CN111814718A - Attention detection method integrating multiple discrimination technologies - Google Patents
Attention detection method integrating multiple discrimination technologies Download PDFInfo
- Publication number
- CN111814718A CN111814718A CN202010691056.1A CN202010691056A CN111814718A CN 111814718 A CN111814718 A CN 111814718A CN 202010691056 A CN202010691056 A CN 202010691056A CN 111814718 A CN111814718 A CN 111814718A
- Authority
- CN
- China
- Prior art keywords
- face
- attention
- frames
- facial
- expression
- 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.)
- Withdrawn
Links
Images
Classifications
-
- 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
- G06V40/172—Classification, e.g. identification
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
- A61B5/1128—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique using image analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/168—Evaluating attention deficit, hyperactivity
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06V40/174—Facial expression recognition
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Pathology (AREA)
- Mathematical Physics (AREA)
- Veterinary Medicine (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Heart & Thoracic Surgery (AREA)
- Human Computer Interaction (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Physiology (AREA)
- Psychiatry (AREA)
- Developmental Disabilities (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Fuzzy Systems (AREA)
- Signal Processing (AREA)
- Child & Adolescent Psychology (AREA)
- Educational Technology (AREA)
- Hospice & Palliative Care (AREA)
Abstract
The invention discloses an attention detection method fusing multiple discrimination techniques, which comprises three stages of face pose estimation, face expression analysis and upper body behavior analysis, wherein the collected images are respectively subjected to the face pose estimation, the face expression analysis and the upper body behavior analysis by fusing multiple discrimination techniques, and then the analysis results of the three stages are combined to obtain a final attention detection result. By adopting the technology, the detection cost is greatly reduced without any tool, the economic benefit is improved, the quantitative analysis of the attention is realized, the attention is divided into four conditions of being not concentrated, being concentrated and being concentrated according to the quantitative result, and the accuracy of the attention detection is greatly improved.
Description
Technical Field
The invention relates to the technical field of computer vision and education informatization, in particular to an attention detection method integrating multiple discrimination technologies.
Background
Whether the attention of the students is concentrated in class is an important index reflecting the learning efficiency and the teaching quality. The traditional analysis of student attention mainly adopts means such as classroom observation or scale comparison, and has obvious defects and lags in the aspects of informatization, standardization, intellectualization and the like. With the rapid development of information technology, especially computer vision technology, information-based intelligence has been widely applied to various fields in daily life of people, it is possible to deploy an information system in a classroom to observe and record behavior and actions of students, and a technical approach is provided for automatically observing the attention of the students.
With the wide popularization of intelligent classes, the attention detection of students is an important component part and is widely researched by broad students and institutions. The invention patent (inventor: Sunning, Liu \20342; Xin, application number: 201910728874.1, name: student attention analysis system based on wearable equipment and multi-mode intelligent analysis) discloses a student attention analysis system based on wearable equipment and multi-mode intelligent analysis, which utilizes a multi-target detection algorithm based on a deep neural network to carry out curtain detection on a teacher and a projector curtain in a video and determine the positions of the two targets in the video; and finally, integrating the attitude data and the video detection data to analyze the attention of the current student. The invention patent (inventor: Huangliya, Wangshen, etc., application number: 201810530784.7, name: learning attention evaluation system based on electroencephalogram) discloses a learning attention evaluation system based on electroencephalogram, which is characterized in that a portable electroencephalogram acquisition device is equipped for each student, the wearable electroencephalogram acquisition device is used for acquiring electroencephalogram data of the student, and the learning attention state of the student is evaluated in real time by analyzing the electroencephalogram data of the class student. The invention patent (inventor: Liuwei, Xujing, etc., application No. 201910451277.9, name: a student attention measurement system based on a moving seat.) discloses a student attention measurement system based on a moving seat, which comprises three parts of student face orientation detection, moving seat positioning and attention orientation measurement, wherein the attention orientation measurement is combined with the position coordinates of the moving seat, the orientation of the moving seat and the face orientation of the student to calculate the orientation of the visual attention of the student. The invention patent (inventor: Yankee and Chili, application number: 201810297899.6, name: classroom attention detection method, device, equipment and computer readable medium) provides a classroom attention detection method, device, equipment and computer readable medium, which can accurately obtain the attention of the current student through face orientation analysis, pupil analysis and fatigue analysis of the eyes of the student. The invention patent (inventor: Dongshi, Zhangshuo, etc., application number: 201910435766.5, name: a method for analyzing the learning state of students in class in a natural teaching environment in real time) provides a method for analyzing the learning state of students in class in a natural teaching environment in real time, which judges the current learning state of the students by detecting whether human faces appear in static position areas of the students and combining expression analysis and head postures. The invention patent (inventor: Chen Liangying, Liu le Yuan, etc., application number: 201410836650.X, name: student classroom attention detection method and system) discloses a student classroom attention detection method, which converts the two-position of a face in an image into the two-dimensional position of a sitting high reference plane in a teacher, adds a student sitting high prior value to obtain the three-dimensional space position of the face in a classroom, and calculates the attention point of a student on a teaching display board by combining the face orientation posture.
The above-mentioned partial method needs every student to wear head-mounted equipment and measures, has the problem that cost is high, and influences student's teaching experience and teaching effect greatly, and other methods have the great problem of error.
Disclosure of Invention
In view of the above problems of the conventional attention detection method, it is an object of the present invention to provide an attention detection method that combines a plurality of discrimination techniques.
The attention detection method fusing multiple discrimination technologies is characterized by comprising the following steps:
step 1: in the face pose estimation stage, the face poses are classified by using a convolutional neural network, and the face is classified into specific pose categories, specifically:
step 1.1: training the facial images of five different posture categories by utilizing a deep convolutional neural network to obtain a trained facial posture classification model M1The face pose class label C ═ { C ═ C1,c2,c3,c4,c5In which c is1、c2、c3、c4、c5Representing five different human face postures which respectively correspond to a front face, a 45-degree side face, a head-up face, a head-down face and a 75-degree side face;
step 1.2: setting the total frame number of the images collected in the time period t as N, wherein the front face frame number is N1The number of 45-degree side frames is N2The number of head-up frames is N3The number of low frames is N475 degree side frame number N5(ii) a Calculating the attention detection result r in the face pose estimation stage according to the formula (1)1;
r1=(N1+N2+N3)/N (1)
Wherein r is1∈[0,1.0]0 means inattention, 1.0 means complete attention;
step 2: in the facial expression analysis stage, the convolutional neural network is used for classifying the facial expressions, and the facial expressions are classified into specific categories, specifically:
step 2.1: training facial images of five different expressions by utilizing a deep convolutional neural network to obtain a trained facial expression classification model M2The facial expression category label L ═ L1,l2,l3,l4,l5In which l1、l2、l3、l4、l5The facial expression system is characterized by showing five different facial expressions which respectively correspond to normal expressions, happy feeling, sadness, confusion and surprise;
step 2.2: setting the total number of the image frames acquired within the time t as N, wherein the number of the normal expression frames is F1The number of the happy expression frames is F2The number of the sad expression frames is F3Number of suspected expression frames is F4The number of surprised expression frames is F5(ii) a Calculating an attention detection result in a facial expression analysis stage according to the formula (2);
r2=(F1+F4)/N (2)
wherein r is2∈[0,1.0]0 means inattention, 1.0 means complete attention;
and step 3: in the upper half body behavior analysis stage, the upper half body behaviors are classified by using a convolutional neural network, and the upper half body behaviors are classified into specific categories, specifically:
step 3.1: training images of four different upper half body behaviors by utilizing a deep convolutional neural network to obtain a trained upper half body behavior classification model M3The upper body behavior category label K ═ K1,k2,k3,k4In which k is1、k2、k3、k4The method comprises the following steps of representing four different upper body behaviors, which respectively correspond to a normal behavior, a hand-held face, drinking water and playing a mobile phone;
step 3.2: the total frame number of the images collected in the time t is N, wherein the normal action number is P1The number of the hand-held face frames is P2The number of drinking frames is P3The number of playing frames is P4(ii) a Calculating the attention detection result of the upper half body behavior analysis stage according to the formula (3);
r3=P1/N (3)
wherein r is3∈[0,1.0]0 means inattention, 1.0 means complete attention;
and 4, step 4: obtaining an attention comprehensive evaluation result RLT according to the formulas (4) and (5);
R=r1×r2×r3(4)
wherein R ∈ [0,1.0], 0 means inattention, and 1.0 means complete attention.
The invention has the beneficial effects that:
1) the invention does not need to wear head-wearing equipment, and only needs to acquire data through the camera, thereby greatly reducing the cost;
2) the invention combines the convolutional neural network to carry out attention analysis, classifies the input images by using three classification models, namely a face posture classification model, a face expression classification model and an upper body behavior classification model, classifies the images into corresponding classes, gives class labels to the images, carries out comprehensive evaluation on attention by fusing various discrimination techniques, and can further improve the accuracy of attention discrimination.
Drawings
FIG. 1 is a schematic diagram of a frame of an attention detection method with multiple discrimination techniques integrated therein according to the present invention.
Detailed Description
The invention is further described below with reference to the drawings and examples of the specification. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, the attention detection method combining multiple discrimination techniques of the present invention specifically includes the following steps:
step 1: in the face pose estimation stage, the face poses are classified by using a convolutional neural network, and the face is classified into specific pose categories, specifically:
step 1.1: training the facial images of five different posture categories by utilizing a deep convolutional neural network to obtain a trained facial posture classification model M1The face pose class label C ═ { C ═ C1,c2,c3,c4,c5In which c is1、c2、c3、c4、c5Representing five different human face postures which respectively correspond to a front face, a 45-degree side face, a head-up face, a head-down face and a 75-degree side face;
step 1.2: setting the total frame number of the images collected in the time period t as N, wherein the front face frame number is N1The number of 45-degree side frames is N2The number of head-up frames is N3The number of low frames is N475 degree side frame number N5(ii) a Calculating the attention detection result r in the face pose estimation stage according to the formula (1)1;
r1=(N1+N2+N3)/N (1)
Wherein r is1∈[0,1.0]0 means inattention, 1.0 means complete attention;
step 2: in the facial expression analysis stage, the convolutional neural network is used for classifying the facial expressions, and the facial expressions are classified into specific categories, specifically:
step 2.1: training facial images of five different expressions by utilizing a deep convolutional neural network to obtain a trained facial expression classification model M2The facial expression category label L ═ L1,l2,l3,l4,l5In which l1、l2、l3、l4、l5The facial expression system is characterized by showing five different facial expressions which respectively correspond to normal expressions, happy feeling, sadness, confusion and surprise;
step 2.2: setting the total number of the image frames acquired within the time t as N, wherein the number of the normal expression frames is F1The number of the happy expression frames is F2The number of the sad expression frames is F3Number of suspected expression frames is F4The number of surprised expression frames is F5(ii) a Calculating a face table according to equation (2)Attention detection results of the situation analysis stage;
r2=(F1+F4)/N (2)
wherein r is2∈[0,1.0]0 means inattention, 1.0 means complete attention;
and step 3: in the upper half body behavior analysis stage, the upper half body behaviors are classified by using a convolutional neural network, and the upper half body behaviors are classified into specific categories, specifically:
step 3.1: training images of four different upper half body behaviors by utilizing a deep convolutional neural network to obtain a trained upper half body behavior classification model M3The upper body behavior category label K ═ K1,k2,k3,k4In which k is1、k2、k3、k4The method comprises the following steps of representing four different upper body behaviors, which respectively correspond to a normal behavior, a hand-held face, drinking water and playing a mobile phone;
step 3.2: the total frame number of the images collected in the time t is N, wherein the normal action number is P1The number of the hand-held face frames is P2The number of drinking frames is P3The number of playing frames is P4(ii) a Calculating the attention detection result of the upper half body behavior analysis stage according to the formula (3);
r3=P1/N (3)
wherein r is3∈[0,1.0]0 means inattention, 1.0 means complete attention;
and 4, step 4: obtaining an attention comprehensive evaluation result RLT according to the formulas (4) and (5);
R=r1×r2×r3(4)
wherein R ∈ [0,1.0], 0 means inattention, and 1.0 means complete attention.
Claims (1)
1. An attention detection method fusing multiple discrimination techniques is characterized by comprising the following steps:
step 1: in the face pose estimation stage, the face poses are classified by using a convolutional neural network, and the face is classified into specific pose categories, specifically:
step 1.1: training the facial images of five different posture categories by utilizing a deep convolutional neural network to obtain a trained facial posture classification model M1The face pose class label C ═ { C ═ C1,c2,c3,c4,c5In which c is1、c2、c3、c4、c5Representing five different human face postures which respectively correspond to a front face, a 45-degree side face, a head-up face, a head-down face and a 75-degree side face;
step 1.2: setting the total frame number of the images collected in the time period t as N, wherein the front face frame number is N1The number of 45-degree side frames is N2The number of head-up frames is N3The number of low frames is N475 degree side frame number N5(ii) a Calculating the attention detection result r in the face pose estimation stage according to the formula (1)1;
r1=(N1+N2+N3)/N (1)
Wherein r is1∈[0,1.0]0 means inattention, 1.0 means complete attention;
step 2: in the facial expression analysis stage, the convolutional neural network is used for classifying the facial expressions, and the facial expressions are classified into specific categories, specifically:
step 2.1: training facial images of five different expressions by utilizing a deep convolutional neural network to obtain a trained facial expression classification model M2The facial expression category label L ═ L1,l2,l3,l4,l5In which l1、l2、l3、l4、l5The facial expression system is characterized by showing five different facial expressions which respectively correspond to normal expressions, happy feeling, sadness, confusion and surprise;
step 2.2: let the total frame of the image acquired within time tThe number is N, wherein the number of the normal expression frames is F1The number of the happy expression frames is F2The number of the sad expression frames is F3Number of suspected expression frames is F4The number of surprised expression frames is F5(ii) a Calculating an attention detection result in a facial expression analysis stage according to the formula (2);
r2=(F1+F4)/N (2)
wherein r is2∈[0,1.0]0 means inattention, 1.0 means complete attention;
and step 3: in the upper half body behavior analysis stage, the upper half body behaviors are classified by using a convolutional neural network, and the upper half body behaviors are classified into specific categories, specifically:
step 3.1: training images of four different upper half body behaviors by utilizing a deep convolutional neural network to obtain a trained upper half body behavior classification model M3The upper body behavior category label K ═ K1,k2,k3,k4In which k is1、k2、k3、k4The method comprises the following steps of representing four different upper body behaviors, which respectively correspond to a normal behavior, a hand-held face, drinking water and playing a mobile phone;
step 3.2: the total frame number of the images collected in the time t is N, wherein the normal action number is P1The number of the hand-held face frames is P2The number of drinking frames is P3The number of playing frames is P4(ii) a Calculating the attention detection result of the upper half body behavior analysis stage according to the formula (3);
r3=P1/N (3)
wherein r is3∈[0,1.0]0 means inattention, 1.0 means complete attention;
and 4, step 4: obtaining an attention comprehensive evaluation result RLT according to the formulas (4) and (5);
R=r1×r2×r3(4)
wherein R ∈ [0,1.0], 0 means inattention, and 1.0 means complete attention.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010691056.1A CN111814718A (en) | 2020-07-17 | 2020-07-17 | Attention detection method integrating multiple discrimination technologies |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010691056.1A CN111814718A (en) | 2020-07-17 | 2020-07-17 | Attention detection method integrating multiple discrimination technologies |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111814718A true CN111814718A (en) | 2020-10-23 |
Family
ID=72865425
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010691056.1A Withdrawn CN111814718A (en) | 2020-07-17 | 2020-07-17 | Attention detection method integrating multiple discrimination technologies |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111814718A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113255572A (en) * | 2021-06-17 | 2021-08-13 | 华中科技大学 | Classroom attention assessment method and system |
CN114159077A (en) * | 2022-02-09 | 2022-03-11 | 浙江强脑科技有限公司 | Meditation scoring method, device, terminal and storage medium based on electroencephalogram signals |
CN114366103A (en) * | 2022-01-07 | 2022-04-19 | 北京师范大学 | Attention assessment method and device and electronic equipment |
WO2023000838A1 (en) * | 2021-07-22 | 2023-01-26 | 北京有竹居网络技术有限公司 | Information detection method and apparatus, medium, and electronic device |
-
2020
- 2020-07-17 CN CN202010691056.1A patent/CN111814718A/en not_active Withdrawn
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113255572A (en) * | 2021-06-17 | 2021-08-13 | 华中科技大学 | Classroom attention assessment method and system |
WO2023000838A1 (en) * | 2021-07-22 | 2023-01-26 | 北京有竹居网络技术有限公司 | Information detection method and apparatus, medium, and electronic device |
CN114366103A (en) * | 2022-01-07 | 2022-04-19 | 北京师范大学 | Attention assessment method and device and electronic equipment |
CN114159077A (en) * | 2022-02-09 | 2022-03-11 | 浙江强脑科技有限公司 | Meditation scoring method, device, terminal and storage medium based on electroencephalogram signals |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111814718A (en) | Attention detection method integrating multiple discrimination technologies | |
CN111528859B (en) | Child ADHD screening and evaluating system based on multi-modal deep learning technology | |
CN110349667B (en) | Autism assessment system combining questionnaire and multi-modal model behavior data analysis | |
CN113762133A (en) | Self-weight fitness auxiliary coaching system, method and terminal based on human body posture recognition | |
CN111563452B (en) | Multi-human-body gesture detection and state discrimination method based on instance segmentation | |
Ludl et al. | Enhancing data-driven algorithms for human pose estimation and action recognition through simulation | |
CN109885595A (en) | Course recommended method, device, equipment and storage medium based on artificial intelligence | |
CN110363129A (en) | Autism early screening system based on smile normal form and audio-video behavioural analysis | |
CN111523445B (en) | Examination behavior detection method based on improved Openpost model and facial micro-expression | |
CN113486744B (en) | Student learning state evaluation system and method based on eye movement and facial expression paradigm | |
Zaletelj | Estimation of students' attention in the classroom from kinect features | |
CN116645721B (en) | Sitting posture identification method and system based on deep learning | |
Panetta et al. | Software architecture for automating cognitive science eye-tracking data analysis and object annotation | |
Tang et al. | Automatic facial expression analysis of students in teaching environments | |
CN116109455A (en) | Language teaching auxiliary system based on artificial intelligence | |
Xu et al. | Wayfinding design in transportation architecture–are saliency models or designer visual attention a good predictor of passenger visual attention? | |
CN114022918A (en) | Multi-posture-based learner excitement state label algorithm | |
Enadula et al. | Recognition of student emotions in an online education system | |
Guo et al. | PhyCoVIS: A visual analytic tool of physical coordination for cheer and dance training | |
CN117542121A (en) | Computer vision-based intelligent training and checking system and method | |
CN112836945A (en) | Teaching state quantitative evaluation system for teaching and teaching of professor | |
CN107862246A (en) | A kind of eye gaze direction detection method based on various visual angles study | |
Xu et al. | Analyzing students' attention by gaze tracking and object detection in classroom teaching | |
Pang et al. | Recognition of Academic Emotions in Online Classes | |
CN115797829A (en) | Online classroom learning state analysis method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201023 |
|
WW01 | Invention patent application withdrawn after publication |