CN116778666A - Child motion safety monitoring system and method - Google Patents
Child motion safety monitoring system and method Download PDFInfo
- Publication number
- CN116778666A CN116778666A CN202310802758.6A CN202310802758A CN116778666A CN 116778666 A CN116778666 A CN 116778666A CN 202310802758 A CN202310802758 A CN 202310802758A CN 116778666 A CN116778666 A CN 116778666A
- Authority
- CN
- China
- Prior art keywords
- module
- child
- alarm
- server
- video
- 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
- 230000033001 locomotion Effects 0.000 title claims abstract description 54
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012544 monitoring process Methods 0.000 title claims abstract description 24
- 230000009471 action Effects 0.000 claims abstract description 19
- 238000012216 screening Methods 0.000 claims abstract description 11
- 238000003062 neural network model Methods 0.000 claims abstract description 9
- 210000003108 foot joint Anatomy 0.000 claims abstract description 4
- 238000000605 extraction Methods 0.000 claims description 12
- 230000003238 somatosensory effect Effects 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000005259 measurement Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000000926 separation method Methods 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 2
- 210000001503 joint Anatomy 0.000 description 5
- 210000003127 knee Anatomy 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 210000004394 hip joint Anatomy 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0205—Specific application combined with child monitoring using a transmitter-receiver system
- G08B21/0208—Combination with audio or video communication, e.g. combination with "baby phone" function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
-
- 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
- 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
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0277—Communication between units on a local network, e.g. Bluetooth, piconet, zigbee, Wireless Personal Area Networks [WPAN]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/243—Image signal generators using stereoscopic image cameras using three or more 2D image sensors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/271—Image signal generators wherein the generated image signals comprise depth maps or disparity maps
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/275—Image signal generators from 3D object models, e.g. computer-generated stereoscopic image signals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/20—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from infrared radiation only
- H04N23/23—Cameras or camera modules comprising electronic image sensors; Control thereof for generating image signals from infrared radiation only from thermal infrared radiation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/61—Control of cameras or camera modules based on recognised objects
- H04N23/611—Control of cameras or camera modules based on recognised objects where the recognised objects include parts of the human body
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Child & Adolescent Psychology (AREA)
- Emergency Management (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Toxicology (AREA)
- Computer Networks & Wireless Communication (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Alarm Systems (AREA)
Abstract
The application relates to the technical field of motion capture and analysis, in particular to a child motion safety monitoring method, which comprises the following steps: s1: the sports ground is provided with a plurality of monitoring cameras for video acquisition; s2: screening main joint points of a human body, and extracting to generate a neural network model; s3: counting coordinate data of each node; s4: calculating the movement speed of the foot joint point; s5: identifying a rapid movement; s6: inverted motion recognition S7: the alarm module acquires the alarm information sent by the server, controls the alarm of the sport area to send out alarm sound prompt, and alerts the guardian to timely take care of the children. The method analyzes the video in the motion range in real time, and immediately gives an alarm once a preset dangerous motion occurs, so that the real-time performance is high; the dangerous action data is judged simply, conveniently, efficiently and quickly, and the universality of video acquisition hardware is good.
Description
Technical Field
The application relates to the technical field of motion capture and analysis, in particular to a child motion safety monitoring system and method.
Background
The application discloses a kindergarten monitoring method based on a somatosensory technology, which is characterized in that motion feature vectors are constructed by screening joint coordinates of children to pre-judge dangerous motions of the children, and the scheme has the defects of complex operation, large calculated amount and inaccurate matching, so that a child motion safety monitoring system and method with more accurate monitoring and small calculated amount are required to be designed.
Disclosure of Invention
The application aims to provide a child motion safety monitoring system and a child motion safety monitoring method, which are used for solving the defects of complicated operation, large calculated amount and inaccurate matching of the existing system.
The basic scheme provided by the application is as follows: a child motion safety monitoring method comprising the steps of:
s1: setting a 3D somatosensory camera on a sports ground and collecting video;
s2: screening main joint points of a human body, extracting and generating a neural network model, dividing the video in the S1 into images, and screening the joint points by using the neural network model;
s3: counting the coordinate data of each node selected in the S2;
s4: calculating the movement speed of the foot joint point in the step S3, and identifying the rapid movement;
s5: performing falling action recognition according to the coordinate data of the S3 articulation point;
s6: performing inverted motion recognition according to the coordinate data of the S3 articulation point;
s7: the server judges and recognizes dangerous actions in S4 to S6 and generates warning information, and the warning module acquires the warning information sent by the server and controls the warner of the sport area to send out warning sound prompt so as to warn the guardian to timely take care of the children.
The principle and the advantages of the application are as follows: through the 3D somatosensory equipment, a 3D human skeleton joint image of the child is captured in real time, key joint point coordinates are extracted, joint point movement speed is calculated and compared with a preset value, and warning information and alarm are generated. The method analyzes the video in the motion range in real time, and immediately gives an alarm once a preset dangerous motion occurs, so that the real-time performance is high; judging dangerous action data is simple and convenient, and only a small amount of action videos are required to be acquired; the multi-path video stream is analyzed simultaneously, and compared with the traditional human eye retrieval, the method is efficient and quick; the video acquisition hardware has good universality.
Further, S2 includes the following steps:
s2-1: importing a data training model;
s2-2: the child camera video is imported, the embodiment utilizes the skeleton tracking function of Kinect, and the body of the child is distinguished from a complex background by adopting a separation strategy;
s2-3: and screening joint points.
Further, S3 includes the following steps:
s3-1: three-dimensional coding is carried out on the measurement space;
s3-2: and counting three-dimensional coordinate data of each joint point at the same time.
Further, S4 includes the following steps:
s4-1: the embodiment adopts the coordinates of the left foot of the child to calculate the instantaneous movement speed of the child;
s4-2: and the server judges whether to generate warning information according to the preset value.
The application also provides a child motion safety monitoring system, which executes the method for monitoring the child motion safety, and comprises the following steps: the system comprises a camera, an alarm and a server; the camera comprises a camera module and a joint point extraction module, and the server comprises an action recognition module, an alarm module and a storage module;
and the camera module: the system comprises a joint point extraction module, a video data acquisition module, a video data transmission module and a video data transmission module, wherein the video data acquisition module is used for acquiring video data, and a 3D somatosensory camera is selected as video acquisition hardware to transmit video data in the range of a child motion place to the joint point extraction module;
the node extraction module: the method comprises the steps of selecting a human body joint point to extract and generate a neural network model, and sending the model to a server;
the action recognition module: the method comprises the steps of establishing space coordinates, counting the positions of the joints, calculating the movement speed of the joints, comparing the movement speed with a preset value, and judging whether warning information is generated or not;
and an alarm module: the alarm device is used for acquiring the alarm information sent by the server and controlling the alarm device in the sport area to send out an alarm sound prompt to warn the guardian to timely take care of the children;
and a storage module: for storing a dangerous action category, an occurrence time, a picture or a short video data to a server when a dangerous action occurs.
Drawings
FIG. 1 is a diagram of a segmentation mask according to an embodiment S2-2 of the present application;
FIG. 2 is a schematic diagram of screening main joint points of a human body according to the embodiment S2-3 of the present application;
FIG. 3 is a schematic view of three-dimensional coordinates of a joint point according to an embodiment S3 of the present application;
FIG. 4 is a graph showing the recognition of a fast-moving function according to the embodiment S4 of the present application;
FIG. 5 is a schematic view of three-dimensional coordinates of a joint point according to an embodiment S5 of the present application;
FIG. 6 is a schematic view of three-dimensional coordinates of an S6 joint point according to an embodiment of the present application
FIG. 7 is a system block diagram of an embodiment of the present application.
Detailed Description
The following is a further detailed description of the embodiments:
the examples are essentially as follows: a child motion safety monitoring method comprising the steps of:
s1: the sports ground is provided with a plurality of monitoring cameras for video acquisition;
the monitoring camera selects Kinect, which is a 3D somatosensory camera with color recognition, distance detection and skeleton tracking functions, and uses Kinect to pick up a video of a sports field child;
s2: screening main joint points of a human body, and extracting to generate a neural network model;
s2-1: importing a data training model: inputting data in TB into a system training model through a Microsoft Exemplar model;
s2-2: the video of the child is imported, the embodiment uses the skeleton tracking function of Kinect, and adopts a separation strategy to distinguish the body of the child from the complex background, and in this stage, as shown in fig. 1, a segmentation mask is created in the depth image for each tracked child, that is, an image segmentation method is adopted to exclude background images outside the human body.
S2-3: joint point screening, as shown in fig. 2, selecting the joint point with the highest weight in the body of the child: the steps from top to bottom are respectively as follows: head, shoulder center, left elbow, right elbow, left hand, right hand, hip joint, left knee, right knee, left foot, right foot;
s3: counting coordinate data of each node;
s3-1: the Kinect sensor irradiates a measured position of a child with continuous light emitted by an infrared emitter, records each speckle of a measurement space by an infrared CMOS camera, and performs three-dimensional coding on the measurement space by combining an original speckle pattern;
s3-2: as shown in FIG. 3, t is noted 1 The child number at the moment is marked as F 1 ，A 1 The coordinates are (x) 1 ,y 1 ,z 1 )，t 2 Time A 1 The coordinates are (x) 2 ,y 2 ,z 2 ) According to the statistics, the method comprises the following steps of,each node t in S2 1 The time three-dimensional coordinate data are as follows:
deriving the data as a matrix:
s4: calculating the movement speed of the foot joint point, and identifying the rapid movement;
s4-1: in this embodiment, the instantaneous movement speed of the child is calculated by using the coordinates of the left foot of the child, and the instantaneous speed is calculated every 2 seconds, and the calculation formula is as follows:
in this embodiment Δt is taken to be 2;
s4-2: because the child has the behavior of suddenly accelerating running in the playing process, if the child falls easily due to overlong fast running time, the child does not go well when running for a period of time, and in order to realize early warning, the child safety movement speed warning value is 5m/s, and when the child Tong Shunshi speed v is greater than 5m/s and lasts for 10 seconds, the server generates warning information; as shown in fig. 4, after 24 seconds, the instantaneous speed v of the child is greater than 5m/s, after 30 seconds, the instantaneous speed v is less than 5m/s, and the server can not generate warning information due to the duration time being less than 10 seconds, the 40 th to 56 th seconds, the instantaneous speed v of the child is greater than 5m/s and lasts more than 10 seconds, and the server generates warning information and sends the warning information to the alarm module;
s5: fall motion recognition;
as shown in fig. 5, when the child falls over on the front, the left knee, the right knee, the left hand and the right hand touch the ground; after the back falls, the head, shoulder center and hip joints are grounded, the Z coordinate is close to 0 when the joints are grounded, and the falling of the child is judged by continuously detecting the coordinates A5, A6, A8 and A9 or the coordinates A1, A2 and A7, and a server generates warning information and sends the warning information to an alarm module;
s6: performing inverted motion recognition; when the child tries to stand upside down or has been standing upside down, the head is positioned under the left and right feet, as shown in FIG. 6, head A 1 The coordinates are (x) 3 ,y 3 ,z 3 ) Right foot A 11 The coordinates are (x) 4 ,y 4 ,z 4 ) When z is detected 4 ＞z 3 The server generates warning information and sends the warning information to the alarm module;
s7: the alarm module acquires the alarm information sent by the server, controls the alarm of the sport area to send out alarm sound prompt, and alerts the guardian to timely take care of the children.
The embodiment of the application also provides a child motion safety monitoring system, which executes the method for monitoring the child motion safety, as shown in fig. 7, and comprises the following steps: the system comprises a camera, an alarm and a server; the camera comprises a camera module and a joint point extraction module, and the server comprises an action recognition module, an alarm module and a storage module;
and the camera module: the system comprises a joint point extraction module, a video data acquisition module, a video data transmission module and a video data transmission module, wherein the video data acquisition module is used for acquiring video data, and a 3D somatosensory camera is selected as video acquisition hardware to transmit video data in the range of a child motion place to the joint point extraction module;
the node extraction module: the method comprises the steps of selecting a human body joint point to extract and generate a neural network model, and sending the model to a server;
the action recognition module: the method comprises the steps of establishing space coordinates, counting the positions of the joints, calculating the movement speed of the joints, comparing the movement speed with a preset value, and judging whether warning information is generated or not;
and an alarm module: the alarm device is used for acquiring the warning information sent by the server and controlling the alarm device in the sport area to send out an alarm sound prompt to warn the guardian to timely take care of the children.
And a storage module: for storing a dangerous action category, an occurrence time, a picture or a short video data to a server when a dangerous action occurs.
The foregoing is merely exemplary of the present application, and specific structures and features well known in the art will not be described in detail herein, so that those skilled in the art will be aware of all the prior art to which the present application pertains, and will be able to ascertain the general knowledge of the technical field in the application or prior art, and will not be able to ascertain the general knowledge of the technical field in the prior art, without using the prior art, to practice the present application, with the aid of the present application, to ascertain the general knowledge of the same general knowledge of the technical field in general purpose. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present application, and these should also be considered as the scope of the present application, which does not affect the effect of the implementation of the present application and the utility of the patent. The protection scope of the present application is subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (5)
1. A child motion safety monitoring method, characterized in that: the method comprises the following steps:
s1: setting a 3D somatosensory camera on a sports ground and collecting video;
s2: screening main joint points of a human body, extracting and generating a neural network model, dividing the video in the S1 into images, and screening the joint points by using the neural network model;
s3: counting the coordinate data of each node selected in the S2;
s4: calculating the movement speed of the foot joint point in the step S3, and identifying the rapid movement;
s5: performing falling action recognition according to the coordinate data of the S3 articulation point;
s6: performing inverted motion recognition according to the coordinate data of the S3 articulation point;
s7: the server judges and recognizes dangerous actions in S4 to S6 and generates warning information, and the warning module acquires the warning information sent by the server and controls the warner of the sport area to send out warning sound prompt so as to warn the guardian to timely take care of the children.
2. A method of child motion safety monitoring according to claim 1, wherein: s2 comprises the following steps:
s2-1: importing a data training model;
s2-2: the child camera video is imported, the embodiment utilizes the skeleton tracking function of Kinect, and the body of the child is distinguished from a complex background by adopting a separation strategy;
s2-3: and screening joint points.
3. A method of child motion safety monitoring according to claim 2, wherein: s3 comprises the following steps:
s3-1: three-dimensional coding is carried out on the measurement space;
s3-2: and counting three-dimensional coordinate data of each joint point at the same time.
4. A method of child motion safety monitoring according to claim 3, wherein: s4 comprises the following steps:
s4-1: calculating the instantaneous movement speed of the child by adopting the left foot coordinates of the child;
s4-2: and judging whether to generate warning information according to the preset value.
5. A method of child motion safety monitoring according to any one of claims 1-4, wherein the method of child motion safety monitoring is performed and comprises: the system comprises a camera, an alarm and a server; the camera comprises a camera module and a joint point extraction module, and the server comprises an action recognition module, an alarm module and a storage module;
and the camera module: the system comprises a joint point extraction module, a video data acquisition module, a video data transmission module and a video data transmission module, wherein the video data acquisition module is used for acquiring video data, and a 3D somatosensory camera is selected as video acquisition hardware to transmit video data in the range of a child motion place to the joint point extraction module;
the node extraction module: the method comprises the steps of selecting a human body joint point to extract and generate a neural network model, and sending the model to a server;
the action recognition module: the method comprises the steps of establishing space coordinates, counting the positions of the joints, calculating the movement speed of the joints, comparing the movement speed with a preset value, and judging whether warning information is generated or not;
and an alarm module: the alarm device is used for acquiring the alarm information sent by the server and controlling the alarm device in the sport area to send out an alarm sound prompt to warn the guardian to timely take care of the children;
and a storage module: for storing a dangerous action category, an occurrence time, a picture or a short video data to a server when a dangerous action occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310802758.6A CN116778666A (en) | 2023-06-30 | 2023-06-30 | Child motion safety monitoring system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310802758.6A CN116778666A (en) | 2023-06-30 | 2023-06-30 | Child motion safety monitoring system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116778666A true CN116778666A (en) | 2023-09-19 |
Family
ID=87994412
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310802758.6A Pending CN116778666A (en) | 2023-06-30 | 2023-06-30 | Child motion safety monitoring system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116778666A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117316377A (en) * | 2023-10-20 | 2023-12-29 | 深圳咕嘟熊教育科技有限责任公司 | Infant outdoor exercises health data acquisition system and intelligent terminal |
-
2023
- 2023-06-30 CN CN202310802758.6A patent/CN116778666A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117316377A (en) * | 2023-10-20 | 2023-12-29 | 深圳咕嘟熊教育科技有限责任公司 | Infant outdoor exercises health data acquisition system and intelligent terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2012231931B2 (en) | Virtual golf simulation apparatus and sensing device and method used for same | |
| CN104038738B (en) | Intelligent monitoring system and intelligent monitoring method for extracting coordinates of human body joint | |
| JP2014512903A (en) | Sensing device and sensing method used in virtual golf simulation device | |
| CN112183355B (en) | Effluent height detection system and method based on binocular vision and deep learning | |
| KR20190031111A (en) | Virtual tennis simulation system, sensing device and method for sensing process using the same | |
| CN111241913A (en) | Method, device and system for detecting falling of personnel | |
| JP3655618B2 (en) | Pedestrian age determination device, walking state / pedestrian age determination method and program | |
| CN109830078B (en) | Intelligent behavior analysis method and intelligent behavior analysis equipment suitable for narrow space | |
| CN111582158A (en) | Tumbling detection method based on human body posture estimation | |
| CN116778666A (en) | Child motion safety monitoring system and method | |
| Stone et al. | Silhouette classification using pixel and voxel features for improved elder monitoring in dynamic environments | |
| Calandre et al. | Extraction and analysis of 3D kinematic parameters of Table Tennis ball from a single camera | |
| CN111144174A (en) | System for identifying falling behavior of old people in video by using neural network and traditional algorithm | |
| WO2020217812A1 (en) | Image processing device that recognizes state of subject and method for same | |
| Hung et al. | Fall detection with two cameras based on occupied area | |
| TWI635887B (en) | Sensing device for calculating information on golf shot of user and sensing method using the same | |
| CN114463838A (en) | Human behavior recognition method, system, electronic device and storage medium | |
| US11521411B2 (en) | System and method for providing multi-camera 3D body part labeling and performance metrics | |
| CN112597898B (en) | Real-time step counting-based intelligent identification method and medium for safety state of electric power personnel | |
| Suzuki et al. | Automatic fault detection in race walking from a smartphone camera via fine-tuning pose estimation | |
| US11741756B2 (en) | Real time kinematic analyses of body motion | |
| CN115424341A (en) | Fighting behavior identification method and device and electronic equipment | |
| CN114639168B (en) | Method and system for recognizing running gesture | |
| CN111144260A (en) | Detection method, device and system of crossing gate | |
| CN115731563A (en) | Method for identifying falling of remote monitoring personnel |
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 |