CN110334610A - A kind of various dimensions classroom based on computer vision quantization system and method - Google Patents
A kind of various dimensions classroom based on computer vision quantization system and method Download PDFInfo
- Publication number
- CN110334610A CN110334610A CN201910516795.4A CN201910516795A CN110334610A CN 110334610 A CN110334610 A CN 110334610A CN 201910516795 A CN201910516795 A CN 201910516795A CN 110334610 A CN110334610 A CN 110334610A
- Authority
- CN
- China
- Prior art keywords
- classroom
- student
- video
- instruction
- data
- 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.)
- Granted
Links
- 238000013139 quantization Methods 0.000 title claims abstract description 27
- 238000000034 method Methods 0.000 title claims abstract description 20
- 230000006399 behavior Effects 0.000 claims abstract description 50
- 238000013079 data visualisation Methods 0.000 claims abstract description 15
- 238000011156 evaluation Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 13
- 206010000117 Abnormal behaviour Diseases 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 8
- 230000003542 behavioural effect Effects 0.000 claims abstract description 5
- 238000011002 quantification Methods 0.000 claims abstract description 5
- 241001269238 Data Species 0.000 claims abstract description 4
- 230000002996 emotional effect Effects 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000013135 deep learning Methods 0.000 claims description 6
- 238000012800 visualization Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000013500 data storage Methods 0.000 claims description 3
- 230000036651 mood Effects 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims description 2
- 230000005484 gravity Effects 0.000 claims description 2
- 238000004445 quantitative analysis Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000013473 artificial intelligence Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 5
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 206010027940 Mood altered Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007510 mood change Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a kind of various dimensions classroom based on computer vision quantization system and method, which includes: data acquisition module, for acquiring the video of the positive plane video of student and teachers' instruction that classroom is attended class in real time;Generating date module is attended class the detection and identification of learning behavior for realizing teachers' instruction behavioral value and identification, student;Data visualization display module, for from four angular quantification classrooms and visualizing, to construct the novel evaluation system of the two-way dimension of Faculty and Students to quantify classroom;Data memory module, the original video data including whole course retains, student's abnormal behaviour cuts frame reservation, classroom instruction assessment report generation, to three part storing datas of processing result from original video to treatment process.The present invention can automatically, intelligently evaluate classroom, facilitate teacher to refer to classroom instruction process after class, quality of instruction fed back to pointedly improve teaching efficiency according to the students ' behavior result of quantization, student is promoted to improve in study.
Description
Technical field
The present invention relates to education artificial intelligence field and Teaching Evaluation System fields, more particularly to a kind of computer that is based on to regard
The various dimensions classroom quantization system and method for feel.
Background technique
In recent years, the support energetically with the development of artificial intelligence and China for artificial intelligence, China has become
One of country most positive using artificial intelligence technology, widest.And this ancient and traditional industry is educated also quietly
It changes, internet is reconstructing study, and artificial intelligence will inclusive education.It is energized by artificial intelligence and educates scene point
Analysis, solves the computability, comprehensibility, evaluable property of education scene, thus realize accurate efficient classroom behavior analysis, it can
The classroom instruction assessment system of sustainable development and the acquisition of education big data and convergence of standardization.For a long time, traditional teaching is commented
Appraisal body is to be arranged with questionnaire survey, teaching manager mostly with hall observation, after class based on classroom observing, there is presently no
The Integrated Teaching evaluation system based on artificial intelligence technology under data-driven designs a set of combination big data, artificial thus
Intellectual technology automatically quantifies classroom, based on data-driven and automatically evaluates classroom system and is of great significance, convenient for reducing
More teacher workloads for being used to evaluate classroom manual observation, while a kind of intelligence based on data for education administrators being provided
It can aid decision-making system.
Summary of the invention
The technical problem to be solved in the present invention is that for quantifying in the prior art, hall of teaching being commented generally to pass through hand-operated manpower
It observes classroom time and effort consuming and lacks data supporting, subjective defect, a kind of various dimensions based on computer vision are provided
Classroom quantization system and method utilize artificial intelligence, education big data technology, automation quantization, evaluation classroom, to reduce religion
Evaluation work amount is learned, teaching evaluation validity is promoted.
The technical solution adopted by the present invention to solve the technical problems is:
The present invention provides a kind of various dimensions classroom based on computer vision quantization system, which includes: data acquisition
Module, generating date module, data visualization display module, data memory module;Wherein:
Data acquisition module, for acquiring the video of the positive plane video of student and teachers' instruction that classroom is attended class in real time, and
It is sent to generating date module;
Generating date module is attended class the inspection of learning behavior for realizing teachers' instruction behavioral value and identification, student
It surveys and identification, and the data after will test are passed to data visualization display module and data memory module;
Data visualization display module, including novel classroom assessment indicator system are used for from four angular quantification classrooms simultaneously
It visualizes, including student's focus, classroom emotional change level, student classroom region liveness, teachers' instruction class
Type, to construct the novel evaluation system of the two-way dimension of Faculty and Students to quantify classroom;
Data memory module, the original video data including whole course retains, student's abnormal behaviour cuts frame reservation, classroom is commented
Valence report generation refers to class for teacher to three part storing datas of processing result from original video to treatment process after class
Hall teaching process feeds back quality of instruction according to the students ' behavior result of quantization to pointedly improve teaching efficiency, promotes to learn
Life is improved in study.
Further, data acquisition module of the invention acquires the front for the student that attends class using former and later two cameras of classroom
Video and the video of giving lessons of teacher amount to two-path video, are then sent to data processing module.
Further, data processing module of the invention is detected and is identified for realizing the two-path video of student and teacher,
Wherein:
In first via video, using opencv tool carry out student attend class front video flowing interception frame be then fed into depth
In learning network, deep learning network is adopted as the object detection method based on YOLOV3, and exports the current study row of student
For and its position;
Meanwhile second in the video of road, equally carries out interception segment using opencv tool, is sent to depth RNN net
Network carries out teachers' instruction mode Classification and Identification.
Further, the teachers' instruction behavior and student identified in generating date module of the invention attends class and learns to go
To include:
Student's learning behavior includes: new line, read, record the note, taking pictures, play mobile phone, sleep, speaking, head pose adjustment,
Arrange clothing totally nine kinds of behaviors;
Teachers' instruction behavior includes: to explain when operating PPT, stand and saying edge of table explanation, the explanation that is seated, standing and say in student
Solution is explained when walking, only plays multimedia video, writing on the blackboard, only operates multimedia, teacher's enquirement, other totally ten kinds of behaviors.
Further, novel classroom assessment indicator system includes that student is absorbed in data visualization display module of the invention
Degree, classroom emotional change level, student classroom region liveness, teachers' instruction type;Wherein:
Student's focus includes 5 two-level index: new line rate, reads the rate, sleep rate of recording the note at the rate that sees the mobile phone, and calculates public
Formula are as follows:
Wherein, m indicates that the number of all students' generation behavior in current time classroom, n indicate in current time classroom
The summation of all behavior frequencies;
Classroom emotional levels are divided into high, steady, droning three kinds of states, and it is high for coming back, read, recording the note, taking pictures
State;Speak, head pose adjustment, arrange clothing be steady state, play mobile phone, sleep be droning state;Classroom mood
Level calculation mode is that the maximum state of specific gravity is the class in current 1 minute in three kinds of classroom emotional levels states in 1 minute
Hall emotional levels;
Classroom region liveness calculation is that the students ' behavior state that will test carries out ten according to seat overall distribution
Student's seating area is divided into four regions up and down towards blackboard by word subregion, compare wherein classroom emotional levels height,
And the active degree in its region is indicated by the depth of grid figure color.
Further, data memory module of the invention includes that original video saves submodule, abnormal behaviour retains submodule
Block, classroom instruction assessment report submodule totally three submodules;Wherein:
Original video saves submodule, for saving the positive plane video of student attended class and teacher gives lessons video;
Abnormal behaviour retains submodule, the abnormal behaviour mark of sleep, object for appreciation mobile phone for being exported by deep learning network
Then label cut frame line using the tool box opencv as region reservation;
Classroom instruction assessment reports submodule, for generating the classroom behavior of a whole course than redistribution pie chart, classroom mood water
Accounting is distributed proportion map, the distribution map of whole course region liveness, teachers' instruction genre distribution figure between usually.
Further, the system of the invention operates in the PC operating system containing GPU video card.
The present invention provides a kind of various dimensions classroom based on computer vision quantization method, comprising the following steps:
Step 1: video stream data acquisition;
By being distributed in above blackboard facing towards the camera of student and being carried out in the camera of classroom rear portion towards teacher
The acquisition of two-path video data, is entered into video processing module after acquisition;
Step 2: video data processing;
Two-way analysis, the view of giving lessons of positive plane video and teacher including the student that attends class are carried out by the video that step 1 inputs
Frequency amounts to two-path video;For student's video using opencv carry out real-time video interception current image frame be input to it is trained
Good target detection model YOLOV3 carries out the detection of learning behavior on 9 kinds of classes of student, i.e., the position of network output student and
The learning behavior state of current time student;To teacher's video, then inputted using the interception of opencv tool video frame of attending class
The Classification and Identification that teachers' instruction style is carried out into trained depth RNN video classification model, by Faculty and Students two
The label information of a dimension output is passed to data visualization display module and data memory module;
Step 3: data visualization is shown;
Student position, behavior state information and the teachers' instruction style information inputted by step 2, carries out visualization exhibition
Show, specifically include 5 submodules: classroom behavior main interface, visualization area, dynamic statistics Index areas, the area Jie Zheng, classroom portrait
Area, after main interface area is by the acquisition training of a large amount of data, the inputting video data study current to video real-time display student
State and teachers' instruction style;It visualizes area and the behavior of classroom student is passed through into classroom overall evaluation index after quantitative analysis
Classroom focus, classroom emotional change level, classroom region liveness, teachers' instruction style situation of change are shown;Dynamically
Statistical indicator area counts classroom middle school student new line rate, rate of bowing, the index for the number that sees the mobile phone;The area Jie Zheng is i.e. by exceptional student shape
State carries out screenshot reservation, so as to subsequent analysis;Classroom portrait area generates classroom portrait and macroscopical whole classroom instruction assessment is analyzed and reported
It accuses;
Step 4: data storage;
The original video data for retaining classroom first, comprising student and teacher's two-path video in case subsequent check;Root simultaneously
According to the label and location information of the student that step 2 exports, the student that interception retains 16*16 pixel value plays the exception of mobile phone, sleep
Behavior;Ultimately producing classroom instruction assessment analysis report includes that the classroom behavior distribution pie chart of whole course and table, classroom region are enlivened
Degree variation hotspot graph, classroom situation change level fluctuate line chart, teachers' instruction style accounting figure.
The beneficial effect comprise that: various dimensions classroom based on computer vision quantization system of the invention and side
Method is based on data-driven, the quantization that is automated using artificial intelligence and big data analysis technology, evaluation classroom, allows classroom instruction assessment
It is relatively objective, there is data explanation strengths, reduce traditional subjective questionnaire news commentary and teach subjectivity, reduce a large amount of craft of classroom instruction assessment
Ground, mechanical labour.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the overall structure diagram of the embodiment of the present invention;
Fig. 2 is the visual presentation function structure chart of the embodiment of the present invention;
Fig. 3 is the data memory module structure chart of the embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
As shown in Figure 1, the various dimensions classroom based on computer vision quantization system of the embodiment of the present invention, is based on computer
The classroom quantization method of vision using the computer vision technique in deep learning from the angle of figure to classroom scene from teachers and students
Two dimensions are quantified, and based on data quantization classroom scene, based on data science evaluate classroom.The system includes: data
Acquisition module, generating date module, data visualization display module, data memory module;Wherein:
Data acquisition module, for acquiring the video of the positive plane video of student and teachers' instruction that classroom is attended class in real time, and
It is sent to generating date module;
Generating date module is attended class the inspection of learning behavior for realizing teachers' instruction behavioral value and identification, student
It surveys and identification, and the data after will test are passed to data visualization display module and data memory module;
Data visualization display module, including novel classroom assessment indicator system are used for from four angular quantification classrooms simultaneously
It visualizes, including student's focus, classroom emotional change level, student classroom region liveness, teachers' instruction class
Type, to construct the novel evaluation system of the two-way dimension of Faculty and Students to quantify classroom;
Data memory module, the original video data including whole course retains, student's abnormal behaviour cuts frame reservation, classroom is commented
Valence report generation refers to class for teacher to three part storing datas of processing result from original video to treatment process after class
Hall teaching process feeds back quality of instruction according to the students ' behavior result of quantization to pointedly improve teaching efficiency, promotes to learn
Life is improved in study.
The classroom quantization method based on computer vision of the embodiment of the present invention, comprising the following steps:
Step 1: video data acquiring;
It is respectively placed in right above blackboard in classroom by 2 tunnel Austria wire high definition video collecting equipment of erection and faces student
Rear with classroom is towards teacher, to carry out the acquisition of the positive plane video of student and the acquisition of teachers' instruction video;
Step 2: video data processing module;
Divide two-way to be inputted in different deep learning models respectively the collected video data of step 1, specifically for
The positive plane video of student passes through the real-time 24fps detection class of YOLOV3 (YOLOv3:An Incremental Improvement) network
The learning behavior of each student in hall, such as object for appreciation mobile phone, record the note, to read 9 kinds of specific students ' behaviors of behavior as shown in table 1, and
By its position, frame is elected;Teacher's video in network will enter into for the detection of teachers' instruction style and utilize opencv tool
Depth RNN (Deep RNN Framework for is input to according to the key frame of video of the time interval interception class-teaching of teacher of 1s
Visual Sequential Applications) the genre classification detection output writing on the blackboard that carries out in network giving lessons, operation multimedia,
It puts question to, stand and saying that it is as shown in table 1 that edge of table such as explains at 9 kinds of stylistic categories of giving lessons style of specifically giving lessons.
The behavior category table of 1 student of table and teacher
Step 3: visualizing module;
The students ' behavior position and class label that are exported by input step 2 and the recognition result of teachers' instruction style into
Row visualizes, and includes 5 submodules: main interface, dynamic indicator area, the area Jie Zheng, visualization area, classroom report area, wherein
Visualization area includes classroom emotional levels variation line chart, classroom region liveness hotspot graph, classroom focus change curve again
Figure, teachers' instruction Behavioral change figure, from two angular quantification classrooms of teachers and students, evaluation classroom.It is specific as shown in Figure 2
Step 4: data memory module;
Data storage module is divided into three submodules, retains the original video data in classroom first, regards comprising student front
Frequency and teacher's two-path video are in case subsequent check;The label and location information of the student exported simultaneously according to step 2, interception retain
The student of 16*16 pixel value plays the abnormal behaviour of mobile phone, sleep;Ultimately produce the class that classroom instruction assessment analysis report includes whole course
Hall behavior distribution map and classroom region liveness change hotspot graph, classroom emotional change wave pattern, teachers' instruction style accounting figure.
Wherein the students ' behavior frequency of whole course is carried out cumulative drafting table and ratio is drawn to scale by classroom behavior distribution map
Example pie chart, classroom region liveness variation hotspot graph will count the whole classroom region liveness situation of whole course, classroom mood
Change wave pattern and draws the classroom emotional change fluctuation line chart for drawing a class middle school student according to 1 minute time scale, religion
Teachers' instruction style frequency cumulative draw table and ratio pie chart is drawn to scale by teacher's style accounting figure of giving lessons.
General frame is specifically as shown in Figure 3.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (8)
1. a kind of various dimensions classroom based on computer vision quantization system, which is characterized in that the system includes: data acquisition module
Block, generating date module, data visualization display module, data memory module;Wherein:
Data acquisition module, for acquiring the video of the positive plane video of student and teachers' instruction that classroom is attended class in real time, and by its
It is sent into generating date module;
Generating date module, for realizing teachers' instruction behavioral value and identification, student attend class learning behavior detection with
Identification, and the data after will test are passed to data visualization display module and data memory module;
Data visualization display module, including novel classroom assessment indicator system, for from four angular quantification classrooms and visual
Change and shows, including student's focus, classroom emotional change is horizontal, student classroom region liveness, teachers' instruction type, from
And the novel evaluation system of the two-way dimension of Faculty and Students is constructed to quantify classroom;
Data memory module, the original video data including whole course retains, student's abnormal behaviour cuts frame reservation, classroom instruction assessment report
It accuses and generates, to three part storing datas of processing result from original video to treatment process, refer to classroom religion after class for teacher
Process feeds back quality of instruction according to the students ' behavior result of quantization to pointedly improve teaching efficiency, student is promoted to learn
Practise progress.
2. various dimensions classroom based on computer vision quantization system according to claim 1, which is characterized in that data are adopted
Collection module acquires the total two-way view of video of giving lessons of the positive plane video and teacher for the student that attends class using former and later two cameras of classroom
Frequently, then it is sent to data processing module.
3. various dimensions classroom based on computer vision quantization system according to claim 1, which is characterized in that at data
Module is managed, detects and identifies for realizing the two-path video of student and teacher, in which:
In first via video, using opencv tool carry out student attend class front video flowing interception frame be then fed into deep learning
In network, deep learning network is adopted as the object detection method based on YOLOV3, and export student current learning behavior and
Its position;
Meanwhile second in the video of road, equally carries out interception segment using opencv tool, be sent to depth RNN network into
Row teachers' instruction mode Classification and Identification.
4. various dimensions classroom based on computer vision quantization system according to claim 1, which is characterized in that data are real
When processing module in the teachers' instruction behavior that identifies and student learning behavior of attending class include:
Student's learning behavior includes: new line, read, record the note, taking pictures, play mobile phone, sleep, speaking, head pose adjustment, arranges
The totally nine kind behavior of clothing clothes;
Teachers' instruction behavior include: explained when operating PPT, stand say edge of table explanation, the explanation that is seated, explanation of standing in student,
It is explained when walking, only plays multimedia video, writing on the blackboard, only operates multimedia, teacher puts question to, other totally ten kinds of behaviors.
5. various dimensions classroom based on computer vision quantization system according to claim 1, which is characterized in that data can
It include student's focus, classroom emotional change level, student classroom area depending on changing novel classroom assessment indicator system in display module
Domain liveness, teachers' instruction type;Wherein:
Student's focus includes 5 two-level index: new line rate, reads the rate, sleep rate of recording the note, calculation formula at the rate that sees the mobile phone are as follows:
Wherein, m indicates that the number of all students' generation behavior in current time classroom, n indicate own in current time classroom
The summation of behavior frequency;
Classroom emotional levels are divided into high, steady, droning three kinds of states, and coming back, read, recording the note, taking pictures is high state;
Speak, head pose adjustment, arrange clothing be steady state, play mobile phone, sleep be droning state;Classroom emotional levels meter
Calculation mode is that the maximum state of specific gravity is the classroom mood in current 1 minute in three kinds of classroom emotional levels states in 1 minute
It is horizontal;
Classroom region liveness calculation is that the students ' behavior state that will test carries out cross point according to seat overall distribution
Student's seating area is divided into four regions up and down towards blackboard by area, compare wherein classroom emotional levels height, and lead to
The depth for crossing grid figure color indicates the active degree in its region.
6. various dimensions classroom based on computer vision quantization system according to claim 1, which is characterized in that data are deposited
Storage module includes that original video saves submodule, abnormal behaviour retains submodule, classroom instruction assessment reports submodule totally three submodules
Block;Wherein:
Original video saves submodule, for saving the positive plane video of student attended class and teacher gives lessons video;
Abnormal behaviour retains submodule, the abnormal behaviour label of sleep, object for appreciation mobile phone for being exported by deep learning network, so
Cut frame line using the tool box opencv afterwards as region reservation;
Classroom instruction assessment reports submodule, when for generating the classroom behavior of a whole course than redistribution pie chart, classroom emotional levels
Between accounting be distributed proportion map, the distribution map of whole course region liveness, teachers' instruction genre distribution figure.
7. various dimensions classroom based on computer vision quantization system according to claim 1, which is characterized in that the system
It operates in the PC operating system containing GPU video card.
8. a kind of being regarded based on computer using various dimensions classroom based on computer vision quantization system described in claim 1
The various dimensions classroom quantization method of feel, which comprises the following steps:
Step 1: video stream data acquisition;
By being distributed in above blackboard facing towards the camera of student and carrying out two-way in the camera of classroom rear portion towards teacher
Video data acquiring is entered into video processing module after acquisition;
Step 2: video data processing;
Two-way analysis is carried out by the video that step 1 inputs, the video of giving lessons of positive plane video and teacher including the student that attends class is total
Count two-path video;For student's video using opencv carry out real-time video interception current image frame be input to it is trained
Target detection model YOLOV3 carries out the detection of learning behavior on 9 kinds of classes of student, i.e. the position of network output student and current
The learning behavior state of moment student;To teacher's video, it is then input to using the interception of opencv tool video frame of attending class
The Classification and Identification that teachers' instruction style is carried out in trained good depth RNN video classification model, by two dimensions of Faculty and Students
The label information of degree output is passed to data visualization display module and data memory module;
Step 3: data visualization is shown;
Student position, behavior state information and the teachers' instruction style information inputted by step 2, is visualized, tool
Body includes 5 submodules: classroom behavior main interface, visualization area, dynamic statistics Index areas, the area Jie Zheng, classroom portrait area, main boundary
After face area is by the acquisition training of a large amount of data, the inputting video data learning state and religion current to video real-time display student
Teacher gives lessons style;The behavior of classroom student is absorbed in after quantitative analysis by classroom overall evaluation index classroom by visualization area
Degree, classroom emotional change level, classroom region liveness, teachers' instruction style situation of change are shown;Dynamic statistics index
Area counts classroom middle school student new line rate, rate of bowing, the index for the number that sees the mobile phone;The area Jie Zheng is cut exceptional student state
Figure retains, so as to subsequent analysis;Classroom portrait area generates the classroom portrait classroom instruction assessment analysis report whole with macroscopic view;
Step 4: data storage;
The original video data for retaining classroom first, comprising student and teacher's two-path video in case subsequent check;Simultaneously according to step
The label and location information of the student of rapid 2 output, the student that interception retains 16*16 pixel value play the abnormal behaviour of mobile phone, sleep;
Ultimately produce the classroom behavior distribution pie chart and table, the variation of classroom region liveness that classroom instruction assessment analysis report includes whole course
Hotspot graph, classroom situation change level fluctuate line chart, teachers' instruction style accounting figure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910516795.4A CN110334610B (en) | 2019-06-14 | 2019-06-14 | Multi-dimensional classroom quantification system and method based on computer vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910516795.4A CN110334610B (en) | 2019-06-14 | 2019-06-14 | Multi-dimensional classroom quantification system and method based on computer vision |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110334610A true CN110334610A (en) | 2019-10-15 |
CN110334610B CN110334610B (en) | 2024-01-26 |
Family
ID=68141123
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910516795.4A Active CN110334610B (en) | 2019-06-14 | 2019-06-14 | Multi-dimensional classroom quantification system and method based on computer vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110334610B (en) |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110708392A (en) * | 2019-10-17 | 2020-01-17 | 重庆工商职业学院 | Student management system and method based on cloud platform |
CN110782185A (en) * | 2019-11-09 | 2020-02-11 | 上海光数信息科技有限公司 | Classroom behavior recognition and analysis method |
CN110837795A (en) * | 2019-11-04 | 2020-02-25 | 防灾科技学院 | Teaching condition intelligent monitoring method, device and equipment based on classroom monitoring video |
CN110853428A (en) * | 2019-12-04 | 2020-02-28 | 广州云蝶科技有限公司 | Recording and broadcasting control method and system based on Internet of things |
CN111027865A (en) * | 2019-12-12 | 2020-04-17 | 山东大学 | Classroom teaching analysis and quality assessment system and method based on intelligent behavior and expression recognition |
CN111178273A (en) * | 2019-12-30 | 2020-05-19 | 云知声智能科技股份有限公司 | Education method and device based on emotion change |
CN111275592A (en) * | 2020-01-16 | 2020-06-12 | 浙江工业大学 | Classroom behavior analysis method based on video images |
CN111291840A (en) * | 2020-05-12 | 2020-06-16 | 成都派沃智通科技有限公司 | Student classroom behavior recognition system, method, medium and terminal device |
CN111553599A (en) * | 2020-04-29 | 2020-08-18 | 江苏加信智慧大数据研究院有限公司 | Course evaluation system and method |
CN111626252A (en) * | 2020-06-02 | 2020-09-04 | 北京中广上洋科技股份有限公司 | Teaching video analysis method and device |
CN111915148A (en) * | 2020-07-10 | 2020-11-10 | 北京科技大学 | Classroom teaching evaluation method and system based on information technology |
CN112001944A (en) * | 2020-07-09 | 2020-11-27 | 浙江大华技术股份有限公司 | Classroom teaching quality evaluation data acquisition method, computer equipment and medium |
CN112270231A (en) * | 2020-10-19 | 2021-01-26 | 北京大米科技有限公司 | Method for determining target video attribute characteristics, storage medium and electronic equipment |
CN112861730A (en) * | 2021-02-09 | 2021-05-28 | 北京文香信息技术有限公司 | Feedback method and device of classroom behavior, electronic equipment and storage medium |
CN112990105A (en) * | 2021-04-19 | 2021-06-18 | 北京优幕科技有限责任公司 | Method and device for evaluating user, electronic equipment and storage medium |
CN113239915A (en) * | 2021-07-13 | 2021-08-10 | 北京邮电大学 | Classroom behavior identification method, device, equipment and storage medium |
CN113515976A (en) * | 2020-04-10 | 2021-10-19 | 华中科技大学 | Intelligent experiment investigation system based on multi-scene video analysis |
CN113792626A (en) * | 2021-08-30 | 2021-12-14 | 华中师范大学 | Teaching process evaluation method based on teacher non-verbal behaviors |
CN115239527A (en) * | 2022-06-27 | 2022-10-25 | 重庆市科学技术研究院 | Teaching behavior analysis system for teaching characteristic fusion and modeling based on knowledge base |
CN115412679A (en) * | 2022-08-23 | 2022-11-29 | 国网浙江省电力有限公司培训中心 | Interactive teaching quality evaluation system with direct recording and broadcasting function and method thereof |
CN115619279A (en) * | 2022-11-03 | 2023-01-17 | 华中师范大学 | Classroom real-record digital course resource quality evaluation method and system |
WO2023024155A1 (en) * | 2021-08-23 | 2023-03-02 | 华中师范大学 | Method and system for measuring non-verbal behavior of teacher |
CN115829234A (en) * | 2022-11-10 | 2023-03-21 | 武汉天天互动科技有限公司 | Automatic supervision system based on classroom detection and working method thereof |
CN115907507A (en) * | 2022-10-13 | 2023-04-04 | 华中科技大学 | Classroom behavior detection and learning situation analysis method for students in combined classroom scene |
CN116029871A (en) * | 2023-01-04 | 2023-04-28 | 广州市慧诚计算机系统科技有限公司 | Visual management method and system for intelligent classroom |
CN116596719A (en) * | 2023-07-18 | 2023-08-15 | 江西科技学院 | Computer room computer teaching quality management system and method |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108648757A (en) * | 2018-06-14 | 2018-10-12 | 北京中庆现代技术股份有限公司 | A kind of analysis method based on various dimensions Classroom Information |
CN109359606A (en) * | 2018-10-24 | 2019-02-19 | 江苏君英天达人工智能研究院有限公司 | A kind of classroom real-time monitoring and assessment system and its working method, creation method |
CN109800663A (en) * | 2018-12-28 | 2019-05-24 | 华中科技大学鄂州工业技术研究院 | Teachers ' teaching appraisal procedure and equipment based on voice and video feature |
-
2019
- 2019-06-14 CN CN201910516795.4A patent/CN110334610B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108648757A (en) * | 2018-06-14 | 2018-10-12 | 北京中庆现代技术股份有限公司 | A kind of analysis method based on various dimensions Classroom Information |
CN109359606A (en) * | 2018-10-24 | 2019-02-19 | 江苏君英天达人工智能研究院有限公司 | A kind of classroom real-time monitoring and assessment system and its working method, creation method |
CN109800663A (en) * | 2018-12-28 | 2019-05-24 | 华中科技大学鄂州工业技术研究院 | Teachers ' teaching appraisal procedure and equipment based on voice and video feature |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110708392A (en) * | 2019-10-17 | 2020-01-17 | 重庆工商职业学院 | Student management system and method based on cloud platform |
CN110708392B (en) * | 2019-10-17 | 2022-05-10 | 重庆工商职业学院 | Student management system and method based on cloud platform |
CN110837795A (en) * | 2019-11-04 | 2020-02-25 | 防灾科技学院 | Teaching condition intelligent monitoring method, device and equipment based on classroom monitoring video |
CN110782185A (en) * | 2019-11-09 | 2020-02-11 | 上海光数信息科技有限公司 | Classroom behavior recognition and analysis method |
CN110853428A (en) * | 2019-12-04 | 2020-02-28 | 广州云蝶科技有限公司 | Recording and broadcasting control method and system based on Internet of things |
CN111027865B (en) * | 2019-12-12 | 2024-04-02 | 山东大学 | Teaching analysis and quality assessment system and method based on behavior and expression recognition |
CN111027865A (en) * | 2019-12-12 | 2020-04-17 | 山东大学 | Classroom teaching analysis and quality assessment system and method based on intelligent behavior and expression recognition |
CN111178273A (en) * | 2019-12-30 | 2020-05-19 | 云知声智能科技股份有限公司 | Education method and device based on emotion change |
CN111275592A (en) * | 2020-01-16 | 2020-06-12 | 浙江工业大学 | Classroom behavior analysis method based on video images |
CN111275592B (en) * | 2020-01-16 | 2023-04-18 | 浙江工业大学 | Classroom behavior analysis method based on video images |
CN113515976A (en) * | 2020-04-10 | 2021-10-19 | 华中科技大学 | Intelligent experiment investigation system based on multi-scene video analysis |
CN113515976B (en) * | 2020-04-10 | 2023-08-29 | 华中科技大学 | Intelligent experiment investigation system based on multi-scene video analysis |
CN111553599A (en) * | 2020-04-29 | 2020-08-18 | 江苏加信智慧大数据研究院有限公司 | Course evaluation system and method |
CN111291840A (en) * | 2020-05-12 | 2020-06-16 | 成都派沃智通科技有限公司 | Student classroom behavior recognition system, method, medium and terminal device |
CN111626252B (en) * | 2020-06-02 | 2023-04-07 | 北京中广上洋科技股份有限公司 | Teaching video analysis method and device |
CN111626252A (en) * | 2020-06-02 | 2020-09-04 | 北京中广上洋科技股份有限公司 | Teaching video analysis method and device |
CN112001944A (en) * | 2020-07-09 | 2020-11-27 | 浙江大华技术股份有限公司 | Classroom teaching quality evaluation data acquisition method, computer equipment and medium |
CN111915148B (en) * | 2020-07-10 | 2023-11-03 | 北京科技大学 | Classroom teaching evaluation method and system based on information technology |
CN111915148A (en) * | 2020-07-10 | 2020-11-10 | 北京科技大学 | Classroom teaching evaluation method and system based on information technology |
CN112270231A (en) * | 2020-10-19 | 2021-01-26 | 北京大米科技有限公司 | Method for determining target video attribute characteristics, storage medium and electronic equipment |
CN112861730A (en) * | 2021-02-09 | 2021-05-28 | 北京文香信息技术有限公司 | Feedback method and device of classroom behavior, electronic equipment and storage medium |
CN112990105B (en) * | 2021-04-19 | 2021-09-21 | 北京优幕科技有限责任公司 | Method and device for evaluating user, electronic equipment and storage medium |
CN112990105A (en) * | 2021-04-19 | 2021-06-18 | 北京优幕科技有限责任公司 | Method and device for evaluating user, electronic equipment and storage medium |
CN113239915B (en) * | 2021-07-13 | 2021-11-30 | 北京邮电大学 | Classroom behavior identification method, device, equipment and storage medium |
CN113239915A (en) * | 2021-07-13 | 2021-08-10 | 北京邮电大学 | Classroom behavior identification method, device, equipment and storage medium |
WO2023024155A1 (en) * | 2021-08-23 | 2023-03-02 | 华中师范大学 | Method and system for measuring non-verbal behavior of teacher |
CN113792626A (en) * | 2021-08-30 | 2021-12-14 | 华中师范大学 | Teaching process evaluation method based on teacher non-verbal behaviors |
CN115239527B (en) * | 2022-06-27 | 2024-05-07 | 重庆市科学技术研究院 | Teaching behavior analysis system based on knowledge base teaching feature fusion and modeling |
CN115239527A (en) * | 2022-06-27 | 2022-10-25 | 重庆市科学技术研究院 | Teaching behavior analysis system for teaching characteristic fusion and modeling based on knowledge base |
CN115412679A (en) * | 2022-08-23 | 2022-11-29 | 国网浙江省电力有限公司培训中心 | Interactive teaching quality evaluation system with direct recording and broadcasting function and method thereof |
CN115907507A (en) * | 2022-10-13 | 2023-04-04 | 华中科技大学 | Classroom behavior detection and learning situation analysis method for students in combined classroom scene |
CN115907507B (en) * | 2022-10-13 | 2023-11-14 | 华中科技大学 | Student class behavior detection and learning analysis method combined with class scene |
CN115619279A (en) * | 2022-11-03 | 2023-01-17 | 华中师范大学 | Classroom real-record digital course resource quality evaluation method and system |
CN115829234A (en) * | 2022-11-10 | 2023-03-21 | 武汉天天互动科技有限公司 | Automatic supervision system based on classroom detection and working method thereof |
CN116029871A (en) * | 2023-01-04 | 2023-04-28 | 广州市慧诚计算机系统科技有限公司 | Visual management method and system for intelligent classroom |
CN116596719B (en) * | 2023-07-18 | 2023-09-19 | 江西科技学院 | Computer room computer teaching quality management system and method |
CN116596719A (en) * | 2023-07-18 | 2023-08-15 | 江西科技学院 | Computer room computer teaching quality management system and method |
Also Published As
Publication number | Publication date |
---|---|
CN110334610B (en) | 2024-01-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110334610A (en) | A kind of various dimensions classroom based on computer vision quantization system and method | |
Hanushek et al. | Institutional structures of the education system and student achievement: A review of cross-country economic research | |
CN109543777B (en) | Method and system for evaluating writing quality of handwritten Chinese characters | |
CN110009210B (en) | Comprehensive assessment method for student class listening level based on attention degree and concentration degree | |
CN109359606A (en) | A kind of classroom real-time monitoring and assessment system and its working method, creation method | |
KR20220111634A (en) | Online offline combined multidimensional education AI school system | |
CN111915148A (en) | Classroom teaching evaluation method and system based on information technology | |
Hieu et al. | Identifying learners’ behavior from videos affects teaching methods of lecturers in Universities | |
CN110232343B (en) | Child personalized behavior statistical analysis system and method based on latent variable model | |
CN108009761A (en) | Teaching quality management method and system | |
CN115810163B (en) | Teaching evaluation method and system based on AI classroom behavior recognition | |
CN117058752A (en) | Student classroom behavior detection method based on improved YOLOv7 | |
CN113688789B (en) | Online learning input degree identification method and system based on deep learning | |
CN115829234A (en) | Automatic supervision system based on classroom detection and working method thereof | |
CN113469001A (en) | Student classroom behavior detection method based on deep learning | |
Liu et al. | An online classroom atmosphere assessment system for evaluating teaching quality | |
Sun et al. | Research on the Application of Students' Answered Record Analyze Model and Question Automatic Classify Based on K-Means Clustering Algorithm | |
Wang et al. | Design and simulation of computer aided chinese vocabulary evaluation system | |
Ranjan et al. | Data analysis to uncover critical parameters for performance appraisal of students in higher education | |
Li | Evaluation Technology of Students’ Learning Status in Chinese Classroom Based on Deep Learning | |
CN117235244B (en) | Online course learning emotion experience evaluation system based on barrage emotion word classification | |
Yang | English scores by distributed ID3 algorithm of computer network | |
Song et al. | Application Research of Machine Vision Platform Based on Ant Colony Algorithm and Software Engineering | |
CN116433427A (en) | Personalized learning career data image drawing method and system | |
CN115588318A (en) | Real-time teacher-student interaction system based on thought political affairs teaching |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |