (6) is electrically connected with the microcomputer;
the disinfection device (6) is used for disinfecting the inner space of the hand tank (200) before and/or after the gesture image acquisition device (3) acquires the gesture image.
6. The artificial intelligence based non-contact temperature detecting instrument according to claim 5, wherein the sterilizing device (6) comprises a plurality of ultraviolet sterilizing lamps uniformly distributed on the inner wall of the hand tank (200);
each ultraviolet disinfection lamp is respectively and electrically connected with the microcomputer.
7. The artificial intelligence based non-contact temperature monitor according to any one of claims 1 to 6, further comprising a voice prompt (7) disposed on the housing (100);
the voice prompter (7) is electrically connected with the microcomputer.
8. The artificial intelligence based non-contact temperature monitor according to any one of claims 1 to 6, further comprising a fan (8) disposed at a rear side of the housing (100);
the fan (8) is electrically connected with the microcomputer.
9. An artificial intelligence based non-contact temperature detection method, which is characterized in that the non-contact temperature detection is carried out by the artificial intelligence based non-contact temperature detector according to any one of claims 1 to 8, and comprises the following steps:
step 1: acquiring a face image of a detected person, and identifying the face image to obtain face complexion characteristics and identity information;
step 2: acquiring a gesture image of the detected person, and identifying the gesture image to obtain a gesture skin color characteristic and gesture positioning information;
and 3, step 3: judging whether the face skin color feature is consistent with the gesture skin color feature, if so, acquiring and displaying body temperature data corresponding to the identity information according to the gesture positioning information; if not, returning to the step 1.
10. The artificial intelligence based non-contact temperature sensing method according to claim 9, further comprising the following steps after step 1:
displaying prompt information for placing standard gestures in the hand slots;
and detecting whether the standard gesture is placed in the hand slot, if so, acquiring the gesture image, and if not, repeatedly displaying the prompt message.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010749287.3A CN111967550B (en) | 2020-07-30 | 2020-07-30 | Non-contact temperature detector based on artificial intelligence and detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010749287.3A CN111967550B (en) | 2020-07-30 | 2020-07-30 | Non-contact temperature detector based on artificial intelligence and detection method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111967550A CN111967550A (en) | 2020-11-20 |
| CN111967550B true CN111967550B (en) | 2022-08-30 |
Family
ID=73362294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010749287.3A Active CN111967550B (en) | 2020-07-30 | 2020-07-30 | Non-contact temperature detector based on artificial intelligence and detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111967550B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116071862A (en) * | 2022-12-16 | 2023-05-05 | 北京声智科技有限公司 | Pass verification method, pass verification device, electronic equipment, pass verification system and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011123653A (en) * | 2009-12-10 | 2011-06-23 | Sumitomo Rubber Ind Ltd | Test device for driver's arousal level |
| CN103488299A (en) * | 2013-10-15 | 2014-01-01 | 大连市恒芯科技有限公司 | Intelligent terminal man-machine interaction method fusing human face and gestures |
| CN103514438A (en) * | 2012-06-25 | 2014-01-15 | 盈泰安股份有限公司 | Face judgment system and method |
| CN106096588A (en) * | 2016-07-06 | 2016-11-09 | 北京奇虎科技有限公司 | The processing method of a kind of view data, device and mobile terminal |
| CN108111754A (en) * | 2017-12-18 | 2018-06-01 | 维沃移动通信有限公司 | A kind of method and mobile terminal of definite image acquisition modality |
| CN109104522A (en) * | 2018-06-27 | 2018-12-28 | 维沃移动通信有限公司 | A kind of method and mobile terminal of recognition of face |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2013080413A (en) * | 2011-10-05 | 2013-05-02 | Sony Corp | Input apparatus and input recognition method |
| US9423879B2 (en) * | 2013-06-28 | 2016-08-23 | Chia Ming Chen | Systems and methods for controlling device operation according to hand gestures |
-
2020
- 2020-07-30 CN CN202010749287.3A patent/CN111967550B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2011123653A (en) * | 2009-12-10 | 2011-06-23 | Sumitomo Rubber Ind Ltd | Test device for driver's arousal level |
| CN103514438A (en) * | 2012-06-25 | 2014-01-15 | 盈泰安股份有限公司 | Face judgment system and method |
| CN103488299A (en) * | 2013-10-15 | 2014-01-01 | 大连市恒芯科技有限公司 | Intelligent terminal man-machine interaction method fusing human face and gestures |
| CN106096588A (en) * | 2016-07-06 | 2016-11-09 | 北京奇虎科技有限公司 | The processing method of a kind of view data, device and mobile terminal |
| CN108111754A (en) * | 2017-12-18 | 2018-06-01 | 维沃移动通信有限公司 | A kind of method and mobile terminal of definite image acquisition modality |
| CN109104522A (en) * | 2018-06-27 | 2018-12-28 | 维沃移动通信有限公司 | A kind of method and mobile terminal of recognition of face |
Non-Patent Citations (1)
| Title |
|---|
| 一种基于肤色特征提取的手势检测识别方法;范文兵等;《现代电子技术》;20170915(第18期);第85-88页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111967550A (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2677490B1 (en) | Authentication device, authentication program, and authentication method | |
| EP1587414B1 (en) | A pupilometer | |
| KR20130006445A (en) | Method and device for detecting the orientation of an area of the body of an individual resting on an apposition area of a mounting of a biometric sensor | |
| US20180271382A1 (en) | Approach for measuring capillary refill time | |
| CN112084965A (en) | Scalp hair detection device and system | |
| CN111967550B (en) | Non-contact temperature detector based on artificial intelligence and detection method thereof | |
| KR102036040B1 (en) | Diagnosis Device of optical skin disease | |
| CN108388858B (en) | Iris anti-fake method and device | |
| Flaucher et al. | Smartphone-based colorimetric analysis of urine test strips for at-home prenatal care | |
| CN110811551A (en) | Oral cavity analysis system and method based on near infrared spectrum | |
| CN111862118B (en) | Pressure sore staging training method, staging method and staging system | |
| CN112668539A (en) | Biological characteristic acquisition and identification system and method, terminal equipment and storage medium | |
| CN104586404A (en) | Method and system for identifying posture of fitness and health monitoring | |
| CN107423606A (en) | A kind of identification system based on fuzzy control theory | |
| CN111150369A (en) | Medical assistance apparatus, medical assistance detection apparatus and method | |
| CN207586946U (en) | Alternative light source intelligent starting and anti-fake active biological characteristic shape of face identification device | |
| CN116092157A (en) | Intelligent facial tongue diagnosis method, system and intelligent equipment | |
| CN213458082U (en) | Iris collecting and identifying device | |
| CN115035086A (en) | Intelligent tuberculosis skin test screening and analyzing method and device based on deep learning | |
| CN212378909U (en) | Face identification wrist temperature measurement terminal | |
| CN111210438A (en) | Mirror | |
| CN114526823A (en) | Accurate temperature measuring method and system for infrared thermometer and storage medium | |
| CN114494299A (en) | Temperature detection device | |
| CN208610822U (en) | A kind of morning inspection equipment | |
| CN112086193A (en) | Face recognition health prediction system and method based on Internet of things |
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 |