CN109464132A - Robot, kindergarten morning check system - Google Patents
Robot, kindergarten morning check system Download PDFInfo
- Publication number
- CN109464132A CN109464132A CN201910025286.1A CN201910025286A CN109464132A CN 109464132 A CN109464132 A CN 109464132A CN 201910025286 A CN201910025286 A CN 201910025286A CN 109464132 A CN109464132 A CN 109464132A
- Authority
- CN
- China
- Prior art keywords
- robot
- bleb
- detection
- cloud server
- neural network
- 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
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/44—Detecting, measuring or recording for evaluating the integumentary system, e.g. skin, hair or nails
- A61B5/441—Skin evaluation, e.g. for skin disorder diagnosis
- A61B5/445—Evaluating skin irritation or skin trauma, e.g. rash, eczema, wound, bed sore
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Cardiology (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Physiology (AREA)
- Dermatology (AREA)
- Pulmonology (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of robot, kindergarten morning check system, including apparatus for testing body temperature, Weight detecting device, height detection device and bleb detection system, the bleb detection system includes work station, cloud server and robot client, the robot client obtains user image data and is transmitted to the cloud server, the cloud server receives the image data of the robot client, and it is distributed to the work station, the work station carries out recognition detection bleb using the target detection recognizer based on deep learning neural network, palm and oral cavity, and recognition result is fed back to the cloud server, and the robot client is transmitted to by it and is shown.Robot, the kindergarten morning check system provided by the invention it is creative identify bleb using cloud server and deep learning neural network model, it is easy to operate, detection speed is fast, testing result is accurate.
Description
Technical field
The present invention relates to target detection technique, image processing techniques and medical detection fields, and in particular to one kind is based on cloud
Hold robot, the kindergarten morning check system of the deep learning neural network bleb detection system of server.
Background technique
With the development of society, the progress in epoch, people are more and more to the safety of kindergarten and the health concerns of child,
The management work of the following kindergarten also can be more and more heavier, and therefore, traditional labor management mode cannot be effectively
Employee and child's information to kindergarten are managed.Especially in child morning procuratorial organ face, artificial, such morning is all relied on greatly at present
Low efficiency is examined, is depended on manually, and easily cause the impatience of child.The especially inspection of bleb, in the prior art, warp
It often needs to carry out careful observation to examiner's palm, the child of kindergarten or primary grades requires to carry out morning daily at this stage
Inspection, prevention brothers mouthful etc. have communicable disease.Common method is usually to pass through patient's palm oral cavity direct visual perception
Afterwards, will test result it is artificial be divided into several ranks, and take different measure according to the actual situation, executor is mostly doctor or old
Teacher.But there are many defects for this mode, such as: observation result depends on the experience for executing inspection personnel and medical speciality is known
Knowledge and the state of mind may cause inspection result inaccuracy, while can not leave detection record and evidence, be unfavorable in time just
Doctor；In addition, detection difficulty is high, the health doctor or teacher of kindergarten or educational institution general lack of experienced profession.
Summary of the invention
The present invention proposes a kind of robot, kindergarten morning check system in view of the above problems, and the system is based on cloud server
Deep learning neural network carries out bleb detection, and detection speed is fast, detection is accurate.
The present invention provides a kind of robot, kindergarten morning check system, including apparatus for testing body temperature, Weight detecting device, height
Detection device, the apparatus for testing body temperature, Weight detecting device, height detection device are respectively used to detection body temperature, weight
And height, the Chen Jian robot further include bleb detection system, the detection system includes work station, cloud server and machine
Device people's client, the robot client obtain user image data and are transmitted to the cloud server, the cloud clothes
Business device receives the image data of the robot client, and is distributed to the work station, and the work station, which utilizes, is based on depth
The target detection recognizer of learning neural network carries out recognition detection bleb, palm and mouth position, and recognition result is anti-
It feeds the cloud server, the cloud server transmits the result to the robot client and shown.
In a kind of preferred embodiment of robot, kindergarten morning check system provided by the invention, the work station is equipped with deep
Spend learning neural network model.
In a kind of preferred embodiment of robot, kindergarten morning check system provided by the invention, the deep learning nerve
Network model is Darknet-Yolov3 network model.
In a kind of preferred embodiment of robot, kindergarten morning check system provided by the invention, the work station identifies blister
Rash workflow are as follows:
S1: start；
S2: the deep learning neural network model is initialized；
S3: network weight, network model, the sort file of the deep learning neural network model are loaded；
S4: the network service end program of the work station is initialized；
S5: receiving the image data of the cloud server and carries out the conversion of image data format；
S6: the deep learning neural network model carries out bleb identification, and returns to recognition result to the cloud service
Device.
In a kind of preferred embodiment of robot, kindergarten morning check system provided by the invention, the deep learning nerve
The process of network model progress bleb identification are as follows: the image data after format transformation described in obtaining step S5；Hand is obtained through detection
It slaps, the position in oral cavity and bleb；Do you judge that Herpes site and palm and/or mouth position are overlapped? if then illustrate palm and/
Or mouth position has bleb, illustrates not detect bleb if without being overlapped.
Compared to the prior art, robot, kindergarten morning check system provided by the invention has the advantages that
One, the deep learning Application of Neural Network based on cloud server is detected and is answered in bleb by the invention
With in Chen Jian robot, kindergarten, directly compared by the good network weight of precondition, network model and sort file
To identification, detection speed is fast, target detection is accurate.In addition, detect oral cavity and palm position simultaneously, by judge bleb, oral cavity,
Coincidence is compared in palm position, keeps judging result more accurate.
Two, detection bleb is carried out by obtaining picture, does not carry out extremity directly, that has cut off contagious infection can
Can, effectively avoid spread in china.In addition fash, nettle rash, eczema, varicella, acne etc. are applied also in mottled distribution
Dermopathic course of disease detection, no matter course of disease weight all can quickly detect identification, practical.
Three, bleb detection is using robot as carrier, by mature Target Recognition Algorithms, detection accurately, not by
The influence of artificial professional knowledge and the state of mind, and the curious psychology of child is made full use of, overcome child can to a certain extent
The anxiety that can be generated.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, used in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure, in which:
Fig. 1 is robot, kindergarten morning check system bleb detection system structure provided by the invention；
Fig. 2 is the work flow diagram of robot, kindergarten morning check system bleb detection system provided by the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that the described embodiments are merely a part of the embodiments of the present invention, instead of all the embodiments.
Referring to Fig. 1, being robot, kindergarten morning check system structural schematic diagram provided by the invention；
Robot, the kindergarten morning check system include apparatus for testing body temperature, Weight detecting device, height detection device and
Bleb detection system 10.Apparatus for testing body temperature, Weight detecting device, height detection device are all set to robot body, robot
Main control unit is equipped in ontology, apparatus for testing body temperature, Weight detecting device, height detection device detect body temperature, body respectively
Weight and height are simultaneously transmitted to the main control unit, and it is aobvious accordingly to be shown in robot client 101 by main control unit control
Showing device.
The bleb detection system 10 includes work station 105, cloud server 103 and robot client 101.
The robot client 101 includes camera, for obtaining user image data and being transmitted through the network to institute
State cloud server 103.The cloud server 103 receives the image data that the robot client 101 is transmitted, and distributes
To the work station 105, the work station 105 is known using the target detection recognizer based on deep learning neural network
Not Jian Ce bleb, palm and oral cavity, and recognition result is fed back to the cloud server 103 and robot client 101.
The work station 105 is equipped with deep learning neural network model.Mesh built in the deep learning neural network model
Mark detection recognizer.Referring to Fig. 2, the identification process of 105 bleb of work station are as follows:
S1: start；
S2: the deep learning neural network model is initialized；
S3: network weight, network model, the sort file of the deep learning neural network model are loaded；
S4: the network service end program of the work station 105 is initialized；
S5: receiving the image data of the cloud server 103 and carries out the conversion of image data format；
S6: the deep learning neural network model carries out bleb identification, and returns to recognition result.Specifically, the depth
Spend the process that learning neural network model carries out bleb identification are as follows: the image data after format transformation described in obtaining step S5；Through
Detection obtains the position of palm, oral cavity and bleb；Do you judge that Herpes site and palm and/or mouth position are overlapped? if then
Illustrate that palm and/or mouth position have bleb, illustrates not detect bleb if without being overlapped.Pass through detection oral cavity and palm position
It sets, judges whether bleb and oral cavity, palm position are overlapped, keep judging result more accurate.
In the prior art, deep learning neural network model has RCNN model, SPP-net mould based on area-of-interest
Type, Fast RCNN model, Faster RCNN model etc., there are also the YOLO systems of the deep learning algorithm of target detection based on recurrence
Column model.
In preferred embodiment, the deep learning neural network model is Darknet-Yolov3 network model.It utilizes
Trained Yolov3 network weight, network model and sort file are called in the encapsulation library of Darknet, take to the cloud
The image data that business device 103 transmits is identified, and recognition result is returned.The processing speed of Darknet-Yolov3 network model
Other opposite several network model datas processing of degree several times faster, network weight be it is trained after obtain, model file
It is identical when with class declaration with training.
The thought of Yolo system algorithm is: carrying out feature extraction by image of the feature extraction network to input first, obtains
A certain size characteristic pattern, then by input picture grid division at several cells, the centre coordinate of some target is fallen in
In which cell, then just predicting the target by the cell.On the one hand Yolov3 uses full convolutional coding structure, on the other hand
Introduce residual error structure.Residual error structure can be very good the propagation of control gradient, and it is unfavorable to avoid the occurrence of gradient disappearance or explosion etc.
In trained situation, this makes that deep layer network difficulty is trained to greatly reduce, and the network number of plies greatly improves, and target detection precision is obvious
It is promoted.
Compared to the prior art, robot, kindergarten morning check system provided by the invention has the advantages that
One, the deep learning Application of Neural Network based on cloud server is detected and is answered in bleb by the invention
With in Chen Jian robot, kindergarten, directly compared by the good network weight of precondition, network model and sort file
To identification, detection speed is fast, target detection is accurate.
Two, detection bleb is carried out by obtaining picture, does not carry out extremity directly, that has cut off contagious infection can
Can, effectively avoid spread in china.In addition fash, nettle rash, eczema, varicella, acne etc. are applied also in mottled distribution
Dermopathic course of disease detection, no matter course of disease weight all can quickly detect identification, practical.
Three, the bleb detection system 10 passes through mature Target Recognition Algorithms, detection essence using robot as carrier
Really, it is not influenced by artificial professional knowledge and the state of mind, and makes full use of the curious psychology of child, overcome to a certain extent
The issuable anxiety of child.
Claims (5)
1. a kind of robot, kindergarten morning check system, including apparatus for testing body temperature, Weight detecting device, height detection device, institute
It states apparatus for testing body temperature, Weight detecting device, height detection device and is respectively used to detection body temperature, weight and height, it is special
Sign is: the Chen Jian robot further includes bleb detection system, and the detection system includes work station, cloud server and machine
Device people's client, the robot client obtain user image data and are transmitted to the cloud server, the cloud clothes
Business device receives the image data of the robot client, and is distributed to the work station, and the work station, which utilizes, is based on depth
The target detection recognizer of learning neural network carries out recognition detection bleb, palm and mouth position, and recognition result is anti-
It feeds the cloud server, the cloud server transmits the result to the robot client and shown.
2. robot, kindergarten morning check system according to claim 1, it is characterised in that: the work station is equipped with depth
Practise neural network model.
3. robot, kindergarten morning check system according to claim 2, it is characterised in that: the deep learning neural network
Model is Darknet-Yolov3 network model.
4. robot, kindergarten morning check system according to claim 2, it is characterised in that: the work station identifies bleb work
Make process are as follows:
S1: start；
S2: the deep learning neural network model is initialized；
S3: network weight, network model, the sort file of the deep learning neural network model are loaded；
S4: the network service end program of the work station is initialized；
S5: receiving the image data of the cloud server and carries out the conversion of image data format；
S6: the deep learning neural network model carries out bleb identification, and returns to recognition result to the cloud server.
5. robot, kindergarten morning check system according to claim 4, it is characterised in that: the deep learning neural network
The process of model progress bleb identification are as follows: the image data after format transformation described in obtaining step S5；Palm, mouth are obtained through detection
The position of chamber and bleb；Do you judge that Herpes site and palm and/or mouth position are overlapped? if then illustrating palm and/or mouth
There is bleb in chamber position, illustrates not detect bleb if without being overlapped.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910025286.1A CN109464132A (en) | 2019-01-11 | 2019-01-11 | Robot, kindergarten morning check system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910025286.1A CN109464132A (en) | 2019-01-11 | 2019-01-11 | Robot, kindergarten morning check system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109464132A true CN109464132A (en) | 2019-03-15 |
Family
ID=65678375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910025286.1A Pending CN109464132A (en) | 2019-01-11 | 2019-01-11 | Robot, kindergarten morning check system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109464132A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059635A (en) * | 2019-04-19 | 2019-07-26 | 厦门美图之家科技有限公司 | A kind of skin blemishes detection method and device |
| CN110584618A (en) * | 2019-08-15 | 2019-12-20 | 济南市疾病预防控制中心 | Infectious disease machine recognition system based on artificial intelligence |
| CN111598865A (en) * | 2020-05-14 | 2020-08-28 | 上海锘科智能科技有限公司 | Hand-foot-and-mouth disease detection method, device and system based on thermal infrared and RGB (red, green and blue) double-taking |
| CN112008740A (en) * | 2020-09-08 | 2020-12-01 | 济南爱维互联网有限公司 | Morning check robot and use method thereof |
| CN113297882A (en) * | 2020-02-21 | 2021-08-24 | 湖南超能机器人技术有限公司 | Intelligent morning check robot, height measuring method and application |
| CN113487610A (en) * | 2021-09-07 | 2021-10-08 | 湖南超能机器人技术有限公司 | Herpes image recognition method and device, computer equipment and storage medium |
| CN113977596A (en) * | 2021-09-29 | 2022-01-28 | 湖北隆感科技有限公司 | Detection robot and detection method for smart campus management |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108742634A (en) * | 2018-06-11 | 2018-11-06 | 江苏童讯科技有限公司 | A kind of morning check system and its application |
-
2019
- 2019-01-11 CN CN201910025286.1A patent/CN109464132A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108742634A (en) * | 2018-06-11 | 2018-11-06 | 江苏童讯科技有限公司 | A kind of morning check system and its application |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059635A (en) * | 2019-04-19 | 2019-07-26 | 厦门美图之家科技有限公司 | A kind of skin blemishes detection method and device |
| CN110059635B (en) * | 2019-04-19 | 2021-03-23 | 厦门美图之家科技有限公司 | Skin defect detection method and device |
| CN110584618A (en) * | 2019-08-15 | 2019-12-20 | 济南市疾病预防控制中心 | Infectious disease machine recognition system based on artificial intelligence |
| CN113297882A (en) * | 2020-02-21 | 2021-08-24 | 湖南超能机器人技术有限公司 | Intelligent morning check robot, height measuring method and application |
| CN111598865A (en) * | 2020-05-14 | 2020-08-28 | 上海锘科智能科技有限公司 | Hand-foot-and-mouth disease detection method, device and system based on thermal infrared and RGB (red, green and blue) double-taking |
| CN111598865B (en) * | 2020-05-14 | 2023-05-16 | 上海锘科智能科技有限公司 | Hand-foot-mouth disease detection method, device and system based on thermal infrared and RGB double-shooting |
| CN112008740A (en) * | 2020-09-08 | 2020-12-01 | 济南爱维互联网有限公司 | Morning check robot and use method thereof |
| CN113487610A (en) * | 2021-09-07 | 2021-10-08 | 湖南超能机器人技术有限公司 | Herpes image recognition method and device, computer equipment and storage medium |
| CN113977596A (en) * | 2021-09-29 | 2022-01-28 | 湖北隆感科技有限公司 | Detection robot and detection method for smart campus management |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109464132A (en) | Robot, kindergarten morning check system | |
| CN110175993A (en) | A kind of Faster R-CNN pulmonary tuberculosis sign detection system and method based on FPN | |
| Thorndike | Regression fallacies in the matched groups experiment | |
| Jassar et al. | Quantitative mitral valve modeling using real-time three-dimensional echocardiography: technique and repeatability | |
| CN104207931B (en) | Face facial point precise positioning and acupuncture and moxibustion prescription, acumoxibustion prescription learning method | |
| Parvizi et al. | BurnCase 3D software validation study: burn size measurement accuracy and inter-rater reliability | |
| CN109003299A (en) | A method of the calculating cerebral hemorrhage amount based on deep learning | |
| Mamlin et al. | Combined time-motion and work sampling study in a general medicine clinic | |
| CN109461188B (en) | A kind of two-dimensional x-ray cephalometry image anatomical features point automatic positioning method | |
| CN104361321A (en) | Methods of judging fall behaviors and body balance for old people | |
| CN110755085B (en) | Motion function evaluation method and equipment based on joint mobility and motion coordination | |
| CN104224129A (en) | Identification method and prompting system for depth of vein blood vessel | |
| CN102670190A (en) | Heart rate variability nonlinear characteristic-based automatic diagnosis method for congestive heart failure | |
| CN110415818A (en) | A kind of intelligent pediatric disease interrogation system and method based on observable illness | |
| Phillips et al. | Prediction of progression to AIDS by analysis of CD4 lymphocyte counts in a haemophilic cohort | |
| Salentijn et al. | Six Sigma to distinguish patterns in COVID-19 approaches | |
| Prescott | Nursing intensity: needed today for more than staffing... the Patient Intensity for Nursing Index (PINI) | |
| CN107818707B (en) | Examination system capable of automatically setting questions | |
| Wang et al. | Student physical fitness test system and test data analysis system based on computer vision | |
| CN117100246A (en) | Health state analysis method based on dynamic bioelectric signals and related products | |
| CN112890767A (en) | Automatic detection device and method for health state of mouth, hands and feet | |
| CN111951950B (en) | Three-dimensional data medical classification system based on deep learning | |
| CN111341459A (en) | Training method of classified deep neural network model and genetic disease detection method | |
| CN103679198B (en) | A kind of retina internal segment based on k nearest neighbor/acromere disappearance automatic testing method | |
| CN100543771C (en) | Body local image automatic standardizing method |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190315 |