CN109191341B - Classroom video frequency point arrival method based on face recognition and Bayesian learning - Google Patents

Classroom video frequency point arrival method based on face recognition and Bayesian learning Download PDF

Info

Publication number
CN109191341B
CN109191341B CN201810996596.3A CN201810996596A CN109191341B CN 109191341 B CN109191341 B CN 109191341B CN 201810996596 A CN201810996596 A CN 201810996596A CN 109191341 B CN109191341 B CN 109191341B
Authority
CN
China
Prior art keywords
face
bayesian
classroom
list
students
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.)
Active
Application number
CN201810996596.3A
Other languages
Chinese (zh)
Other versions
CN109191341A (en
Inventor
温浩
陈江豪
石君
陈兰
万珺
周曦
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.)
Guangzhou Yuncongkaifeng Technology Co Ltd
Original Assignee
Guangzhou Yuncongkaifeng 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 Guangzhou Yuncongkaifeng Technology Co Ltd filed Critical Guangzhou Yuncongkaifeng Technology Co Ltd
Priority to CN201810996596.3A priority Critical patent/CN109191341B/en
Publication of CN109191341A publication Critical patent/CN109191341A/en
Application granted granted Critical
Publication of CN109191341B publication Critical patent/CN109191341B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of 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
    • 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
    • G06V40/168—Feature extraction; Face representation
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Economics (AREA)
  • Human Resources & Organizations (AREA)
  • Marketing (AREA)
  • Primary Health Care (AREA)
  • General Business, Economics & Management (AREA)
  • Image Analysis (AREA)

Abstract

A classroom video frequency arriving method based on face recognition and Bayesian learning adopts the following steps, step 1: the processing module carries out head and shoulder detection, people counting, modeling classroom position distribution map and position coordinates of each person on a single picture at the time t in the video stream of the camera; setting the set of students in class as N, the number of people detected as N ═ N |, the set detected at head and shoulder as M (t), the number of people as m (t), and m (t) is less than or equal to N; step 2: extracting the features of the face in the picture, retrieving a lesson list n according to the face features, confirming a current set K (t), and iterating with a face confirmation set K (t-1) of the previous picture to obtain a confirmation set K (t) K (t) K (t-1) at the time t; hardware equipment and a camera do not need to be modified, most of the existing cameras can meet the requirements, and the user cost is reduced; the accuracy and speed of the original face recognition dynamic point arrival are improved. The invention can solve the problem of fast and efficient arrival of the students in the classroom at present.

Description

Classroom video frequency point arrival method based on face recognition and Bayesian learning
Technical Field
The invention relates to the field of face recognition, in particular to a classroom video frequency assignment method based on face recognition and Bayesian learning.
Background
In a traditional classroom, teachers and educational administration department want to quickly and accurately know which students are not in class, so that subsequent teaching management is implemented. If the teacher calls one student, much time is wasted, and in the case of 50 students, the time is about 3-5 minutes, which is not always accurate. If the student signs his or her own signature, the student signs his or her own signature. If the attendance machine with a card swiping function, a fingerprint function or a human face is arranged, students need to queue to check in before or after class, which is very troublesome and additionally increases the cost. A face recognition point arrival method based on video monitoring is already available in the market, and on the representative of monitoring manufacturers such as Haikangwei video and the like, the feature extraction is carried out on the face captured in real time by a monitoring picture in the background, and a face library of a student list is carried out by the steps of 1: n, searching, confirming one by one, and finally realizing no perception point. However, the method depends heavily on whether the student is looking forward, especially when the student always lowers the head or the face angle is more inclined, the situation of missed grabbing can occur, and the point-to-accuracy rate of a single picture is only about 80%. Even if the identification result is repeatedly iterated according to a long-time monitoring picture (the student heads are randomly lowered), the identification result can only reach about 95%, and the problem that the time is too long exists at the time, and the result can be obtained generally within about 15 minutes (100 iterations, which are calculated according to 10 seconds of each iteration interval).
Disclosure of Invention
The invention provides a classroom video frequency point arrival method based on face recognition and Bayesian learning aiming at the defects of the prior art, and the specific technical scheme is as follows: a classroom video frequency arriving method based on face recognition and Bayesian learning is characterized in that:
the following steps are adopted for the preparation of the anti-cancer medicine,
step 1: the processing module carries out head and shoulder detection, people counting, modeling classroom position distribution map and position coordinates of each person on a single picture at the time t in the video stream of the camera;
setting the set of students in class as N, the number of people detected as N ═ N |, the set detected at head and shoulder as M (t), the number of people as m (t), and m (t) is less than or equal to N;
step 2: extracting the features of the face in the picture, retrieving a lesson list n according to the face features, confirming a current set K (t), and iterating with a face confirmation set K (t-1) of the previous picture to obtain a confirmation set K (t) K (t) K (t-1) at the time t;
and step 3: judging whether K (t) is equal to N, if so, entering step 11, otherwise, entering step 4;
and 4, step 4: if K (t) < N, carrying out Bayesian analysis on the member objects of the M (t) — K (t) set one by one;
judging whether an island position exists in the classroom, wherein the island position is defined as that no people exist around the position, if so, entering step 5, otherwise, entering step 6;
and 5: sorting M (t) -K (t) collective persons according to their historical attendance probabilities P (j);
step 6: the front, the back, the left and the right of the position of the target member to be determined are determined members, i is the face of the confirmed person in the adjacent seat, and i is i1，i2，…，i4∈K(t)；
j is the target member to be confirmed, j ═ j1，…，jsE.m (t) -k (t), and the adjacent probability is not zero according to the bayesian probability formula
P (a | B) ═ P (B | a) × P (a)/P (B), and the estimated probability that j also appears when i appears is obtained:
Pn(j1|i1)＝Pn(i1|j1)*P(j1)/P(i1)
Pn(j1|i1i2)＝Pn(i1|j1)*P(j1)*P(i2|j1,i1)/P(i1)*P(i2|i1) To iterate the calculation of the number of times,
by analogy, Pn (j) is obtained1|i1i2i3i4) Let j besFor maximum Bayesian probability, s is equal to {1, 2, 3, 4}, jsBayesian estimation is carried out on target members to be confirmed to obtain an estimation set B (t);
and 7: setting iteration times to be at least N times, re-analyzing a new picture at the moment of t +1, and repeating the steps 1 to 6 for at least N times;
and 8: after iterating the set N times of pictures, if the termination condition is not reached, stopping iteration, and finally estimating jsInputting adjacent personnel into the Bayesian network for learning and updating, and entering the step 9, otherwise, entering the step 10;
and step 9: outputting attendance lists M (t), K (t), B (t), M (t) ═ K (t) + B (t), wherein K (t) is a confirmation list, and B (t) is an estimation list, wherein the estimation list comprises personnel and corresponding probabilities;
step 10: and (3) explaining that all students are confirmed, ending the round of point arrival, outputting a result that the attendance list of the students is N (t) ═ K (t) ═ M (t), inputting the attendance list and the front, back, left and right adjacent personnel of each student into the Bayesian network corresponding to the course for learning, updating the attendance probability P (i) of each course of each student, updating the probability Pn (i | j), i, j ∈ K of the adjacent positions of other students, and ending the round of point arrival.
Further: in the step 1, a deep learning-based CNN network is adopted to identify a single picture at the time t in a video stream of a camera.
The invention has the beneficial effects that: firstly, hardware equipment and a camera do not need to be modified, most of the existing cameras can meet the requirements, and the user cost is reduced;
secondly, the accuracy and speed of the original face recognition dynamic point arrival are improved. The invention can solve the problem of fast and efficient arrival of the students in the classroom at present.
Drawings
FIG. 1 is a flow chart of the operation of the present invention.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand by those skilled in the art, and thus will clearly and clearly define the scope of the invention.
As shown in fig. 1: a classroom video frequency arriving method based on face recognition and Bayesian learning is characterized in that:
the following steps are adopted for the preparation of the anti-cancer medicine,
step 1: the processing module carries out head and shoulder detection, people counting, modeling classroom position distribution map and position coordinates of each person on a single picture at the time t in the video stream of the camera;
setting the set of students in class as N, the number of people detected as N ═ N |, the set detected at head and shoulder as M (t), the number of people as m (t), and m (t) is less than or equal to N;
step 2: extracting the features of the face in the picture, retrieving a lesson list n according to the face features, confirming a current set K (t), and iterating with a face confirmation set K (t-1) of the previous picture to obtain a confirmation set K (t) K (t) K (t-1) at the time t;
and step 3: judging whether K (t) is equal to N, if so, entering step 11, otherwise, entering step 4;
and 4, step 4: if K (t) < N, carrying out Bayesian analysis on the member objects of the M (t) -K (t) set one by one, wherein M (t) -K (t) is a part of M (t) except K (t), or is expressed as K (t) in a complementary set CuK (t) in the full set M (t);
judging whether an island position exists in the classroom, wherein the island position is defined as that no people exist around the position, if so, entering step 5, otherwise, entering step 6;
and 5: sorting M (t) -K (t) collective persons according to their historical attendance probabilities P (j);
step 6: the front, the back, the left and the right of the position of the target member to be determined are determined members, i is the face of the confirmed person in the adjacent seat, and i is i1，i2，…，i4∈K(t)；
j is the target member to be confirmed, j ═ j1，…，jsE.m (t) -k (t), and the adjacent probability is not zero according to the bayesian probability formula
P (a | B) ═ P (B | a) × P (a)/P (B), and the estimated probability that j also appears when i appears is obtained:
Pn(j1|i1)＝Pn(i1|j1)*P(j1)/P(i1)
Pn(j1|i1i2)＝Pn(i1|j1)*P(j1)*P(i2|j1,i1)/P(i1)*P(i2|i1) To iterate the calculation of the number of times,
by analogy, Pn (j) is obtained1|i1i2i3i4) Let j besFor maximum Bayesian probability, s is equal to {1, 2, 3, 4}, jsBayesian estimation is carried out on target members to be confirmed to obtain an estimation set B (t);
and 7: setting iteration times to be at least N times, re-analyzing a new picture at the moment of t +1, and repeating the steps 1 to 6 for at least N times;
and 8: after iterating the set N times of pictures, if the termination condition is not reached, stopping iteration, and finally estimating jsInputting adjacent personnel into the Bayesian network for learning and updating, and entering the step 9, otherwise, entering the step 10;
and step 9: outputting attendance lists M (t), K (t), B (t), M (t) ═ K (t) + B (t), wherein K (t) is a confirmation list, and B (t) is an estimation list, wherein the estimation list comprises personnel and corresponding probabilities;
step 10: and (3) explaining that all students are confirmed, ending the round of point arrival, outputting a result that the attendance list of the students is N (t) ═ K (t) ═ M (t), inputting the attendance list and the front, back, left and right adjacent personnel of each student into the Bayesian network corresponding to the course for learning, updating the attendance probability P (i) of each course of each student, updating the probability Pn (i | j), i, j ∈ K of the adjacent positions of other students, and ending the round of point arrival.
In the step 1, a deep learning-based CNN network is adopted to identify a single picture at the time t in a video stream of a camera.

Claims (2)

1. A classroom video frequency arriving method based on face recognition and Bayesian learning is characterized in that:
the following steps are adopted for the preparation of the anti-cancer medicine,
step 1: the processing module carries out head and shoulder detection, people counting, modeling classroom position distribution map and position coordinates of each person on a single picture at the time t in the video stream of the camera;
setting the set of students in class as N, the number of people detected as N ═ N |, the set detected at head and shoulder as M (t), the number of people as m (t), and m (t) is less than or equal to N;
step 2: extracting the features of the face in the picture, retrieving a lesson list n according to the face features, confirming a current set K (t), and iterating with a face confirmation set K (t-1) of the previous picture to obtain a confirmation list K (t) K (t) K (t-1) at the time t;
and step 3: judging whether K (t) is equal to N, if so, entering a step 10, otherwise, entering a step 4;
and 4, step 4: if K (t) < N, carrying out Bayesian analysis on the member objects of the M (t) — K (t) set one by one;
judging whether an island position exists in the classroom, wherein the island position is defined as that no people exist around the position, if so, entering step 5, otherwise, entering step 6;
and 5: sorting M (t) -K (t) collective persons according to their historical attendance probabilities P (j);
step 6: the front, the back, the left and the right of the position of the target member to be determined are determined members, i is the face of the confirmed person in the adjacent seat, and i is i1，i2，…，i4∈K(t)；
j is the target member to be confirmed, j ═ j1，…，jSE.m (t) -k (t), and the adjacent probability is not zero according to the bayesian probability formula
P (a | B) ═ P (B | a) × P (a)/P (B), and the estimated probability that j also appears when i appears is obtained:
Pn(j1|i1)＝Pn(i1|j1)*P(j1)/P(i1)
Pn(j1|i1i2)＝Pn(i1|j1)*P(j1)*P(i2|j1,i1)/P(i1)*P(i2|i1) To iterate the calculation of the number of times,
by analogy, Pn (j) is obtained1|i1i2i3i4) Let j beSFor maximum Bayesian probability, s is equal to {1, 2, 3, 4}, jSThen the Bayesian estimation is carried out on the target member to be confirmed to obtain an estimation list B (t);
and 7: setting iteration times to be at least N times, re-analyzing a new picture at the moment of t +1, and repeating the steps 1 to 6 for at least N times;
and 8: after iterating the set N times of pictures, if a termination condition is reached, stopping iteration, and finally estimating jSInputting adjacent personnel into the Bayesian network for learning and updating, and entering the step 9, otherwise, entering the step 10;
and step 9: outputting an attendance list M (t), a confirmation list K (t), an estimation list B (t), wherein M (t) K (t) + B (t) comprises personnel and corresponding probabilities;
step 10: and (3) explaining that all students are confirmed, ending the round of point arrival, outputting a result that the attendance list of the students is N (t) ═ K (t) ═ M (t), inputting the attendance list and the front, back, left and right adjacent personnel of each student into the Bayesian network corresponding to the course for learning, updating the attendance probability P (i) of the course of each student, updating the probability Pn (i | j), i, j ∈ K of the adjacent positions of other students, and ending the round of point arrival.
2. The classroom video frequency arriving method based on face recognition and bayesian learning according to claim 1, characterized in that: in the step 1, a deep learning-based CNN network is adopted to identify a single picture at the time t in a video stream of a camera.
CN201810996596.3A 2018-08-29 2018-08-29 Classroom video frequency point arrival method based on face recognition and Bayesian learning Active CN109191341B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810996596.3A CN109191341B (en) 2018-08-29 2018-08-29 Classroom video frequency point arrival method based on face recognition and Bayesian learning

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810996596.3A CN109191341B (en) 2018-08-29 2018-08-29 Classroom video frequency point arrival method based on face recognition and Bayesian learning

Publications (2)

Publication Number Publication Date
CN109191341A CN109191341A (en) 2019-01-11
CN109191341B true CN109191341B (en) 2020-10-23

Family

ID=64916549

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810996596.3A Active CN109191341B (en) 2018-08-29 2018-08-29 Classroom video frequency point arrival method based on face recognition and Bayesian learning

Country Status (1)

Country Link
CN (1) CN109191341B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110533788B (en) * 2019-08-14 2021-12-24 合肥智圣新创信息技术有限公司 College student attendance system based on face recognition and online real-time data
CN110827432B (en) * 2019-11-11 2021-12-28 深圳算子科技有限公司 Class attendance checking method and system based on face recognition
CN110889672B (en) * 2019-11-19 2022-04-12 哈尔滨理工大学 Student card punching and class taking state detection system based on deep learning

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102831412A (en) * 2012-09-11 2012-12-19 魏骁勇 Teaching attendance checking method and device based on face recognition
CN104376611A (en) * 2014-10-20 2015-02-25 胡昔兵 Method and device for attendance of persons descending well on basis of face recognition

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9715807B2 (en) * 2010-02-26 2017-07-25 Thl Holding Company, Llc Wireless device and methods for use in determining classroom attendance

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102831412A (en) * 2012-09-11 2012-12-19 魏骁勇 Teaching attendance checking method and device based on face recognition
CN104376611A (en) * 2014-10-20 2015-02-25 胡昔兵 Method and device for attendance of persons descending well on basis of face recognition

Also Published As

Publication number Publication date
CN109191341A (en) 2019-01-11

Similar Documents

Publication Publication Date Title
CN109034036B (en) Video analysis method, teaching quality assessment method and system and computer-readable storage medium
CN109191341B (en) Classroom video frequency point arrival method based on face recognition and Bayesian learning
CN110837784B (en) Examination room peeping and cheating detection system based on human head characteristics
Ahmed et al. Vision based hand gesture recognition using dynamic time warping for Indian sign language
Pantic et al. Dynamics of facial expression: recognition of facial actions and their temporal segments from face profile image sequences
CN112184705B (en) Human body acupuncture point identification, positioning and application system based on computer vision technology
US20160078287A1 (en) Method and system of temporal segmentation for gesture analysis
US11194997B1 (en) Method and system for thermal infrared facial recognition
KR20170006355A (en) Method of motion vector and feature vector based fake face detection and apparatus for the same
CN104123543A (en) Eyeball movement identification method based on face identification
CN108229352B (en) Standing detection method based on deep learning
CN109299690B (en) Method capable of improving video real-time face recognition precision
CN105183758A (en) Content recognition method for continuously recorded video or image
CN109345427B (en) Classroom video frequency point arrival method combining face recognition technology and pedestrian recognition technology
CN110175534A (en) Teaching assisting system based on multitask concatenated convolutional neural network
CN108305187A (en) Dining room based on computer vision is had dinner guidance system
CN110163567A (en) Classroom roll calling system based on multitask concatenated convolutional neural network
CN110147736A (en) A kind of repetition anomaly detection method based on posture
CN111259844B (en) Real-time monitoring method for examinees in standardized examination room
CN111666829A (en) Multi-scene multi-subject identity behavior emotion recognition analysis method and intelligent supervision system
CN103426005B (en) Automatic database creating video sectioning method for automatic recognition of micro-expressions
Fabbri et al. Inter-homines: Distance-based risk estimation for human safety
Yang et al. Deep learning based real-time facial mask detection and crowd monitoring
CN109064578B (en) Attendance system and method based on cloud service
CN111813995A (en) Pedestrian article extraction behavior detection method and system based on space-time relationship

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
CB02 Change of applicant information

Address after: 511458 room 1009, No.26, Jinlong Road, Nansha District, Guangzhou City, Guangdong Province (only for office use)

Applicant after: Guangzhou yuncongkaifeng Technology Co., Ltd

Address before: 511457 Room 1009, No. 26 Jinlong Road, Nansha District, Guangzhou City, Guangdong Province

Applicant before: GUANGZHOU KAIFENG TECHNOLOGY Co.,Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant