CN116453038A - Intelligent aging-assisting nursing method and device based on vision - Google Patents
Intelligent aging-assisting nursing method and device based on vision Download PDFInfo
- Publication number
- CN116453038A CN116453038A CN202310112620.3A CN202310112620A CN116453038A CN 116453038 A CN116453038 A CN 116453038A CN 202310112620 A CN202310112620 A CN 202310112620A CN 116453038 A CN116453038 A CN 116453038A
- Authority
- CN
- China
- Prior art keywords
- module
- vision
- intelligent
- key point
- model
- 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
- 230000000474 nursing effect Effects 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 14
- 230000009471 action Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 230000000694 effects Effects 0.000 claims description 6
- 230000006399 behavior Effects 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000013136 deep learning model Methods 0.000 claims description 3
- 238000001931 thermography Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000012544 monitoring process Methods 0.000 description 6
- 206010001488 Aggression Diseases 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000001012 protector Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000009191 jumping Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000001454 recorded image Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/22—Social work
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
-
- 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
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses an intelligent nursing method and device for helping the aged based on vision, which relate to the technical field of nursing for helping the aged.
Description
Technical Field
The invention belongs to the technical field of nursing for the elderly, and particularly relates to an intelligent nursing method and device for the elderly based on vision.
Background
The nursing home is a professional organization for providing aged people with nursing services, such as life nursing, physical rehabilitation, mental comfort, cultural entertainment, physical exercise, safe life and the like in daily life of the aged, and at present, most of the nursing institutions are occupied by aged people with living incapable of self-care, and can be divided into different types of nursing home according to different setting purposes, support subjects and service objects;
at present, the monitoring camera is installed in the nursing home in cooperation with the supervision mode of the patrol manager, so that the behavior action of the old can not be performed in real time, special situations possibly occur, service personnel can monitor the violent behavior of the old and illegal intrusion of strangers in real time and accurately judge the violent behavior, and the mood and the comfortableness of living life of the old are affected.
Therefore, there is a need to provide an intelligent care method and device for the elderly people based on vision, which aims to solve the above problems.
Disclosure of Invention
The invention aims to provide an intelligent nursing method and device for helping old people based on vision, which solve the problem that the prior art cannot monitor and identify several abnormal conditions in a nursing home in real time and analyze and judge in time through the design of the intelligent nursing method for helping old people, the intelligent management system for the nursing home, a functional module and a core algorithm module.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to an intelligent nursing method and device for helping old people based on vision, comprising an intelligent nursing method for helping old people based on vision, an intelligent nursing system for nursing home, a functional module and a core algorithm module, wherein the intelligent nursing method for helping old people based on vision is provided with a data acquisition module, and the data acquisition module is provided with a plurality of infrared cameras and a main server;
the intelligent care method based on vision is connected with an application deployment module, and the application deployment module comprises a PC (personal computer) for running an intelligent care management system;
the intelligent pension management system is connected with a data processing module, and the data processing module has a video stream decoding processing function and a pedestrian recognition tracking function;
the intelligent pension management system is provided with a functional module, and the functional module is provided with a violence recognition unit which is performed based on a deep learning model trained on a public data set;
the functional module is provided with an attendance recording unit, the attendance recording unit mainly depends on a key point detection model, detects key points of a worker body by using an advanced human body key point detection technology, and records position coordinates corresponding to each frame;
the function module is provided with a stranger intrusion recording unit, visiting relatives and friends need to register and record face information in the foreground in advance, and when a person enters a room, the face characteristics of the person are matched with visiting relatives and friends characteristics recorded in the database through a face recognition algorithm;
the functional module is provided with a fall detection unit, the fall detection unit consists of two models, namely a human body key point identification model and a fall behavior identification model, the human body key point model is consistent with the key point identification model used by the attendance recording unit, the network structure used by the fall detection model is ST-GCN, and the fall detection unit is trained by using a public data set UR Fall Detection Dataset;
the intelligent pension management system is provided with a core algorithm module, and the core algorithm module is provided with a face recognition unit, a pedestrian recognition unit, a target tracking unit, a human body key point recognition unit, an action recognition unit and a result output unit, so that the effects of detecting and processing face information of pedestrians and workers, tracking targets, marking and positioning main key points of human bodies, recognizing actions and transmitting recognized information are realized.
Preferably, the ST-GCN model is specifically composed of a graph convolution network and a time convolution network.
Preferably, the functional module is connected with infrared cameras, the number of the infrared cameras is N, and meanwhile, the angle and the position can be adjusted according to different actual scenes.
Preferably, the ST-GCN model is specifically composed of a graph convolution network and a time convolution network.
Preferably, the functional module is connected with infrared cameras, the number of the infrared cameras is N, and meanwhile, the angle and the position can be adjusted according to different actual scenes.
Preferably, the infrared camera is connected with the main server through a wireless network.
Preferably, the main server is connected with a PC.
Preferably, the infrared camera is specifically an infrared thermal imaging camera.
The invention has the following beneficial effects:
1. according to the intelligent nursing method based on vision, the data acquisition module, the intelligent nursing management system, the functional module, the core algorithm module and the data processing module are designed, the data acquisition module is composed of the monitoring camera and is deployed in the nursing home, so that the nursing home can conveniently find out several abnormal conditions in the nursing home in time, different types of events are classified through each unit arranged in the functional module, and detection and analysis are carried out after target key points are captured through each unit arranged in the core algorithm module, therefore, the effects of high identification accuracy and high evaluation efficiency can be achieved, the effect of timely feeding back to a user side is achieved, the living safety of the old is improved, and timely rescue can not be obtained when accidents happen.
2. The invention adopts the design of a core algorithm module and an attendance management module, and compares the face coordinates with a face base by monitoring, identifying and confirming the face, matching the successfully compared face frame coordinate frame with the key point coordinates, counting the frame number after ID corresponding to the worker in a mode of counting once every five seconds, and finally forming the total worker time result of the worker according to the total time of each day of each ID, thereby effectively counting the working time of the worker.
Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of an intelligent nursing method based on vision and an intelligent management system of a nursing home and an integral connection structure of each module;
FIG. 2 is a schematic diagram of the overall connection structure of a data acquisition module with a functional module and a core algorithm module;
fig. 3 is a schematic diagram of the overall connection structure of each hardware in the intelligent management system of the nursing home;
fig. 4 is a schematic diagram of an overall connection structure of a monitoring flow of the intelligent management system of the nursing home.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-4, the invention discloses an intelligent aging-aiding nursing method and device based on vision, comprising an intelligent aging-aiding nursing method based on vision, an intelligent nursing system of a nursing home, a functional module and a core algorithm module, wherein the intelligent aging-aiding nursing method based on vision is provided with a data acquisition module, the data acquisition module is provided with a plurality of infrared cameras and a main server, the infrared cameras are used for acquiring and recording video stream data under each scene, and the server processes the acquired video stream data and learns the model reasoning deeply;
the intelligent care method based on vision is connected with an application deployment module, the application deployment module comprises a PC (personal computer) for running an intelligent care management system, video pictures recorded by all infrared cameras can be displayed in real time, and a scene with problems can be fed back to the application deployment module in time after the calculation of a main server;
the intelligent endowment management system is connected with a data processing module, and the data processing module has a video stream decoding processing function and a pedestrian recognition tracking function, can decode video stream data from a plurality of paths of infrared cameras in real time, and processes the video stream data into input data required by each model in a violence recognition unit, an attendance recording unit, a stranger intrusion recording unit and a fall detection unit;
the intelligent care management system is provided with a functional module, the functional module is provided with a violence recognition unit, the violence recognition unit is carried out based on a deep learning model obtained by training on a public data set, the basic structure of the model adopts a Resnet50 frame comprising a Temporal Shift Module module, an image sequence with an input part of 1*8 is output as a classification result of whether violence exists, the classification result is obtained through prediction of the model, data processing is carried out every eight seconds for video data from infrared monitoring, a frame sequence of 8 dimensions is formed according to time sequence after randomly extracting one frame in each second of the first 8 seconds, and the data is sent into the model for classification prediction after preprocessing such as super resolution, denoising and the like to obtain result data for judging whether the violence exists in the current 8 seconds;
the functional module is provided with an attendance recording unit, the attendance recording unit mainly depends on a key point detection model, the network structure of the key point detection model is based on openpost, the network structure is obtained by training on a public data set coco, the network structure is input into a frame of picture, 18 body key point coordinates of a plurality of persons are output, the network structure is consistent with the coordinates on the coco data set, an advanced human body key point detection technology is utilized to detect key points of a worker body, the position coordinates corresponding to each frame of the key points are recorded, so that the position of the worker is tracked, the recording duration is long, when the worker faces a camera, the face characteristics of the worker are extracted through the face recognition technology, the face characteristics in a database are compared, so that the identity of the worker is determined, and when the worker leaves a room, the record is ended, so that the flexible recording of the working time of the worker is realized;
the function module is provided with a stranger intrusion recording unit, visiting relatives and friends need to register and record face information in the foreground in advance, when a person enters a room, the face characteristics of the person are matched with visiting relatives and friends characteristics recorded in the database through a face recognition algorithm, and if the face characteristics are not matched with the visiting relatives and friends characteristics, a stranger intrusion warning is sent to the foreground;
the functional module is provided with a fall detection unit, the fall detection unit consists of two models, namely a human body key point identification model and a fall behavior identification model, the human body key point model is consistent with the key point identification model used by the attendance recording unit, the network structure used by the fall detection model is ST-GCN, the public data set UR Fall Detection Dataset is used for training, the input of the model is a human body key point coordinate sequence vector, the network mainly consists of a space-time diagram convolution module and a residual error module, finally, a softmax classifier is used for obtaining the identification result of whether falling or not, the space-time diagram convolution is easy to obtain the relation between different key points and the same key point at different moments, the method for identifying falling from a single Zhang Jingtai image is easy to judge lying flat and jumping into falling due to neglect of action continuity, the falling detection is based on the ST-GCN model, the model takes the time sequence of the human body key point as input, the space-time change relation of the key points is easy to capture the space-time change relation of the key points, the lying flat and jumping can be effectively prevented from being misjudged into falling, in practical application, a transmission picture in each picture is easy to capture the space-time change of the key point, the human body coordinate is sent into the network coordinate after the key point is detected through the key point identification algorithm, and the key point is sent into the network coordinate to the relevant image detection algorithm to the human body coordinate for people if the key point is generated by the key point identification model;
the intelligent pension management system is provided with a core algorithm module, and the core algorithm module is provided with a face recognition unit, a pedestrian recognition unit, a target tracking unit, a human body key point recognition unit, an action recognition unit and a result output unit, so that the effects of detecting and processing face information of pedestrians and workers, tracking targets, marking and positioning main key points of human bodies, recognizing actions and transmitting recognized information are realized.
Working principle: before the device is used, hardware is installed, a plurality of infrared cameras are arranged, the infrared cameras are installed at different positions according to actual scenes, angles are adjusted, the infrared cameras can shoot all-around non-blind areas of an environment picture, meanwhile, the installed infrared cameras are connected with a main server through a network, the real-time transmission of pictures shot by the infrared cameras to the main server is realized, the main server is connected with a PC through the network, so that picture information transmitted into the main server is uploaded to the PC end in real time, and different areas and room information are monitored in real time through a display panel of the PC end;
when the violent behavior is analyzed, an intelligent endowment management system is installed on a PC, an environment picture is monitored and recorded through an infrared camera arranged by a data acquisition module and fed back to the intelligent endowment management system in real time, firstly, picture information is decoded through an violent recognition module, human faces are detected and recognized through an image frame list, human face frame coordinates and characteristic sequences are formed, meanwhile, key detection is carried out on human bodies of pedestrians in the image frame list, 18 human body key point coordinate sequences are formed for each pedestrian in each frame, meanwhile, the human face frame coordinates and the characteristic sequences are compared with a human face ground library, when the comparison is abnormal with the human face ground library, the current human face picture is cut according to the coordinates, the picture and the characteristic are stored in the abnormal library, the early warning prompt is given when the picture and the characteristic are confirmed to be a stranger intruder, and after the comparison is successful with the human face ground library, matching face coordinates with key point coordinates, performing tumble behavior recognition on an old man corresponding to an ID (identity) and a limb key point sequence, judging by combining multi-frame limb key point sequences, counting the number of frames of a protector according to a mode of five seconds each time when successful recognition is performed, counting the number of frames according to a mode of five seconds each time when the ID corresponds to the protector, counting the number of frames according to the ID corresponding to each protector when the ID corresponds to the frame, counting the number of frames according to a mode of five seconds each time when successful recognition is performed, finally obtaining a valid man-hour result of the protector when the ID total worker is counted according to a counting mode of one time each day, forming an 8-frame picture frame sequence by input preprocessing through violence recognition in an image frame list, performing violence recognition, detecting that violence does not exist when the violence recognition result is 0, and detecting that the violent behavior exists when the violent recognition result is 1.
Further, the ST-GCN model is specifically composed of a graph convolution network and a time convolution network.
Further, the functional module is connected with infrared cameras, the number of the infrared cameras is N, meanwhile, the angle and the position can be adjusted according to different actual scenes, the effect of no dead angle omnibearing monitoring in the scenes is achieved, the mind rejection degree of monitored personnel is relieved, and when violent personnel and strangers break into opponents to threaten life and property, damage to probe equipment by the strangers is avoided.
Further, the infrared thermal imaging camera is connected with the main server through a wireless network, the infrared camera shoots and records indoor scenes, the indoor scenes are transmitted to the main server through the wireless network, and the shot and recorded image information is edited and processed through the main server.
Further, the main server is connected with a PC, the main server feeds back the received data information to the PC, the PC is provided with a display panel and a control panel, the received data information is edited and controlled through the PC, and meanwhile, the picture information in a plurality of rooms is uploaded to the display panel of the PC in real time, so that background personnel can monitor the picture information in the plurality of rooms in real time.
Further, the temperature field on the surface of the object can be reflected, so that personnel intrusion and violent behavior actions can be shot and recorded better, and the accuracy of the key point marks on the marks of the human body parts is improved.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean 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 present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (6)
1. The utility model provides an intelligence helps old nurse method and device based on vision, includes intelligence based on vision helps old nurse method, nursing home intelligent management system, functional module and core algorithm module, its characterized in that: the intelligent aging-assisting nursing method based on vision is provided with a data acquisition module, wherein the data acquisition module is provided with a plurality of infrared cameras and a main server;
the intelligent care method based on vision is connected with an application deployment module, and the application deployment module comprises a PC (personal computer) for running an intelligent care management system;
the intelligent pension management system is connected with a data processing module, and the data processing module has a video stream decoding processing function and a pedestrian recognition tracking function;
the intelligent pension management system is provided with a functional module, and the functional module is provided with a violence recognition unit which is performed based on a deep learning model trained on a public data set;
the functional module is provided with an attendance recording unit, the attendance recording unit mainly depends on a key point detection model, detects key points of a worker body by using an advanced human body key point detection technology, and records position coordinates corresponding to each frame;
the function module is provided with a stranger intrusion recording unit, visiting relatives and friends need to register and record face information in the foreground in advance, and when a person enters a room, the face characteristics of the person are matched with visiting relatives and friends characteristics recorded in the database through a face recognition algorithm;
the functional module is provided with a fall detection unit, the fall detection unit consists of two models, namely a human body key point identification model and a fall behavior identification model, the human body key point model is consistent with the key point identification model used by the attendance recording unit, the network structure used by the fall detection model is ST-GCN, and the fall detection unit is trained by using a public data set UR Fall Detection Dataset;
the intelligent pension management system is provided with a core algorithm module, and the core algorithm module is provided with a face recognition unit, a pedestrian recognition unit, a target tracking unit, a human body key point recognition unit, an action recognition unit and a result output unit, so that the effects of detecting and processing face information of pedestrians and workers, tracking targets, marking and positioning main key points of human bodies, recognizing actions and transmitting recognized information are realized.
2. The vision-based intelligent care-for-aged method and device according to claim 1, wherein the ST-GCN model is composed of a graph convolution network and a time convolution network.
3. The vision-based intelligent aging-aiding nursing method and device according to claim 1, wherein the functional modules are connected with infrared cameras, the number of the infrared cameras is N, and meanwhile, the angle and the position of the functional modules can be adjusted according to different actual scenes.
4. The vision-based intelligent care-for-aged method and device according to claim 3, wherein the infrared camera is connected with the main server through a wireless network.
5. The vision-based intelligent care-for-old method and device according to claim 1, wherein the main server is connected with a PC.
6. The vision-based intelligent care-for-aged method and device according to claim 4, wherein the infrared camera is specifically an infrared thermal imaging camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310112620.3A CN116453038A (en) | 2023-02-14 | 2023-02-14 | Intelligent aging-assisting nursing method and device based on vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310112620.3A CN116453038A (en) | 2023-02-14 | 2023-02-14 | Intelligent aging-assisting nursing method and device based on vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116453038A true CN116453038A (en) | 2023-07-18 |
Family
ID=87122651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310112620.3A Pending CN116453038A (en) | 2023-02-14 | 2023-02-14 | Intelligent aging-assisting nursing method and device based on vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116453038A (en) |
-
2023
- 2023-02-14 CN CN202310112620.3A patent/CN116453038A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103517042B (en) | A kind of nursing house old man's hazardous act monitoring method | |
| CN106203458B (en) | Crowd video analysis method and system | |
| CN103839373B (en) | A kind of unexpected abnormality event Intelligent Recognition alarm device and warning system | |
| CN110321780B (en) | Abnormal falling behavior detection method based on space-time motion characteristics | |
| US9665777B2 (en) | System and method for object and event identification using multiple cameras | |
| CN106780250B (en) | Intelligent community security event processing method and system based on Internet of things technology | |
| CN112233300A (en) | Community passing epidemic prevention monitoring joint defense system and method based on artificial intelligence | |
| Shoaib et al. | View-invariant fall detection for elderly in real home environment | |
| JP2005506740A (en) | Video trip wire | |
| CN109377697A (en) | Rapid Alarm method of disposal under a kind of intensive camera head environment | |
| CN111564224A (en) | Intelligent monitoring system with health monitoring function and implementation method thereof | |
| CN114469076B (en) | Identity-feature-fused fall identification method and system for solitary old people | |
| CN113963301A (en) | Space-time feature fused video fire and smoke detection method and system | |
| Zambanini et al. | Detecting falls at homes using a network of low-resolution cameras | |
| KR102182660B1 (en) | System and method for detecting violence using spatiotemporal features and computer readable recording media storing program for executing method thereof | |
| Huang et al. | A method for fast fall detection | |
| CN111612815A (en) | Infrared thermal imaging behavior intention analysis method and system | |
| CN112330742A (en) | Method and device for recording activity routes of key personnel in public area | |
| CN116453038A (en) | Intelligent aging-assisting nursing method and device based on vision | |
| CN115798047A (en) | Behavior recognition method and apparatus, electronic device, and computer-readable storage medium | |
| KR20230064095A (en) | Apparatus and method for detecting abnormal behavior through deep learning-based image analysis | |
| CN111832451A (en) | Airworthiness monitoring process supervision system and method based on video data processing | |
| CN112686146A (en) | Passenger flow analysis method, device and system based on facial feature recognition | |
| Yu et al. | Fall detection and alert for ageing-at-home of elderly | |
| CN112101078A (en) | Intelligent behavior analysis system applied to prison site |
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 |