[go: up one dir, main page]

CN106056035A - Motion-sensing technology based kindergarten intelligent monitoring method - Google Patents

Motion-sensing technology based kindergarten intelligent monitoring method Download PDF

Info

Publication number
CN106056035A
CN106056035A CN201610210171.6A CN201610210171A CN106056035A CN 106056035 A CN106056035 A CN 106056035A CN 201610210171 A CN201610210171 A CN 201610210171A CN 106056035 A CN106056035 A CN 106056035A
Authority
CN
China
Prior art keywords
child
action
motion
dangerous play
sensing technology
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
Application number
CN201610210171.6A
Other languages
Chinese (zh)
Inventor
周晓军
杨高峰
李骊
盛赞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Huajie Imi Software Technology Co Ltd
Original Assignee
Nanjing Huajie Imi Software Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing Huajie Imi Software Technology Co Ltd filed Critical Nanjing Huajie Imi Software Technology Co Ltd
Priority to CN201610210171.6A priority Critical patent/CN106056035A/en
Publication of CN106056035A publication Critical patent/CN106056035A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24147—Distances to closest patterns, e.g. nearest neighbour classification
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/29—Graphical models, e.g. Bayesian networks
    • G06F18/295—Markov models or related models, e.g. semi-Markov models; Markov random fields; Networks embedding Markov models
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30221—Sports video; Sports image

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to a motion-sensing technology based kindergarten intelligent monitoring method, which comprises the steps of installing 3D motion-sensing equipment in a kindergarten, capturing 3D human body skeleton images of children in real time, extracting key joint feature vectors, inputting the feature vectors into a motion classifier so as to carry out motion classification, and finding out motions with the highest matching degree, wherein motion classification is trained in advance through a machine learning method. The method provided by the invention can realize detection, analysis and tracking for human body motion postures and figure motion trails through a three-dimensional visual perception technology, and motions of the children are captured dynamically in real time, so that dangerous behaviors such as fighting, tumbling and boundary crossing can be predicted, and a warning is given out in advance so as to reduce occurrence of kindergarten accidents.

Description

A kind of Intelligence In Baogang Kindergarten based on body-sensing technology monitoring method
Technical field
The invention belongs to body-sensing monitoring technical field, particularly relate to a kind of kindergarten monitoring side based on body-sensing technology Method.
Background technology
3D body-sensing technology is a new generation's human-computer interaction technology revolution, is realized personage's movement locus by body-sensing technology Accurately detect and track, and action is analyzed, this is by the development promoting intelligent security guard of essence.
In recent years, kindergarten Frequent Accidents, Campus Security becomes whole society's focus of attention, child's safety during garden Also become the necessary requirement that the head of a family selects a school；And on the basis of current kindergarten monitoring system is all built upon video monitoring, Monitoring when needing special messenger special, due to limited staff, limited energy, instructors cannot learn the generation of dangerous play in advance, So the security situation of whole children in can not accomplishing comprehensively to grasp garden.
Chinese patent application 201410223422 discloses " a kind of kindergarten video frequency monitoring method and device ", and the program carries Supplied a kind of remote video monitor, need personnel real-time check video, do not accomplish the action of real-time intelligent analysis child Posture behavior, thus do not reach the effect given warning in advance.
Chinese patent application 201320180777 discloses " a kind of kindergarten personnel monitoring system ", and the program uses location The technology such as device, identification card monitors kindergarten personnel positions, is only capable of being monitored based on positional information, and can not Intelligent Recognition Go out the behavior act of personnel, can not meet the scene demand of complexity.
In sum, how to overcome the deficiency existing for prior art become current body-sensing monitoring technical field in urgently One of emphasis difficult problem solved.
Summary of the invention
It is an object of the invention to provide a kind of child based on body-sensing technology for overcoming the deficiency existing for prior art Garden monitoring method, the present invention passes through 3D vision perception technology, it is possible to realize human action attitude and personage's movement locus Detection, analyze and follow the tracks of, the most real-time action catching child, and then dope fight, fall, the dangerous play such as cross the border And send alarm in advance, to reduce the generation of kindergarten accident.
A kind of based on body-sensing technology the Intelligence In Baogang Kindergarten monitoring method proposed according to the present invention, it is characterised in that include Following basic step:
Step one, somatosensory device exports space three-dimensional measurement data in real time, obtains the RGB image containing depth map information；
Step 2, for the depth map information of every frame RGB image, extracts simultaneously and follows the tracks of in 1 people or many people RGB image The motion characteristic vector of human body 3D skeleton, described human body 3D skeleton is the coordinate data of human body major joint point；
Step 3, according to the motion characteristic vector of human body 3D skeleton, carries out including limb size, reference zero and side To the normalized of child's dangerous play monitoring objective；
Step 4, the coordinate data of screening major joint point；
Step 5, extracts motion characteristic vector value from the coordinate data after screening, and builds motion characteristic sequence vector；
Step 6, is normalized motion characteristic sequence vector, and the n forming present frame ties up multiple human actions spy Levy vector；
Step 7, child's dangerous play identification is that the n obtained is tieed up multiple human action characteristic vector input action identifications Module, carries out classification of motion identification；If identifying child's dangerous play, then enter step 8, otherwise continue to repeat step one, Two, three, four, five and six；
Step 8, starts video record, records video recording by RGB photographic head；
Step 9, generates warning information, reports to warning module；
Step 10, warning module plays the alarm call of the different human body dangerous play of correspondence preset in predetermined location, with The continuation of warning child's dangerous play occurs；
Step 11, is reported and submitted information to carry-on other smart machine of corresponding management personnel by network, in order to by phase Pass personnel adopt appropriate measures and stop the generation of child's dangerous play.
The principle that realizes of the present invention is: kindergarten install 3D somatosensory device, real-time capture child's 3D human skeleton image, Extract crucial joint characteristic vector, characteristic vector is input to action in classification of motion device and classifies, find out matching degree the highest Action, thus reach the early warning to hazardous act action, wherein the classification of motion trained in advance by machine learning method.
The present invention compared with prior art its remarkable advantage is:
One is more intelligent, and traditional video frequency monitoring method needs personnel's real time inspection, and the present invention utilizes body-sensing skill Art, identifies hazardous act action by computer.
Two is to have more autgmentability, and the position of personnel can only be monitored, and can not divide in real time by traditional monitoring method The action behavior of analysis personnel, and the present invention can customize and gather different alerts action, with the demand of satisfied different scenes.
Three is more preferable practicality, and the intelligence of the present invention sets means and has stronger early warning and alarm function, it is simple to anti- Model, in possible trouble, is widely used in the children playing space of kindergarten and has similar safety with the children playing space of silver kindergarten Require such as the intelligent monitoring in the places such as physical education for children recreation room, children's stadium, zoo.
Accompanying drawing explanation
Fig. 1 is the principle square frame signal of a kind of based on body-sensing technology the Intelligence In Baogang Kindergarten monitoring system that the present invention proposes Figure.
Fig. 2 is the process blocks signal of a kind of based on body-sensing technology the Intelligence In Baogang Kindergarten monitoring method that the present invention proposes Figure.
Fig. 3 be a kind of based on body-sensing technology Intelligence In Baogang Kindergarten that the present invention proposes monitoring method child's dangerous play it Fall down action Time-space serial schematic diagram.
Fig. 4 be a kind of based on body-sensing technology Intelligence In Baogang Kindergarten that the present invention proposes monitoring method child's dangerous play it Hurry up action Time-space serial schematic diagram.
Fig. 5 be a kind of based on body-sensing technology Intelligence In Baogang Kindergarten that the present invention proposes monitoring method child's dangerous play it Jump action Time-space serial schematic diagram.
Detailed description of the invention
With embodiment, the detailed description of the invention of the present invention is described in further detail below in conjunction with the accompanying drawings.
In conjunction with Fig. 1-5, a kind of based on body-sensing technology the Intelligence In Baogang Kindergarten monitoring method that the present invention proposes, including having as follows Body step:
Step one, somatosensory device exports space three-dimensional measurement data in real time, obtains the RGB image containing depth map information；
Step 2, for the depth map information of every frame RGB image, extracts simultaneously and follows the tracks of in 1 people or many people RGB image The motion characteristic vector of human body 3D skeleton, described human body 3D skeleton is the coordinate data of human body major joint point；
Step 3, according to the motion characteristic vector of human body 3D skeleton, carries out including limb size, reference zero and side To the normalized of child's dangerous play monitoring objective；
Step 4, the coordinate data of screening major joint point, specifically refer to, for child's race, the feature made of beating, choose The articulare that in child's dangerous play, weight is the highest: left foot, right crus of diaphragm, left knee joint, right knee joint, the right hand, left hand, left elbow, right elbow, head, shoulder Center, spinal column, buttocks joint the data of body joint point coordinate as the original input value of characteristic vector, be designated as V=[v1,v2,v3, v4,v5,v6,v7,v8,v9,v10, v11, v12]；Described w is the number of sampling articulare, and its numerical value is 12；Action in view of child Relatively slow relative to adult, take into account the real-time of alarm again simultaneously, seasonal effect in time series length T arranges 1s, per second takes 30 frame bones Rack data；Finally include that speed, position, the spatial relationship of angle carry out feature extraction, OK according to articulare motion characteristic For sequence two dimension W × T eigenmatrixCharacteristic vector for moment t；
Step 5, extracts motion characteristic vector value from the coordinate data after screening, and builds motion characteristic sequence vector； Described motion characteristic sequence vector is space and the sequence of time, the J={j of two dimension1,...,jt,...jT, wherein T is sample The length of sequence, andFor moment t articulare original feature vector, whereinRepresent joint Three coordinates after some normalization, including towards, the normalization of height, three-dimensional space position；
Step 6, is normalized motion characteristic sequence vector, and the n forming present frame ties up multiple human actions spy Levy vector；
Step 7, child's dangerous play identification is that the n obtained is tieed up multiple human action characteristic vector input action identifications Module, carries out classification of motion identification；If identifying child's dangerous play, then entering step 8, otherwise continuing to repeat step one To six；Wherein:
Described action recognition module refers to child's dangerous play grader, inputs motion characteristic vector to be sorted, Whether output is dangerous play classification, and this grader has been trained in advance by action training module；
Described action recognition module refers to the classification of motion device of a multilamellar, and ground floor includes dangerous play, normally moves Make the binary classifier carrying out classifying；The second layer includes falling down, fast run, dangerous play of fighting specifically are classified many Class grader；
Described action recognition module refers to child's dangerous play grader, raw by the training of child motor training module Becoming, training method is, in the activity of kindergarten, is gathered the sample of a large amount of motion characteristics vector by step one to six, goes forward side by side Pedestrian's work demarcates classification, uses supervised learning method training action grader；Including the falling of training for children's sport feature Fall, hurry up, jump need alarm typical action and formation fall down action sequence；
Described child's dangerous play refers to fall down action Time-space serial, vertically sits including shoulder center knuckle, buttocks center knuckle It is marked on rapid decrease in sequence period, shoulder center relative angle Rapid Variable Design；
Described child's dangerous play refers to action Time-space serial of hurrying up, including sequence period inner frame towards unanimously；Left and right Knee joint, left right foot joint vertical coordinate Rapid Variable Design；Skeleton quickly moves in space coordinates；
Described child's dangerous play refers to jump action Time-space serial, including foot vertical coordinate in space in left and right in the cycle Relatively areal coordinate exceeds threshold value, and stops certain time；
Described child's dangerous play grader is that space sequential HMM (HMM) based on two dimension has been trained Becoming, model automatically learns the sequence of composition action by finding continuous human motion, and classifies sequence, and then realizes dynamic The identification made, HMM is especially suitable for processing multivariate time-variable data matching problem, therefore uses Hidden Markov mould Behavior characteristics sequence is classified and identifies by type；One HMM can use 5 element group representations: λ=S, V, H, B, π }, SwFor state set, VwFor state-transition matrix on Spatial Dimension, HwFor state-transition matrix on time dimension, BwFor defeated Go out probability density, πwFor each state set initial distribution probability；Or use k nearest neighbor algorithm, the multiple classification of support vector machine, return Return the child's dangerous play grader trained with data clusters machine learning algorithm；
Step 8, starts video record, records video recording by RGB photographic head；Described RGB photographic head is recorded video recording and is referred to clap Take the photograph segment video push at that time to related management personnel's mobile phone or other can receive the equipment of information in time；Described segment video Refer to ensure that management personnel can accurately judge situation at that time, ensure that again 1 second or several seconds of in time transmission with Interior video.
Step 9, generates warning information, reports to warning module；
Step 10, warning module plays the alarm call of the different human body dangerous play of correspondence preset in predetermined location, with The continuation of warning child's dangerous play occurs；
Step 11, is reported and submitted information to carry-on other smart machine of corresponding management personnel by network, in order to by phase Pass personnel adopt appropriate measures and stop the generation of child's dangerous play.
Further illustrating the specific embodiment of the present invention below in conjunction with the accompanying drawings, illustrated embodiment is served only for explaining the present invention, It is not intended to limit the scope of the present invention.
As it is shown in figure 1, a kind of based on body-sensing technology the Intelligence In Baogang Kindergarten monitoring method that the present invention proposes is to based on body The concrete application of the Intelligence In Baogang Kindergarten monitoring system of sense technology, described Intelligence In Baogang Kindergarten monitoring system based on body-sensing technology, bag Include somatosensory device, action recognition module, the training of deliberate action storehouse input module, warning module；Wherein: somatosensory device includes one Infrared transmitter, infrared remote receiver, RGB photographic head, 3D body-sensing chip, it is possible to export the three-dimensional vision information in space in real time, can Select the somatosensory device such as Kinect somatosensory photographic head, Xtion PRO；Described warning module, this module connects the Internet, and docking is each Class IMU is applied；When receiving early warning information, play early warning information, and pass through network push photo or short-sighted frequency to related management Other smart machine of personnel.
As in figure 2 it is shown, the classification of a kind of based on body-sensing technology the Intelligence In Baogang Kindergarten monitoring method proposed according to the present invention The specific embodiment of step is as follows:
Step 1, somatosensory device exports space three-dimensional measurement data in real time, obtains the RGB image containing depth map information；
Step 2, extracts human body 3D skeleton, and skeleton is body weight for humans and wants the data of articulare；
Step 3, action recognition module, by framework information, identifies action, specifically includes:
Human body 3D joint coordinates is normalized by step 3.1, and concrete grammar is for selecting a human body joint coordinates For model, by the length of the limbs Vector enlarging that obtains to model；
Step 3.2 filters out the articulare data that child motor is crucial, has 12 articulares, left foot, right crus of diaphragm, left knee joint, Right knee joint, the right hand, left hand, left elbow, right elbow, head, shoulder center, spinal column, buttocks joint articulare；
Step 3.3 extracts motion characteristic value from skeleton joint point data, specifically refers to include health height, inclination angle Degree, pitch velocity, the feature of movement locus, and build motion characteristic sequence vector；
Motion characteristic vector is normalized by step 3.4, formed present frame human action n dimensional feature to Amount, normalization includes size normalization, place normalization；Normalized purpose is to reduce human body diversity and position difference band The impact come.
Step 3.5 child's dangerous play identification is that the n obtained is tieed up motion characteristic vector input action identification module, carries out Classification of motion identification, if identified as dangerous play, entrance step 3.6, otherwise continuation repetition above steps；Action recognition Module is the classification of motion device of a multilamellar, and ground floor is the grader of two classes, is divided into dangerous play class, regular event class, the Two layers carry out multi classifier to dangerous play, specifically classify dangerous play, as fallen down, fast run, fight；By The training of child motor training module generates；Training method is, in the activity of kindergarten, is gathered a large amount of dynamic by above steps Making characteristic vector sample, pedestrian's work of going forward side by side demarcates classification, uses supervised learning method training action grader；
Step 3.6 starts video record, records video recording in 1 second by RGB photographic head；
Step 3.7 generates warning information, reports to warning module；
Step 4, warning module receives the real-time process after warning information, including:
Step 4.1 warning module plays the alarm call of the respective action preset in place, to warn child's dangerous play Continue to occur；
Information is reported and submitted to carry-on other smart machine of corresponding management personnel by step 4.2 by network, and related personnel adopts Take appropriate measure and stop the generation of child's dangerous play.
In the detailed description of the invention of the present invention, all explanations not related to belong to techniques known, refer to known skill Art is carried out.
The present invention, through validation trial, achieves satisfied trial effect.
Above detailed description of the invention and embodiment are a kind of based on body-sensing technology the Intelligence In Baogang Kindergartens proposing the present invention The concrete support of monitoring method and technology thought, it is impossible to limit protection scope of the present invention with this, every proposes according to the present invention Technological thought, any equivalent variations done on the basis of the technical program or the change of equivalence, all still fall within the technology of the present invention The scope of scheme protection.

Claims (12)

1. Intelligence In Baogang Kindergarten based on a body-sensing technology monitoring method, it is characterised in that comprise the following steps that
Step one, somatosensory device exports space three-dimensional measurement data in real time, obtains the RGB image containing depth map information；
Step 2, for the depth map information of every frame RGB image, extracts simultaneously and follows the tracks of the human body in 1 people or many people RGB image 3D skeleton, described human body 3D skeleton is the coordinate data of human body major joint point；
Step 3, according to the motion characteristic vector of human body 3D skeleton, carries out including limb size, reference zero and direction The normalized of child's dangerous play monitoring objective；
Step 4, the coordinate data of screening major joint point；
Step 5, extracts motion characteristic vector value from the coordinate data after screening, and builds motion characteristic sequence vector；
Step 6, is normalized motion characteristic sequence vector, formed present frame n tie up multiple human action features to Amount；
Step 7, child's dangerous play identification is that the n obtained is tieed up multiple human action characteristic vector input action identification modules, Carry out classification of motion identification；If identifying child's dangerous play, then entering step 8, otherwise continuing to repeat step one to six；
Step 8, starts video record, records video recording by RGB photographic head；
Step 9, generates warning information, reports to warning module；
Step 10, warning module plays the alarm call of the different human body dangerous play of the correspondence preset in predetermined location, with warning The continuation of child's dangerous play occurs；
Step 11, is reported and submitted information to carry-on other smart machine of corresponding management personnel by network, in order to by relevant people Member adopts appropriate measures and stops the generation of child's dangerous play.
A kind of Intelligence In Baogang Kindergarten based on body-sensing technology the most according to claim 1 monitoring method, it is characterised in that step The coordinate data screening major joint point described in four refers to, for child's race, the feature made of beating, choose in child's dangerous play The articulare that weight is the highest: left foot, right crus of diaphragm, left knee joint, right knee joint, the right hand, left hand, left elbow, right elbow, head, shoulder center, spinal column, buttocks close The data of the body joint point coordinate of joint as characteristic vector original input value and are designated as V, this V=[v1,v2,v3,v4,v5,v6,v7,v8, v9,v10, v11, v12]。
A kind of Intelligence In Baogang Kindergarten based on body-sensing technology the most according to claim 1 monitoring method, it is characterised in that step Motion characteristic sequence vector described in five is the Time-space serial of two dimension and is designated as J, this J={j1,...,jt,...jT, wherein T is sample The length of this sequence, andFor original feature vector input value v of each articulare of moment t, andRepresent three coordinates after articulare normalization, including towards, the normalization of height, three-dimensional space position.
A kind of Intelligence In Baogang Kindergarten based on body-sensing technology the most according to claim 3 monitoring method, it is characterised in that described W is the number of sampling articulare, and its numerical value is 12；In view of the action of child is relatively slow relative to adult, take into account announcement again simultaneously Alert real-time, seasonal effect in time series length T arranges 1s, per second takes 30 frame skeleton datas；Final according to articulare motion characteristic bag Include speed, position, the spatial relationship of angle carry out feature extraction, obtain behavior sequence two dimension W × T eigenmatrixCharacteristic vector for moment t.
A kind of Intelligence In Baogang Kindergarten based on body-sensing technology the most according to claim 1 monitoring method, it is characterised in that step Action recognition module described in seven refers to child's dangerous play grader, inputs motion characteristic vector to be sorted, and output is No for dangerous play classification, this grader has been trained in advance by action training module.
A kind of Intelligence In Baogang Kindergarten based on body-sensing technology the most according to claim 1 monitoring method, it is characterised in that step Action recognition module described in seven refers to the classification of motion device of a multilamellar, and ground floor includes carrying out dangerous play, regular event The binary classifier of classification；The multicategory classification that the second layer includes falling down, fast run, dangerous play of fighting specifically are classified Device.
A kind of Intelligence In Baogang Kindergarten based on body-sensing technology the most according to claim 1 monitoring method, it is characterised in that step Action recognition module described in seven refers to child's dangerous play grader, the training of child motor training module generate, instruction Practicing method is, in the activity of kindergarten, is gathered the sample of a large amount of characteristic vectors by step one to six, and pedestrian's work of going forward side by side is demarcated Classification, uses supervised learning method training action grader；Fall down including train for children's sport feature, hurry up, jump Jump and need the typical action of alarm formation to fall down action sequence.
A kind of Intelligence In Baogang Kindergarten based on body-sensing technology the most according to claim 1 monitoring method, it is characterised in that step Child's dangerous play described in seven refers to fall down action Time-space serial, including shoulder center knuckle, buttocks center knuckle vertical coordinate in sequence Rapid decrease in the row cycle, shoulder center relative angle Rapid Variable Design.
A kind of Intelligence In Baogang Kindergarten based on body-sensing technology the most according to claim 1 monitoring method, it is characterised in that step Child's dangerous play described in seven refers to action Time-space serial of hurrying up, including sequence period inner frame towards unanimously；Left and right knee joint, Left right foot joint vertical coordinate Rapid Variable Design；Skeleton quickly moves in space coordinates.
A kind of Intelligence In Baogang Kindergarten based on body-sensing technology the most according to claim 1 monitoring method, it is characterised in that step Child's dangerous play described in seven refers to jump action Time-space serial, including foot vertical coordinate in space in left and right in the cycle relatively Areal coordinate exceeds threshold value, and stops certain time.
11. a kind of Intelligence In Baogang Kindergarten based on body-sensing technology according to claim 6 monitoring methods, it is characterised in that institute Stating child's dangerous play grader is that space sequential HMM (HMM) based on two dimension has been trained, and model passes through Find continuous human motion and automatically learn the sequence of composition action, and sequence is classified, and then realize the identification to action, hidden Markov model is especially suitable for processing multivariate time-variable data matching problem, therefore it is special to use HMM to come behavior Levy sequence to carry out classifying and identifying；One HMM can use 5 element group representations: λ={ S, V, H, B, π }, SwFor state Set, VwFor state-transition matrix on Spatial Dimension, HwFor state-transition matrix on time dimension, BwFor output probability density, πw For each state set initial distribution probability；Or use k nearest neighbor algorithm, multiple classification, recurrence and the data clusters of support vector machine Child's dangerous play grader that machine learning algorithm is trained.
12. a kind of Intelligence In Baogang Kindergarten based on body-sensing technology according to claim 1 monitoring methods, it is characterised in that step Described in eight RGB photographic head record video recording refer to shoot at that time segment video push to related management personnel's mobile phone or other can and Time receive other smart machines of information；Described segment video refers to ensure that management personnel can accurately judge feelings at that time Condition, ensure that again the video within 1 second or several seconds of transmission in time.
CN201610210171.6A 2016-04-06 2016-04-06 Motion-sensing technology based kindergarten intelligent monitoring method Pending CN106056035A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610210171.6A CN106056035A (en) 2016-04-06 2016-04-06 Motion-sensing technology based kindergarten intelligent monitoring method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610210171.6A CN106056035A (en) 2016-04-06 2016-04-06 Motion-sensing technology based kindergarten intelligent monitoring method

Publications (1)

Publication Number Publication Date
CN106056035A true CN106056035A (en) 2016-10-26

Family

ID=57484198

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610210171.6A Pending CN106056035A (en) 2016-04-06 2016-04-06 Motion-sensing technology based kindergarten intelligent monitoring method

Country Status (1)

Country Link
CN (1) CN106056035A (en)

Cited By (55)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106648120A (en) * 2017-02-21 2017-05-10 戴雨霖 Training system for escape from fire based on virtual reality and somatosensory technology
CN106791655A (en) * 2016-12-24 2017-05-31 深圳云天励飞技术有限公司 A kind of method for processing video frequency and device
CN106776757A (en) * 2016-11-15 2017-05-31 中国银行股份有限公司 User completes the indicating means and device of Net silver operation
CN107194955A (en) * 2017-06-20 2017-09-22 秦玲 Adaptive big data management method
CN107220604A (en) * 2017-05-18 2017-09-29 清华大学深圳研究生院 A kind of fall detection method based on video
CN107239767A (en) * 2017-06-08 2017-10-10 北京纽伦智能科技有限公司 Mouse Activity recognition method and its system
CN107247945A (en) * 2017-07-04 2017-10-13 刘艺晴 A kind of ward sufferer monitor system and monitoring method based on Kinect device
CN108284434A (en) * 2017-01-10 2018-07-17 发那科株式会社 Machine learning device, the impact suppression system of teaching apparatus and machine learning method
CN108596032A (en) * 2018-03-21 2018-09-28 浙江大华技术股份有限公司 It fights in a kind of video behavioral value method, apparatus, equipment and medium
CN108664887A (en) * 2018-03-20 2018-10-16 重庆邮电大学 Prior-warning device and method are fallen down in a kind of virtual reality experience
CN108803341A (en) * 2018-06-29 2018-11-13 炬大科技有限公司 A kind of house security monitoring system and method based on sweeping robot
CN108858201A (en) * 2018-08-15 2018-11-23 深圳市烽焌信息科技有限公司 It is a kind of for nursing the robot and storage medium of children
CN108898108A (en) * 2018-06-29 2018-11-27 炬大科技有限公司 A kind of user's abnormal behaviour monitoring system and method based on sweeping robot
CN109117893A (en) * 2018-08-28 2019-01-01 华中师范大学 A kind of action identification method and device based on human body attitude
CN109389041A (en) * 2018-09-07 2019-02-26 南京航空航天大学 A kind of fall detection method based on joint point feature
CN109711289A (en) * 2018-12-13 2019-05-03 Oppo广东移动通信有限公司 Riding reminding method and device, electronic equipment and storage medium
CN109815816A (en) * 2018-12-24 2019-05-28 山东山大鸥玛软件股份有限公司 A kind of examinee examination hall abnormal behaviour analysis method based on deep learning
CN109815921A (en) * 2019-01-29 2019-05-28 北京融链科技有限公司 Method and device for predicting activity category in hydrogen refueling station
CN109857114A (en) * 2019-02-26 2019-06-07 温州市职业中等专业学校 Campus Mobile Intelligent Robot and campus intelligent management system
CN109934881A (en) * 2017-12-19 2019-06-25 华为技术有限公司 Image encoding method, the method for action recognition and computer equipment
CN110062210A (en) * 2019-04-28 2019-07-26 广东安居宝数码科技股份有限公司 Monitoring method, device, equipment and the storage medium of object
CN110414306A (en) * 2019-04-26 2019-11-05 吉林大学 An infant abnormal behavior detection method based on meanshift algorithm and SVM
CN110516720A (en) * 2019-08-13 2019-11-29 北京三快在线科技有限公司 Safety monitoring equipment and method for safety monitoring
CN110717381A (en) * 2019-08-28 2020-01-21 北京航空航天大学 Human intention understanding method facing human-computer cooperation and based on deep stacking Bi-LSTM
CN111382306A (en) * 2018-12-28 2020-07-07 杭州海康威视数字技术股份有限公司 Method and apparatus for querying video frames
CN111460978A (en) * 2020-03-30 2020-07-28 中国科学院自动化研究所南京人工智能芯片创新研究院 Infant behavior monitoring system based on motion judgment sensor and deep learning technology and judgment method thereof
CN111543950A (en) * 2019-09-17 2020-08-18 恩乐孩子有限公司 Children growth state measuring system using intelligent weighing scale
CN111753594A (en) * 2019-03-29 2020-10-09 杭州海康威视数字技术股份有限公司 Hazard identification method, device and system
CN111767812A (en) * 2020-06-18 2020-10-13 浙江大华技术股份有限公司 Fall detection method, fall detection device and storage device
CN111801939A (en) * 2018-02-20 2020-10-20 电子护理公司 Connected kiosks for real-time fall risk assessment
CN112071041A (en) * 2020-08-31 2020-12-11 广东小天才科技有限公司 Security detection method, wearable device and computer-readable storage medium
CN112070016A (en) * 2020-09-08 2020-12-11 安徽兰臣信息科技有限公司 Detection method for identifying child behavior and action
CN112381002A (en) * 2020-11-16 2021-02-19 深圳技术大学 Human body risk posture identification method and system
CN112949503A (en) * 2021-03-05 2021-06-11 齐齐哈尔大学 Site monitoring management method and system for ice and snow sports
CN113034503A (en) * 2021-05-28 2021-06-25 博奥生物集团有限公司 High-flux automatic cup separating method, device and system
CN113627369A (en) * 2021-08-16 2021-11-09 南通大学 Action recognition and tracking method in auction scene
US11213224B2 (en) 2018-03-19 2022-01-04 Electronic Caregiver, Inc. Consumer application for mobile assessment of functional capacity and falls risk
US11222198B2 (en) 2019-11-21 2022-01-11 International Business Machines Corporation Video analysis system for optimizing an activity protocol
CN113971868A (en) * 2020-07-23 2022-01-25 易程融创信息科技有限公司 Alarm method and system based on infant behavior statistics
CN114079724A (en) * 2020-07-31 2022-02-22 北京小米移动软件有限公司 Method and device for taking-off snapshot and storage medium
CN114495264A (en) * 2021-12-31 2022-05-13 上海卓菡科技有限公司 Method and device for detecting behavior of reverse climbing slide
CN114842401A (en) * 2022-05-25 2022-08-02 广州智能科技发展有限公司 Method and system for capturing and classifying human body actions
US11488724B2 (en) 2018-06-18 2022-11-01 Electronic Caregiver, Inc. Systems and methods for a virtual, intelligent and customizable personal medical assistant
WO2023130696A1 (en) * 2022-01-05 2023-07-13 深眸科技(北京)有限公司 Smart system for automatically tracking-photographing sports events, and control method therefor
US11791050B2 (en) 2019-02-05 2023-10-17 Electronic Caregiver, Inc. 3D environment risks identification utilizing reinforced learning
CN117373110A (en) * 2023-08-30 2024-01-09 武汉星巡智能科技有限公司 Visible light-thermal infrared imaging infant behavior recognition method, device and equipment
US11923058B2 (en) 2018-04-10 2024-03-05 Electronic Caregiver, Inc. Mobile system for the assessment of consumer medication compliance and provision of mobile caregiving
US12009083B2 (en) 2020-11-16 2024-06-11 Electronic Caregiver, Inc. Remote physical therapy and assessment of patients
US12011259B2 (en) 2015-12-11 2024-06-18 Electronic Caregiver, Inc. Systems and methods for fall detection
US12033484B2 (en) 2019-05-07 2024-07-09 Electronic Caregiver, Inc. Systems and methods for predictive environmental fall risk identification using dynamic input
US12034748B2 (en) 2020-02-28 2024-07-09 Electronic Caregiver, Inc. Intelligent platform for real-time precision care plan support during remote care management
US12125137B2 (en) 2020-05-13 2024-10-22 Electronic Caregiver, Inc. Room labeling drawing interface for activity tracking and detection
US12127817B2 (en) 2020-07-22 2024-10-29 Electronic Caregiver, Inc. Systems and methods for mitigating the spread of infectious diseases
US12265900B2 (en) 2018-01-17 2025-04-01 Electronic Caregiver, Inc. Computing devices with improved interactive animated conversational interface systems
US12315640B2 (en) 2015-12-11 2025-05-27 Electronic Caregiver, Inc. Atmospheric mirroring and dynamically varying three-dimensional assistant addison interface for interior environments

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102074095A (en) * 2010-11-09 2011-05-25 无锡中星微电子有限公司 System and method for monitoring infant behaviors
CN104038738A (en) * 2014-06-04 2014-09-10 东北大学 Intelligent monitoring system and intelligent monitoring method for extracting coordinates of human body joint
CN104427309A (en) * 2013-09-04 2015-03-18 张宇奇 School-safety monitoring system
CN104519460A (en) * 2015-01-29 2015-04-15 上海电机学院 Kindergarten monitoring system
CN104850846A (en) * 2015-06-02 2015-08-19 深圳大学 Human behavior recognition method and human behavior recognition system based on depth neural network

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102074095A (en) * 2010-11-09 2011-05-25 无锡中星微电子有限公司 System and method for monitoring infant behaviors
CN104427309A (en) * 2013-09-04 2015-03-18 张宇奇 School-safety monitoring system
CN104038738A (en) * 2014-06-04 2014-09-10 东北大学 Intelligent monitoring system and intelligent monitoring method for extracting coordinates of human body joint
CN104519460A (en) * 2015-01-29 2015-04-15 上海电机学院 Kindergarten monitoring system
CN104850846A (en) * 2015-06-02 2015-08-19 深圳大学 Human behavior recognition method and human behavior recognition system based on depth neural network

Cited By (72)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12011259B2 (en) 2015-12-11 2024-06-18 Electronic Caregiver, Inc. Systems and methods for fall detection
US12315640B2 (en) 2015-12-11 2025-05-27 Electronic Caregiver, Inc. Atmospheric mirroring and dynamically varying three-dimensional assistant addison interface for interior environments
CN106776757A (en) * 2016-11-15 2017-05-31 中国银行股份有限公司 User completes the indicating means and device of Net silver operation
CN106776757B (en) * 2016-11-15 2020-03-27 中国银行股份有限公司 Method and device for indicating user to complete online banking operation
CN106791655A (en) * 2016-12-24 2017-05-31 深圳云天励飞技术有限公司 A kind of method for processing video frequency and device
CN108284434B (en) * 2017-01-10 2019-08-20 发那科株式会社 The impact of machine learning device, teaching apparatus inhibits system and machine learning method
CN108284434A (en) * 2017-01-10 2018-07-17 发那科株式会社 Machine learning device, the impact suppression system of teaching apparatus and machine learning method
CN106648120B (en) * 2017-02-21 2020-04-03 戴雨霖 Fire escape training system based on virtual reality and somatosensory technology
CN106648120A (en) * 2017-02-21 2017-05-10 戴雨霖 Training system for escape from fire based on virtual reality and somatosensory technology
CN107220604A (en) * 2017-05-18 2017-09-29 清华大学深圳研究生院 A kind of fall detection method based on video
CN107239767A (en) * 2017-06-08 2017-10-10 北京纽伦智能科技有限公司 Mouse Activity recognition method and its system
CN107194955A (en) * 2017-06-20 2017-09-22 秦玲 Adaptive big data management method
CN107194955B (en) * 2017-06-20 2018-04-13 安徽中杰信息科技有限公司 Adaptive big data management method
CN107247945A (en) * 2017-07-04 2017-10-13 刘艺晴 A kind of ward sufferer monitor system and monitoring method based on Kinect device
US11303925B2 (en) 2017-12-19 2022-04-12 Huawei Technologies Co., Ltd. Image coding method, action recognition method, and action recognition apparatus
CN109934881A (en) * 2017-12-19 2019-06-25 华为技术有限公司 Image encoding method, the method for action recognition and computer equipment
US11825115B2 (en) 2017-12-19 2023-11-21 Huawei Technologies Co., Ltd. Image coding method, action recognition method, and action recognition apparatus
US12265900B2 (en) 2018-01-17 2025-04-01 Electronic Caregiver, Inc. Computing devices with improved interactive animated conversational interface systems
CN111801939A (en) * 2018-02-20 2020-10-20 电子护理公司 Connected kiosks for real-time fall risk assessment
US11213224B2 (en) 2018-03-19 2022-01-04 Electronic Caregiver, Inc. Consumer application for mobile assessment of functional capacity and falls risk
CN108664887A (en) * 2018-03-20 2018-10-16 重庆邮电大学 Prior-warning device and method are fallen down in a kind of virtual reality experience
CN108596032A (en) * 2018-03-21 2018-09-28 浙江大华技术股份有限公司 It fights in a kind of video behavioral value method, apparatus, equipment and medium
CN108596032B (en) * 2018-03-21 2020-09-29 浙江大华技术股份有限公司 Detection method, device, equipment and medium for fighting behavior in video
US11923058B2 (en) 2018-04-10 2024-03-05 Electronic Caregiver, Inc. Mobile system for the assessment of consumer medication compliance and provision of mobile caregiving
US11488724B2 (en) 2018-06-18 2022-11-01 Electronic Caregiver, Inc. Systems and methods for a virtual, intelligent and customizable personal medical assistant
CN108898108B (en) * 2018-06-29 2022-04-26 炬大科技有限公司 User abnormal behavior monitoring system and method based on sweeping robot
CN108803341A (en) * 2018-06-29 2018-11-13 炬大科技有限公司 A kind of house security monitoring system and method based on sweeping robot
CN108898108A (en) * 2018-06-29 2018-11-27 炬大科技有限公司 A kind of user's abnormal behaviour monitoring system and method based on sweeping robot
CN108858201A (en) * 2018-08-15 2018-11-23 深圳市烽焌信息科技有限公司 It is a kind of for nursing the robot and storage medium of children
CN109117893A (en) * 2018-08-28 2019-01-01 华中师范大学 A kind of action identification method and device based on human body attitude
CN109389041A (en) * 2018-09-07 2019-02-26 南京航空航天大学 A kind of fall detection method based on joint point feature
CN109711289A (en) * 2018-12-13 2019-05-03 Oppo广东移动通信有限公司 Riding reminding method and device, electronic equipment and storage medium
CN109815816A (en) * 2018-12-24 2019-05-28 山东山大鸥玛软件股份有限公司 A kind of examinee examination hall abnormal behaviour analysis method based on deep learning
CN111382306A (en) * 2018-12-28 2020-07-07 杭州海康威视数字技术股份有限公司 Method and apparatus for querying video frames
CN111382306B (en) * 2018-12-28 2023-12-01 杭州海康威视数字技术股份有限公司 Method and device for querying video frames
CN109815921A (en) * 2019-01-29 2019-05-28 北京融链科技有限公司 Method and device for predicting activity category in hydrogen refueling station
US11791050B2 (en) 2019-02-05 2023-10-17 Electronic Caregiver, Inc. 3D environment risks identification utilizing reinforced learning
CN109857114A (en) * 2019-02-26 2019-06-07 温州市职业中等专业学校 Campus Mobile Intelligent Robot and campus intelligent management system
CN111753594B (en) * 2019-03-29 2023-09-29 杭州海康威视数字技术股份有限公司 Hazard identification methods, devices and systems
CN111753594A (en) * 2019-03-29 2020-10-09 杭州海康威视数字技术股份有限公司 Hazard identification method, device and system
CN110414306A (en) * 2019-04-26 2019-11-05 吉林大学 An infant abnormal behavior detection method based on meanshift algorithm and SVM
CN110414306B (en) * 2019-04-26 2022-07-19 吉林大学 Baby abnormal behavior detection method based on meanshift algorithm and SVM
CN110062210A (en) * 2019-04-28 2019-07-26 广东安居宝数码科技股份有限公司 Monitoring method, device, equipment and the storage medium of object
US12033484B2 (en) 2019-05-07 2024-07-09 Electronic Caregiver, Inc. Systems and methods for predictive environmental fall risk identification using dynamic input
CN110516720A (en) * 2019-08-13 2019-11-29 北京三快在线科技有限公司 Safety monitoring equipment and method for safety monitoring
CN110717381A (en) * 2019-08-28 2020-01-21 北京航空航天大学 Human intention understanding method facing human-computer cooperation and based on deep stacking Bi-LSTM
CN111543950A (en) * 2019-09-17 2020-08-18 恩乐孩子有限公司 Children growth state measuring system using intelligent weighing scale
US11222198B2 (en) 2019-11-21 2022-01-11 International Business Machines Corporation Video analysis system for optimizing an activity protocol
US12034748B2 (en) 2020-02-28 2024-07-09 Electronic Caregiver, Inc. Intelligent platform for real-time precision care plan support during remote care management
CN111460978A (en) * 2020-03-30 2020-07-28 中国科学院自动化研究所南京人工智能芯片创新研究院 Infant behavior monitoring system based on motion judgment sensor and deep learning technology and judgment method thereof
US12125137B2 (en) 2020-05-13 2024-10-22 Electronic Caregiver, Inc. Room labeling drawing interface for activity tracking and detection
CN111767812A (en) * 2020-06-18 2020-10-13 浙江大华技术股份有限公司 Fall detection method, fall detection device and storage device
CN111767812B (en) * 2020-06-18 2023-04-21 浙江大华技术股份有限公司 Fall detection method, fall detection device and storage device
US12127817B2 (en) 2020-07-22 2024-10-29 Electronic Caregiver, Inc. Systems and methods for mitigating the spread of infectious diseases
CN113971868A (en) * 2020-07-23 2022-01-25 易程融创信息科技有限公司 Alarm method and system based on infant behavior statistics
CN114079724A (en) * 2020-07-31 2022-02-22 北京小米移动软件有限公司 Method and device for taking-off snapshot and storage medium
CN112071041A (en) * 2020-08-31 2020-12-11 广东小天才科技有限公司 Security detection method, wearable device and computer-readable storage medium
CN112070016A (en) * 2020-09-08 2020-12-11 安徽兰臣信息科技有限公司 Detection method for identifying child behavior and action
CN112070016B (en) * 2020-09-08 2023-12-26 浙江铂视科技有限公司 Detection method for identifying child behavior and action
CN112381002B (en) * 2020-11-16 2023-08-15 深圳技术大学 Method and system for human risk posture recognition
US12009083B2 (en) 2020-11-16 2024-06-11 Electronic Caregiver, Inc. Remote physical therapy and assessment of patients
CN112381002A (en) * 2020-11-16 2021-02-19 深圳技术大学 Human body risk posture identification method and system
CN112949503A (en) * 2021-03-05 2021-06-11 齐齐哈尔大学 Site monitoring management method and system for ice and snow sports
CN112949503B (en) * 2021-03-05 2022-08-09 齐齐哈尔大学 Site monitoring management method and system for ice and snow sports
CN113034503A (en) * 2021-05-28 2021-06-25 博奥生物集团有限公司 High-flux automatic cup separating method, device and system
CN113627369A (en) * 2021-08-16 2021-11-09 南通大学 Action recognition and tracking method in auction scene
CN114495264B (en) * 2021-12-31 2025-12-12 北京龙智数科科技服务有限公司 Methods and devices for detecting backward climbing behavior on slides
CN114495264A (en) * 2021-12-31 2022-05-13 上海卓菡科技有限公司 Method and device for detecting behavior of reverse climbing slide
WO2023130696A1 (en) * 2022-01-05 2023-07-13 深眸科技(北京)有限公司 Smart system for automatically tracking-photographing sports events, and control method therefor
CN114842401A (en) * 2022-05-25 2022-08-02 广州智能科技发展有限公司 Method and system for capturing and classifying human body actions
CN117373110B (en) * 2023-08-30 2025-02-11 武汉星巡智能科技有限公司 Infant behavior recognition method, device and equipment based on visible light-thermal infrared imaging
CN117373110A (en) * 2023-08-30 2024-01-09 武汉星巡智能科技有限公司 Visible light-thermal infrared imaging infant behavior recognition method, device and equipment

Similar Documents

Publication Publication Date Title
CN106056035A (en) Motion-sensing technology based kindergarten intelligent monitoring method
CN105913559B (en) A kind of ATM in bank intelligent control method based on body-sensing technology
Feng et al. Spatio-temporal fall event detection in complex scenes using attention guided LSTM
Asif et al. Privacy preserving human fall detection using video data
US10235565B2 (en) System and methodologies for occupant monitoring utilizing digital neuromorphic (NM) data and fovea tracking
CN105574501B (en) A kind of stream of people's video detecting analysis system
CN110321780B (en) Detection method of abnormal fall behavior based on spatiotemporal motion characteristics
CN109154976A (en) System and method for training object classifiers via machine learning
CN109670446A (en) Anomaly detection method based on linear dynamic system and depth network
CN108229407A (en) A kind of behavioral value method and system in video analysis
Almaadeed et al. A novel approach for robust multi human action recognition and summarization based on 3D convolutional neural networks
Osigbesan et al. Vision-based fall detection in aircraft maintenance environment with pose estimation
CN118887604A (en) Campus safety control method and system based on AI video technology
CN114758326A (en) Real-time traffic post working behavior state detection system
Tripathy et al. Advances in human activity detection and recognition (hadr) systems
CN114596587B (en) Group monkey action recognition method based on spatiotemporal interaction network
Burkert et al. UAV-based monitoring of pedestrian groups
Khalili et al. Elderly fall detection using CCTV cameras under partial occlusion of the subjects body
Pervaiz et al. An optimized system for human behaviour analysis in E-learning
CN116778666A (en) Child motion safety monitoring system and method
ShanShan et al. Fall detection method based on semi-contour distances
CN116416565A (en) A method and system for detecting pedestrians following and overtaking in a specific area
Lee A smart camera network with SVM classifiers for crowd event recognition
CN120612657B (en) Security control and early warning system based on multi-source data fusion and AI large model analysis
Halder et al. Anomalous activity detection from ego view camera of surveillance robots

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20161026