CN107495971A - Morbidity's alarm medical system and its detection method based on skeleton identification - Google Patents
Morbidity's alarm medical system and its detection method based on skeleton identification Download PDFInfo
- Publication number
- CN107495971A CN107495971A CN201710621799.XA CN201710621799A CN107495971A CN 107495971 A CN107495971 A CN 107495971A CN 201710621799 A CN201710621799 A CN 201710621799A CN 107495971 A CN107495971 A CN 107495971A
- Authority
- CN
- China
- Prior art keywords
- image
- data
- matrix morphology
- real
- time
- 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
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
-
- 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
- A61B5/1079—Measuring physical dimensions, e.g. size of the entire body or parts thereof using optical or photographic means
-
- 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
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1121—Determining geometric values, e.g. centre of rotation or angular range of movement
-
- 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
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
- A61B5/1128—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique using image analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/7405—Details of notification to user or communication with user or patient ; user input means using sound
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
Abstract
The present invention relates to medical treatment detection device technical field, specifically morbidity's alarm medical system and its detection method based on skeleton identification, including visible terminal, real time inspection patient activity situation and skeletal gesture；Image capture module, for being in real time the image or video flowing needed for the collection of visible terminal；Data transmission module, image or video stream data transmission are carried out in real time；The dangerous matrix morphology data of collection are completed in storage module, storage in advance；Processing module, the image or video flowing of processing image capture module collection, real-time matrix morphology data are converted into by image or video flowing；The dangerous matrix morphology data needed for storage module are transferred, and contrasted with real-time matrix morphology data, judge similarity；Optoacoustic equipment, the abnormal conditions judged in real time according to visible terminal send warning, and the present invention contributes to care provider and medical personnel to take corresponding urgent emergency measures in time, has further ensured health of human body safety.
Description
Technical field
The present invention relates to medical treatment detection device technical field, that the body skeleton specifically based on real time image collection identifies,
Judge whether patient falls ill and make the supervision equipment system of warning.
Background technology
Acquisition of the biological identification technology based on object organisms feature.Compare language and word, and biological identification technology is most
Big feature is to be embodied and intuitive, and different conditions are distinguished by the nuance of biological characteristic.Closely or connect in
The biological characteristic obtained, such as fingerprint, iris and face and voice etc. are touched, identification technology is played and has obtained tremendous development and input
Using, but the acquisition of above-mentioned biological characteristic constrains to a certain extent with obtaining distance and obtaining the limitation of picture quality
The further development of these technologies.
Skeleton identification technology belongs to the biological identification technology of long distance acquisition.For identification for biology, use is as simple as possible
Single shape, the combination of even Points And lines bar describes object information, can briefly describe structural topology information, i.e., visual
" skeleton ", or axis.Be compared to other identification technologies of aforementioned list, skeleton identification information can in remotely gathering,
Close to collected object or it need not be in contact with it；And other identification technologies are compared to the image quality requirements of gathered information
It is more loose.
It is non-autonomous locally or systemically ictal fortune by typical case, the significant clinical manifestation of some illnesss of epilepsy
It is dynamic；And such illness has sudden, and fatal wound may be caused to patient in a short time, this also causes to patient
Monitoring propose the round-the-clock and requirement that warns in time.International anti-epileptic alliance to epileptic attack reclassify and mend
Fill so that the breaking-out pattern of epilepsy can have more fully to be distinguished with complete system.And the standard of this morbidity gesture actions
It is long-range to monitor patient's to change and distinguish, also analyzed to using real-time monitoring images --- i.e. the biological identification technology such as skeleton identification ---
Behavioral aspect provides the benchmark of the note on the use and reference.
The content of the invention
Lack the present situation of detection and alarm, this hair during in order to solve to fall ill for specified disease in existing medical monitoring devices
It is bright that a kind of morbidity's alarm medical system based on skeleton identification is provided, it can detect and be presented when warning some morbidities specific
The appearance of the illness for posture of falling ill so that the monitoring to sufferer adds real-time biological identification skill on the basis of physical signs
Art, contribute to care provider and medical personnel to take corresponding urgent emergency measures in time, further ensured health of human body peace
Entirely.
On the one hand, the present invention provides a kind of morbidity's alarm medical system based on skeleton identification, and it includes visual prison
Terminal is protected, for real time inspection patient activity situation and skeletal gesture；Image capture module, for being in real time visible terminal
Image or video flowing needed for collection；Data transmission module, for carrying out image or video stream data transmission in real time；Store mould
Block, complete the dangerous matrix morphology data of collection in advance for storing；Processing module, for handling image capture module collection
Image or video flowing, image or video flowing are converted into real-time matrix morphology data；Transfer the dangerous bone needed for storage module
Frame morphological data, and contrasted with real-time matrix morphology data, judge similarity；Optoacoustic equipment, in real time according to visual
The abnormal conditions that monitoring terminal is judged send warning.
On the other hand, there is provided a kind of detection method of morbidity's alarm medical system based on skeleton identification, its is specific
Step is as follows：
Step 1：Video collecting device is called to carry out:The acquirement of image or video flowing；
Step 2：Acquired obtained image or video stream data are sent to computer equipment input by data transmission set
Mouthful；
Step 3：Computer input port receives to the image in step 2 or video stream data, and carries out the data to meter
The reading operation of calculation machine hard disk；
Step 4：For the real time data having been read into, the reality of monitored target in image is drawn with matrix morphology following function
When matrix morphology data；
Step 5：Search for storage module in specify matrix morphology abnormal attitude data, by abnormal attitude data in database with
The comparison of real-time matrix morphology data, the similarity degree of the latter before judgement；Step 6：According to similarity degree in step 5, qualitative reality
When the state that is shown of matrix morphology whether can determine whether as abnormality；
Step 7：It is judged as the real-time matrix morphology data of abnormality for step 6, system could be made that warning.
Step 8：The matrix morphology data in real time will be released or be stored among the record of monitoring, for adjusting once again
With.
Technical scheme includes following entry：
（a1）Supporting hardware facility, as the Equipment Foundations of the real-time matrix morphology of detection object sufferer, including：Visible is whole
End, it can usually show by the monitor screen and or computer screen of monitoring end situation.The video terminal should meet minimum
Configuration requirement, the picture frame quality handled by picture system shown by meaning, i.e. inside is at least matrix morphology detecting can be just
The lowest image quality often operated；
The optoacoustic equipment of warning is sent, it is supporting with matrix morphology monitoring system, it can be realized in time with human sensory in real time
Message form sends the optoacoustic equipment of warning, including but not limited to warning lamp and loudspeaker etc..This optoacoustic equipment be able to should supervise in real time
The abnormal conditions that examining system is judged, and obvious information warning can be sent so that care provider can be instantly available burst shape
The presence of condition, so as to make timely corresponding measure；
Transmission equipment when adopting picture equipment sum factually of image taking required by above-mentioned form monitoring system can be met.Configured
Before adopting as equipment should be able to gather image quality enough clearly image or video flowing, and the equipment acquired image frame disclosure satisfy that
State the lowest image quality of matrix morphology monitoring system normal operation.The image or video flowing of collection according to circumstances can be black and white or
Colored image quality, and picking rate and collection delay are not more than required minimum standard.Used data transmission set
The transmission speed of above-mentioned requirements and the minimum standard of transmission delay should be met.
（a2）The software section realized for matrix morphology monitoring function, including：Abnormal posture based on matrix morphology
Data bank.For required monitoring morbidity when produce posture distortion etc. unusual condition illness, gathered by pretesting
Etc. mode, obtain such a illness when occurring patient in physically issuable abnormal skeleton pose.With above-mentioned abnormal bone
Based on frame posture, skeleton data series corresponding thereto is established, and is stored in that matrix morphology monitoring system is built-in or peripheral hardware
In data stock, for the calling at any time of monitoring system.The corresponding abnormal bone of a variety of different syndromes can be allowed among same database
Rack data series exists simultaneously.According to real needs, appeal data can carry out the classification based on various criterion, and allow monitoring
Transferred among the process of function operation with one kind or transfer the matching that multiclass exception skeleton data carries out posture simultaneously；For guardian
The user interface that member uses.The user interface should be designed as being principle to user close friend, according to care provider
The specific requirement of body is operated accordingly, including but not limited to the beginning of detection function and termination or when manually setting monitoring
Section, monitored object and called data purposeful selection, the criterion of object monitored " unsafe condition "（I.e. dangerous appearance
The effective range of gesture and data in database adjusts）, and the preference selection of warning way；Realize skeleton pose identification
Program and algorithm include but is not limited to：Video collecting device is called to carry out the acquirement of the image or video flowing of given frame per second.
Acquired obtained image or video stream data are passing through（Or without）After processing, by data transmission set,
Computer equipment input port is sent to based on certain frame per second.
Reception of the computer input port to image or video stream data from above-mentioned transmission equipment, and the data to
The reading operation of hard disc of computer.For the real time data having been read into, with matrix morphology following function, quilt in image is drawn
The real-time matrix morphology data of monitoring object.Search, the abnormal posture for specifying matrix morphology, pass through database middle skeleton form
（Group）With the comparison of real-time matrix morphology, the similarity degree of the latter before judgement.In similarity measurement standard and whether send warning
In the case that the threshold value of signal is previously set, can the qualitative state that is shown of matrix morphology in real time whether can determine whether to be " different
Normal state ".Real-time matrix morphology data for meeting the above " abnormality ", system could be made that corresponding warning to notify prison
Shield personnel.On the premise of monitoring function normal operation is not influenceed, real-time matrix morphology data will be released or be stored into prison
Among the record of shield, and it is available for calling once again.
Beneficial effects of the present invention：It can detect and warn going out for the illness that specific morbidity posture is presented during some morbidities
It is existing so that the monitoring to sufferer adds real-time biological identification technology on the basis of physical signs, contribute to care provider and
Medical personnel take corresponding urgent emergency measures in time, have further ensured health of human body safety.
Brief description of the drawings
Fig. 1 is redundant module schematic diagram；
Fig. 2 is that skeleton contrasts program circuit.
Embodiment
, it is necessary to carry out corresponding software and database preparation to computer before the monitoring system comes into operation.
In terms of application software, computer should support the compiling and operation of the language such as C++；
The database of skeleton identification is with stacking hourglass network（Stacked Hourglass Network）Realize.For image
Pose detection, be low-res by picture breakdown using convolution method in very high resolution image and attempt to look for human synovial
Characteristic point；The thermal map that will be drawn afterwards with warp area method in aforementioned operation（Heatmap）Recombinated, finally obtain a secondary tool
There is the thermal map of personage's individual pose feature.Human skeleton is the Topology connection of joint characteristic point.
Above-mentioned convolution and deconvolution process, shaped like hourglass, turn into single hourglass module in pixel scale feature.It is each husky
Redundant module is inserted in stripping pattern block, i.e., by the result of lower processing in artwork and artwork（The minimum resolution that convolutional calculation obtains）
The process of superposition, can Reduction Computation machine process memory space.
And the network that the data place of the present invention is used is end to end including 8 single hourglass modules, turns into and stack hourglass net
Network.This convolution repeatedly/deconvolution processing to input picture is advantageous to more accurately refine last pose detecting effect.
The maximum resolution of hourglass module pair is arranged to 64x64.Whole network originates from the 7x7 convolutional layers that stride is 2, after
A redundant module and once maximum pond are connect, resolution is down to 64 from initial 256.Access redundant module twice afterwards,
Finally hourglass configuration is connect again.In whole hourglass configuration, redundant module will export 256 features（Point）.
The study of hourglass network needs reference scale of the database of standard as training.The database that we choose includes
FLIC and MPII Human Pose.FLIC includes 5003 the image from film（3987 learn images and 1016
Test image）.All most of personages are marked with half body to showing in image.MPII Human Pose are then included about
25000 images, count the mark of more people's images in, share about 40000 mark samples（28000 learn samples and 11000
Learn sample）.Because of the mark without test, the subfamily for learning sample is learnt in experiment, and uses the 3000 of definite value
Individual checking series is evaluated.MPII includes being shot from the mankind's activity of broad range, comprising a series of whole body postures
Image.
Hourglass network except carrying out pose identification to personage's individual in given image, the database required for this patent
Also typical pose during epilepsy invasion is included.
Following description describe and the epileptic specified in ward is carried out remotely using the human skeleton identifying system
Some details and running points for attention of patient's states monitoring.
In addition to meeting the minimalist configuration on monitoring system hardware and software, detected environment, which should try one's best, meets following bar
Part：
A1, detection environment are ward, and background arrangement should try one's best simply, for example, the wall of monitoring direction and ground, sick bed and other
The ornaments of furniture so that detected person is that the profile of patient is easy to extract；
Blocking for object should be avoided between a2, image capture device and monitored person as far as possible.In some monitoring situation such as whole bodies
Property spasm, it is generally desirable to adopt to obtain the whole body skeletal gesture of monitored person as in the range of entirely, shelter is present can to a certain extent
Influence the comparison and judgement of skeleton identification Compare System；
If a3, adopting as moveable condition is not present in the shooting of equipment, its pose should be fixed so that monitored people is in fixation
Background under state change become apparent, so as to the more stable operation of detection function.
When occur medical personnel for some reason can not in detection ambient scene situation about being monitored, can set manually or timing from
It is dynamic to run the skeleton identifying system；If multiple monitoring of environmental be present, the system can also be according to the period need of indivedual monitoring of environmental
Ask, timesharing separated time journey operation skeleton identifying system.
Adopt as equipment with given frame per second carries out adopting picture to monitoring of environmental；Gathered image enters computer by transmission equipment
Data-in port, wait the reading of computer.
After skeleton identifying system brings into operation, first ejection is set panel by display device, and detection function is adjusted for user
Correlated variables, timesharing separated time journey as the aforementioned, the selectivity in institute's data storage storehouse calls, effective model of qualitative " danger " state
Enclose, and sending method of alarm, etc..
After computer completes the reading of image stream, called by skeleton identifying system module.
The situation of monitored environment passes through odd number or plural display device real-time projection；And simultaneously, for being monitored environment
In the also circular flow of skeleton identification function；The skeleton state of the monitored personnel detected by identification function will be by " rod
The simple topology combination of bar " and " tie point ", is shown in same interface with the image of monitored environment in real time.
Above-mentioned skeleton state will also be called by comparison function, and calculate the state with being adjusted shown while simultaneously
Degree is overlapped with the state of the abnormal skeleton state stored in database, and show that both is " similar with given quantized versions
Degree "；By " similarity " of quantization compared with default threshold value.
Comparative result in above-mentioned steps can be represented simply with class Boolean, that is, judge that the state of current monitored person is " non-
It is dangerous " or " danger ".If qualitative is " not dangerous ", alarm function is not triggered；If qualitative is " precarious position ", will call
Alarm module, triggering start the type of alarm previously selected（Sound rings, vibration, flash of light, etc.）；It can sound all clear manually and temporary transient
The alarm function closed in skeleton identifying system.After the completion of skeleton identification process, institute's calling figure picture will be deposited according to setting in advance
Storage or directly release, and continue to perform identification and comparison module to next two field picture.
With morbidity's alarm Medical Devices based on skeleton identification, can closely be guarded such as in the non-of medical personnel
The behavior state for object patient is kept to carry out remote monitoring when rest.This measure can effectively improve medical personnel's
Operating efficiency, while can still ensure the life and health safety of related human patients.
Claims (4)
- The medical system 1. morbidity based on skeleton identification alarms, it is characterised in that：Including visible terminal, for real-time Check patient activity's situation and skeletal gesture；Image capture module, for being in real time the image needed for the collection of visible terminal Or video flowing；Data transmission module, for carrying out image or video stream data transmission in real time；Storage module, for storing in advance Complete the dangerous matrix morphology data of collection；Processing module, will for handling the image or video flowing of image capture module collection Image or video flowing are converted into real-time matrix morphology data；Transfer the dangerous matrix morphology data needed for storage module, and with Real-time matrix morphology data are contrasted, judge similarity；Optoacoustic equipment, for being judged in real time according to visible terminal Abnormal conditions send warning.
- The medical system 2. morbidity according to claim 1 based on skeleton identification alarms, it is characterised in that：It is also wrapped Interactive module is included, it includes being used for the User Interface for realizing monitoring function.
- The detection method of medical system 3. the morbidity based on skeleton identification alarms, it is characterised in that：Comprise the following steps that：Step 1：Video collecting device is called to carry out:The acquirement of image or video flowing；Step 2：Acquired obtained image or video stream data are sent to computer equipment input by data transmission set Mouthful；Step 3：Computer input port receives to the image in step 2 or video stream data, and carries out the data to meter The reading operation of calculation machine hard disk；Step 4：For the real time data having been read into, the reality of monitored target in image is drawn with matrix morphology following function When matrix morphology data；Step 5：Search for storage module in specify matrix morphology abnormal attitude data, by abnormal attitude data in database with The comparison of real-time matrix morphology data, the similarity degree of the latter before judgement；Step 6：According to similarity degree in step 5, whether the state that matrix morphology is shown qualitative in real time can determine whether as exception State；Step 7：It is judged as the real-time matrix morphology data of abnormality for step 6, system could be made that warning.
- The detection method of medical system 4. the morbidity according to claim 3 based on skeleton identification alarms, its feature It is：Also include step 8：The matrix morphology data in real time will be released or be stored among the record of monitoring, for once again Call.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710621799.XA CN107495971A (en) | 2017-07-27 | 2017-07-27 | Morbidity's alarm medical system and its detection method based on skeleton identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710621799.XA CN107495971A (en) | 2017-07-27 | 2017-07-27 | Morbidity's alarm medical system and its detection method based on skeleton identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107495971A true CN107495971A (en) | 2017-12-22 |
Family
ID=60689896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710621799.XA Pending CN107495971A (en) | 2017-07-27 | 2017-07-27 | Morbidity's alarm medical system and its detection method based on skeleton identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107495971A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109002783A (en) * | 2018-07-02 | 2018-12-14 | 北京工业大学 | Rescue the human testing in environment and gesture recognition method |
| CN109299685A (en) * | 2018-09-14 | 2019-02-01 | 北京航空航天大学青岛研究院 | Deduction network and its method for the estimation of human synovial 3D coordinate |
| CN109376673A (en) * | 2018-10-31 | 2019-02-22 | 南京工业大学 | A kind of coal mine down-hole personnel unsafe acts recognition methods based on human body attitude estimation |
| CN110364253A (en) * | 2018-04-11 | 2019-10-22 | 西门子医疗有限公司 | The system and method that patient for auxiliary positions |
| CN113421641A (en) * | 2021-06-30 | 2021-09-21 | 重庆医科大学 | Eclampsia patient protection device and prediction system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102113034A (en) * | 2008-05-12 | 2011-06-29 | 阿列森斯有限公司 | Monitoring, predicting and treating clinical episodes |
| CN105787439A (en) * | 2016-02-04 | 2016-07-20 | 广州新节奏智能科技有限公司 | Depth image human body joint positioning method based on convolution nerve network |
| CN106073792A (en) * | 2016-06-08 | 2016-11-09 | 惠州学院 | A kind of human motion posture analyzing system |
-
2017
- 2017-07-27 CN CN201710621799.XA patent/CN107495971A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102113034A (en) * | 2008-05-12 | 2011-06-29 | 阿列森斯有限公司 | Monitoring, predicting and treating clinical episodes |
| CN105787439A (en) * | 2016-02-04 | 2016-07-20 | 广州新节奏智能科技有限公司 | Depth image human body joint positioning method based on convolution nerve network |
| CN106073792A (en) * | 2016-06-08 | 2016-11-09 | 惠州学院 | A kind of human motion posture analyzing system |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110364253A (en) * | 2018-04-11 | 2019-10-22 | 西门子医疗有限公司 | The system and method that patient for auxiliary positions |
| CN110364253B (en) * | 2018-04-11 | 2024-03-01 | 西门子医疗有限公司 | System and method for assisted patient positioning |
| CN109002783A (en) * | 2018-07-02 | 2018-12-14 | 北京工业大学 | Rescue the human testing in environment and gesture recognition method |
| CN109299685A (en) * | 2018-09-14 | 2019-02-01 | 北京航空航天大学青岛研究院 | Deduction network and its method for the estimation of human synovial 3D coordinate |
| CN109376673A (en) * | 2018-10-31 | 2019-02-22 | 南京工业大学 | A kind of coal mine down-hole personnel unsafe acts recognition methods based on human body attitude estimation |
| CN109376673B (en) * | 2018-10-31 | 2022-02-25 | 南京工业大学 | Method for identifying unsafe behaviors of underground coal mine personnel based on human body posture estimation |
| CN113421641A (en) * | 2021-06-30 | 2021-09-21 | 重庆医科大学 | Eclampsia patient protection device and prediction system |
| CN113421641B (en) * | 2021-06-30 | 2023-01-10 | 重庆医科大学 | Eclampsia patient protection device and prediction system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107495971A (en) | Morbidity's alarm medical system and its detection method based on skeleton identification | |
| Chaudhuri et al. | Fall detection devices and their use with older adults: a systematic review | |
| CN101977302B (en) | System and method for monitoring of sleep security | |
| CN101937605B (en) | Sleep monitoring system based on face detection | |
| CN110477925A (en) | A kind of fall detection for home for the aged old man and method for early warning and system | |
| CN101937606B (en) | Sleep monitoring system and method for quilt kicking alarm | |
| JPWO2016147770A1 (en) | Monitoring system and monitoring method | |
| CN101937604A (en) | Sleep monitoring system based on human body detection and method thereof | |
| CN109492595B (en) | Behavior prediction method and system suitable for fixed group | |
| US20050196023A1 (en) | Method for real-time remote diagnosis of in vivo images | |
| Anishchenko | Machine learning in video surveillance for fall detection | |
| US9408562B2 (en) | Pet medical checkup device, pet medical checkup method, and non-transitory computer readable recording medium storing program | |
| Fan et al. | Fall detection via human posture representation and support vector machine | |
| CN107072548A (en) | For people orientation and/or position automatic detection equipment, system and method | |
| CN112957042B (en) | Non-contact target emotion recognition method and system | |
| CN109891516A (en) | Equipment, system and method for patient-monitoring to predict and prevent bed from falling | |
| CN109543607A (en) | Object abnormal state detection method, system, monitor system and storage medium | |
| CN109863562A (en) | For carrying out patient-monitoring to predict and prevent the equipment, system and method for falling from bed | |
| Gjoreski et al. | Context-based fall detection and activity recognition using inertial and location sensors | |
| CN109952615A (en) | Queue for patient-monitoring | |
| CN108882853A (en) | Measurement physiological parameter is triggered in time using visual context | |
| CN104506809B (en) | A kind of severe sufferer monitoring system based on intelligent video | |
| CN112036267A (en) | Target detection method, device, equipment and computer readable storage medium | |
| US20210400920A1 (en) | Livestock stillbirthing alerting system | |
| CN115482485A (en) | Video processing method and device, computer equipment and readable storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 116023 Room 1 203, Block 12, Block C, 6 Yiyang Road, Qixianling, Dalian High-tech Industrial Park, Liaoning Province Applicant after: Hechuang Lazy Man (Dalian) Technology Co., Ltd. Address before: 116023 Dalian High-tech Park, Liaoning Province, Takeoff Software Park Phase II 1-04B Applicant before: Dalian and the creation of lazy Technology Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171222 |