CN110647842A - Double-camera classroom inspection method and system - Google Patents
Double-camera classroom inspection method and system Download PDFInfo
- Publication number
- CN110647842A CN110647842A CN201910893948.7A CN201910893948A CN110647842A CN 110647842 A CN110647842 A CN 110647842A CN 201910893948 A CN201910893948 A CN 201910893948A CN 110647842 A CN110647842 A CN 110647842A
- Authority
- CN
- China
- Prior art keywords
- camera
- classroom
- inspection
- desk
- desks
- 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
- 238000007689 inspection Methods 0.000 title claims abstract description 94
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000002159 abnormal effect Effects 0.000 claims abstract description 70
- 238000012545 processing Methods 0.000 claims abstract description 36
- 238000011156 evaluation Methods 0.000 claims abstract description 14
- 238000005295 random walk Methods 0.000 claims description 19
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 abstract description 7
- 230000009286 beneficial effect Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 10
- 238000012549 training Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 238000007637 random forest analysis Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000001154 acute effect Effects 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 210000005069 ears Anatomy 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008921 facial expression Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- 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
-
- 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
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Educational Technology (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Educational Administration (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a double-camera class inspection method and a double-camera class inspection system, wherein the method comprises the following steps: s1, establishing a three-dimensional coordinate system; acquiring three-dimensional coordinates of center points of desk tops of all desks in a classroom; s2, setting an inspection route, and acquiring a rotation angle of the second camera when the second camera inspects the desk according to the three-dimensional coordinates of the center point of the desktop of the desk on the inspection route; s3, the second camera sequentially shoots the desks on the inspection route to obtain a first local image; meanwhile, a first camera shoots a global image of a classroom, abnormal target recognition is carried out on the global image, and single personal information and a single classroom state of a student are obtained by processing a first local image; and S4, obtaining attendance information and classroom evaluation of each student. Every student is monitored through turned angle fixed point to the second camera, and first camera monitors the classroom global simultaneously, and two cameras are mutually supported, can realize accurate student's monitoring, can acquire global information again, realize that intelligence patrols and examines, improve teaching efficiency.
Description
Technical Field
The invention relates to the field of intelligent teaching, in particular to a double-camera class inspection method and a double-camera class inspection system.
Background
The video camera is used as a general electronic product, is widely used in network communication and video chat, and also plays an important role in assisting classroom teaching, and is commonly used in classrooms of colleges and universities at present, the main application scenes are video monitoring and classroom attendance checking, and particularly the combination of a face recognition technology to help teachers to perform classroom attendance checking is always a hotspot of camera application.
The camera is used for accurate discernment to the human body of the basis of classroom auxiliary teaching such as attendance, especially be to the detection and the discernment of face information, how can effectual detection and the student of discernment in the classroom be very important, under the general condition, fixed single camera function singleness, can not rotate the location at any time as required, not following the heart to accurate face identification and obtain clear facial expression and limbs power of action, the cloud platform camera can change angle control classroom, but the global information that obtains that can not be fine when rotatory to a certain angle, to listening global information change and to the fine overall planning of local monitoring can not be fine.
Disclosure of Invention
The invention aims to at least solve the technical problems in the prior art, and particularly innovatively provides a double-camera class inspection method and a double-camera class inspection system.
In order to achieve the above object, according to a first aspect of the present invention, there is provided a dual-camera class inspection method, including:
step S1, establishing a three-dimensional coordinate system by taking the position of the first camera and/or the second camera as an origin; initializing shooting parameters of a first camera, capturing a global image of a classroom through the first camera, and acquiring three-dimensional coordinates of center points of desk tops of all desks in the classroom based on the global image;
step S2, setting an inspection route for a second camera, and acquiring a rotation angle of the second camera when the second camera inspects the desk according to a three-dimensional coordinate of a desk desktop central point on the inspection route;
step S3, in the classroom, the second camera is rotated at intervals, so that the second camera can shoot the desk on the inspection route in sequence to obtain the first local image and process the local image;
synchronously, a first camera shoots a global image of a classroom in real time or at intervals, and performs abnormal target identification on the global image to obtain an abnormal target area:
if the abnormal target exists, further carrying out human body posture recognition on the abnormal target area, if the result of the human body posture recognition on the abnormal target area is that the human body stands, pausing the inspection by the second camera, rotating the second camera to shoot the abnormal target, obtaining a second local image and carrying out local image processing, and continuing the inspection by the second camera;
if the result of the human body posture recognition on the abnormal target area is that the human body does not stand or an abnormal target does not exist, the first camera continues to shoot the overall image of the classroom and carries out abnormal target recognition;
the local image processing of the first and/or second local image comprises: carrying out face recognition on the first partial image and/or the second partial image to obtain single personal information of the student, and carrying out state recognition on the first partial image and/or the second partial image to obtain a single classroom state of the student;
step S4, processing the single personal information to obtain the attendance information of each student; and processing a plurality of single classroom states of each student to obtain classroom evaluation of the student.
The beneficial effects of the above technical scheme are: by establishing a three-dimensional coordinate system of a classroom and acquiring the coordinate of the central point of the desktop of each desk, the second camera can monitor students at fixed points in front of each desk through a rotation angle, local images of most of the students can be rapidly and accurately acquired, and the states of the students can be more easily identified by using the local images; meanwhile, the classroom is monitored globally through the first camera, an abnormal target is found, and the abnormal target is detected by turning the second camera when the abnormal target stands, so that the situation that the inspection of the second camera is interrupted frequently is avoided; and in the whole monitoring process, the monitoring system does not interact with teachers, so that the teaching work of teachers is facilitated to be developed, intelligent routing inspection is realized, and the teaching efficiency is improved.
In a preferred embodiment of the present invention, in the step S2, the routing inspection route adopts a sequential walking manner, or a random walking manner, or a combination of the sequential walking manner and the random walking manner.
The beneficial effects of the above technical scheme are: the intelligent routing inspection route is formulated, and the routing inspection route does not need to be formulated manually every time.
In a preferred embodiment of the present invention, the sequential walking mode is to patrol the desks in the ascending order of the x-axis coordinate and the y-axis coordinate, starting from the desk with the smallest x-axis coordinate and the y-axis coordinate;
and/or the random walk manner comprises one or more of a complete random walk, a key-seat random walk, a key-student random walk, a BFS walk, and a DFS walk;
and/or the fully random walk is: randomly drawing K desks, rotating a second camera at intervals, and sequentially carrying out inspection shooting on the K desks to obtain a first local image and carry out local image processing;
and/or the key seat random walk is: recording the back H class desk in the classroom as class A desk, recording the rest desks as class B desk, and adopting probability PaExtracting part of class A desks from class A desks, and adopting probability PbExtracting part of class B desks from the class B desks, and sequentially carrying out inspection shooting on the part of class A desks and the part of class B desks to obtain a first local image and carrying out local image processing; pa+Pb＝1，0<Pb<Pa<1; h is a positive integer less than the total number of rows of the desk;
and/or the key students randomly walk as follows: after all desks are patrolled to obtain personal information of students on attendance, histories of the students on attendance are checkedSequencing classroom evaluation, dividing students two thirds of the first ranking into class C, dividing students one third of the second ranking into class D, and adopting probability PcExtracting part of C-class desk from C-class desk by using probability PdExtracting part of the D-class desks from the D-class desks, and sequentially performing inspection shooting on the part of the C-class desks and the part of the D-class desks to obtain a first local image and perform local image processing; pc+Pd＝1，0<Pc<Pd<1。
The beneficial effects of the above technical scheme are: various routing inspection modes of routing inspection routes are disclosed so as to be convenient for users to select, wherein the routing inspection efficiency can be improved by adopting algorithms such as BFS wandering, DFS wandering and the like.
In a preferred embodiment of the invention, the routing inspection route is multi-round inspection, the first round and the last round of inspection adopt a sequential walking mode, and the rest rounds of inspection adopt any random walking mode at random.
The beneficial effects of the above technical scheme are: the optimized routing inspection route can comprehensively detect students in front of each desk, and can perform key routing inspection on partial students and partial seats in a random walk mode.
In a preferred embodiment of the present invention, in the step S2, the rotation angle includes a horizontal rotation angle and a vertical rotation angle;
horizontal rotation angle alpha of ith desk is patrolled and examined by second cameraivpComprises the following steps:
wherein, TixIs the x-axis coordinate of the center point of the ith desk top; t isiyIs the y-axis coordinate of the center point of the desktop of the ith desk;
vertical rotation angle beta of ith desk is patrolled and examined by second cameraivpComprises the following steps:
wherein, TizIs the z-axis coordinate of the center point of the ith desk top; hsThe average value of the height of the human body higher than the desktop when sitting down.
The beneficial effects of the above technical scheme are: the calculation formula of the rotation angle is disclosed, and the average value of the height of the human body higher than the desktop when the human body sits down is introduced into the calculation formula to compensate the vertical rotation angle, so that the partial image captured by the second camera is the face of a student in front of the desk completely or partially, and the subsequent state recognition processing is facilitated.
In a preferred embodiment of the present invention, the first camera and the second camera are disposed close to each other and in parallel;
in the three-dimensional coordinate system, an x axis is transversely arranged along a classroom, and the right side of a student facing a platform is taken as the positive direction of the x axis; the y axis is arranged longitudinally along the classroom and takes the rear side of the student facing the platform as the positive direction of the y axis; the z-axis is arranged in the vertical direction.
The beneficial effects of the above technical scheme are: the positions of the first camera and the second camera are approximate to the origin of the three-dimensional coordinate system, and subsequent calculation is facilitated. The three-dimensional coordinate system conforms to the habits of people and is convenient for subsequent processing.
In a preferred embodiment of the present invention, in step S4, the method further includes the step of notifying students who are not on attendance of the attendance information of each student;
and/or in the step S4, the method further comprises the step of reminding students whose classroom state does not reach the standard in each round of inspection after each round of inspection;
and/or the step of saving attendance information and classroom evaluation of each student after the classroom is finished.
The beneficial effects of the above technical scheme are: can in time inform not student on duty, remind the not up to standard student of classroom state to shift attention, the teaching management of being convenient for improves the teaching quality, is convenient for follow-up inquiry student's information on duty and classroom evaluation.
In a preferred embodiment of the present invention, the process of performing abnormal target identification on the global image and obtaining an abnormal target region includes:
subtracting a pixel matrix of the current global image from a pixel matrix of the global image at the previous moment to obtain a difference matrix, recording areas occupied by non-zero pixel points with continuous positions in the difference matrix as abnormal target areas, judging whether the abnormal target areas are larger than a threshold area, if the abnormal target areas are larger than the threshold area, determining that abnormal targets exist, and if the abnormal target areas are not larger than the threshold area, determining that the abnormal targets do not exist.
The beneficial effects of the above technical scheme are: a method for quickly judging and accurately recognizing an abnormal target is disclosed.
In order to achieve the above object, according to a second aspect of the present invention, there is provided a dual-camera classroom inspection system including a first camera and a second camera disposed on a front wall of a classroom, and a server;
the first camera shoots a global image containing all desks; the second camera can rotate and is used for polling and shooting local images of each desk;
the server comprises an image processing module, and the image processing module is respectively connected and communicated with the first camera and the second camera;
the image processing module controls the second camera to perform polling shooting on desks in the classroom, controls the first camera to perform overall shooting on the classroom and obtains attendance information and classroom evaluation of each student in the classroom according to the double-camera classroom polling method.
The beneficial effects of the above technical scheme are: by establishing a three-dimensional coordinate system of a classroom and acquiring the coordinate of the central point of the desktop of each desk, the second camera can change the angle and monitor students in front of each desk at fixed points, so that local images containing faces can be rapidly and accurately acquired, and the states of the students can be more easily identified by the acquired local images; meanwhile, the classroom is monitored globally through the first camera, an abnormal target is found, the second camera is turned to detect the abnormal target, and the two cameras are matched with each other, so that accurate individual student monitoring can be realized, and global information can be well acquired; and in the whole monitoring process, the system does not interact with teachers, so that the teachers can conveniently develop teaching work, intelligent attendance is realized, and the teaching efficiency is improved.
In a preferred embodiment of the present invention, the system further comprises a student terminal device, and the student terminal device is in wireless connection communication with the server.
The beneficial effects of the above technical scheme are: the student can be informed and prompted in time.
Drawings
FIG. 1 is a schematic diagram of a three-dimensional coordinate system of a classroom in accordance with one embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a three-dimensional coordinate calculation principle of a center point of a desk top according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a global image obtained by a first camera according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a sequential routing inspection route in accordance with an embodiment of the present invention;
FIG. 5 is a schematic diagram of a BFS routing inspection path in accordance with an embodiment of the present invention; fig. 5(a) is a number schematic diagram of a classroom desk, and fig. 5(b) is a BFS routing inspection route simplified diagram of the classroom desk.
Reference numerals:
1 a first camera; 2 a second camera; 3, a server; 4 terminal equipment.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and limited, it is to be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection via an intermediate medium, and specific meanings of the terms may be understood by those skilled in the art according to specific situations.
The invention discloses a double-camera class inspection method, which comprises the following steps of:
step S1, establishing a three-dimensional coordinate system by taking the position of the first camera 1 and/or the second camera 2 as an origin, wherein the three-dimensional coordinate system is shown in figure 1; initializing shooting parameters of the first camera 1, wherein the shooting parameters are preferably but not limited to focal length, focusing direction and the like, capturing a global image of a classroom through the first camera 1, and acquiring three-dimensional coordinates of center points of desk tops of all desks in the classroom based on the global image;
step S2, setting a routing inspection route for the second camera 2, and acquiring a rotation angle of the second camera 2 when the second camera 2 inspects the desk according to the three-dimensional coordinates of the center point of the desktop of the desk on the routing inspection route;
step S3, in the classroom, the second camera 2 is rotated at intervals, so that the second camera 2 can shoot the desk on the routing inspection route in sequence, and a first local image is obtained and processed;
synchronously, the first camera 1 shoots a global image of a classroom in real time or at intervals, performs abnormal target recognition on the global image and obtains an abnormal target area:
if the abnormal target exists, further carrying out human body posture recognition on the abnormal target area, if the result of the human body posture recognition on the abnormal target area is that the human body stands, pausing the inspection by the second camera 2, rotating the second camera 2 to shoot the abnormal target, obtaining a second local image and carrying out local image processing, and continuing the inspection by the second camera 2;
if the result of recognizing the human body posture of the abnormal target area is that the human body does not stand or an abnormal target does not exist, the first camera 1 continuously shoots the global image of the classroom and recognizes the abnormal target;
the local image processing of the first and/or second local image comprises: carrying out face recognition on the first partial image and/or the second partial image to obtain single personal information of the student, and carrying out state recognition on the first partial image and/or the second partial image to obtain a single classroom state of the student;
step S4, processing the single personal information to obtain the attendance information of each student; and processing a plurality of single classroom states of each student to obtain classroom evaluation of the student.
In the present embodiment, as shown in fig. 2, a schematic diagram of calculating a three-dimensional coordinate of a center point of a desk top is shown, where the height of an origin of a coordinate system (where the first camera 1 and/or the second camera 2 is located) from the ground is HcThe width of the table is WtHeight of table HtFixed focal length F of the first camera 1vaThe width of a desk pixel in the picture is Pti。
From the formula Fva×Wt＝Pti×DtiThe linear distance between the first camera 1 and the center point of the desktop of the ith desk (target desk) can be calculated as
Let the coordinate of the center point of the desktop of the ith desk be Ti＝(Tix,Tiy,Tiz)。
First camera 1VaThe acquired classroom panorama schematic (i.e., global image) is shown in fig. 3. As shown in fig. 2, define αivpThe angle is horizontal rotation, namely a first camera 1 (a second camera 2) is connected with the central point of the desktop of the ith deskThe projection line of the line on the xoy horizontal plane forms an included angle (an acute angle) with the y axis; definition of betaivpThe included angle (which is an acute angle) between the connecting line of the first camera 1 (the second camera 2) and the central point of the desktop of the ith desk and the projection line of the desktop on the xoy horizontal plane is a vertical rotation angle.
Setting the pixel coordinate of the central point of the ith desk top in the obtained global image as Ti'＝(Tix',Tiy') can know the central point T of the ith desk top in the global imageiAt a distance from the x' axis in the image plane of
Center point T of ith desk topiAt a distance from the y' axis in the image plane of
Definition of
The distance between the center point of the desktop of the ith desk and the y axis in the three-dimensional coordinate system is actually,
the distance from the actual target table to the x axis in the three-dimensional coordinate system is as follows:
by the formula:
the central point T of the desktop of the ith actual desk can be obtainediDistance from y-axis in classroom three-dimensional coordinate system
Further, the method can be obtained as follows:
if Tix' > 0 or more, then Tix＝Tiy；
If Tix'<0, then
By the formula:
the central point T of the desktop of the ith actual desk can be obtainediA distance from the x-axis in the three-dimensional coordinate system of
Further obtain the
Tiz＝Hc-Ht。
In the present embodiment, the three-dimensional coordinate system uses the position of the first camera 1 as the origin, or uses the position of the second camera 2 as the origin, or the first camera 1 and the second camera 2 are closely arranged, and uses the center point of the positions of the two cameras as the origin of coordinates. When the first camera 1 and the second camera 2 are separately arranged, and the distance between the first camera 1 and the second camera 2 is set to be L, when the rotation angle of each desk is obtained by the second camera 2 through inspection, the three-dimensional coordinates of the center point of the desktop of the desk are compensated by using the components of the L on the x axis and the y axis (the compensation mode can be that the components on the x axis and the y axis are respectively added to the coordinate values of the x axis and the y axis obtained through the calculation), and the rotation angle can be obtained by using the compensated three-dimensional coordinates.
In the present embodiment, the result of the human posture recognition of the abnormal target region is not that the human body stands, that is, includes both cases of not being the human body and being the human body but not standing. Preferably, the process of recognizing the human body posture of the abnormal target region includes:
carrying out human body recognition on the abnormal target area, further carrying out human body posture recognition if the human body recognition result is a human body, continuously shooting the global image of the classroom by the first camera 1 and carrying out abnormal target recognition if the human body recognition result is not the human body, and continuously polling by the second camera 2;
if the human body posture recognition result is standing, the second camera 2 suspends the inspection, the second camera 2 is rotated to shoot an abnormal target, a second local image is obtained and is subjected to local image processing, and the second camera 2 continues the inspection;
if the human body posture recognition result is not standing, the first camera 1 continues to shoot the global image of the classroom and performs abnormal target recognition, and the second camera 2 continues to perform inspection.
The method for identifying the human body in the abnormal target area may adopt an existing human body identification method, for example, but not limited to, refer to the technical content of the patent publication with publication number CN103049747B or CN104392223B in the prior art, and is not described herein again; the method for recognizing the human body gesture can adopt a absorbed human body gesture recognition method, for example, but not limited to, refer to the technical content of the patent publication with the publication number of CN106570480B or CN101576953B in the prior art, and is not described herein again.
In this embodiment, the routing inspection route preferably includes all desks, so as to obtain attendance. The rotation angle of the second camera 2 when inspecting the desk is obtained according to the three-dimensional coordinates of the center point of the desktop of the desk on the inspection route, and the rotation angle mainly comprises a horizontal rolling angle alpha shown in figure 3ivpAnd vertical roll angle betaivpThe second camera 2 is an auto-focusing camera, and generally, the second camera 2 takes a proper focal distance when the face portion of the first partial image captured by the first camera occupies more than 80% of the total image.
In the present embodiment, after the end of the class, different pieces of personal information are counted from the individual pieces of personal information to form a first personal information set, and the number of samples in the first personal information set is taken as the number of attendance in the class, and it is considered that the pre-stored samples in the first personal information set, which are not included in the personal information sets corresponding to the students in the class, are recorded as the personal information of the absent staff.
In this embodiment, the method for performing face recognition on the first partial image and/or the second partial image may refer to a face recognition algorithm in the prior art, preferably, all photos of all students in a classroom and personal information associated with the photos are stored in advance, the face images in the single video clip are compared with the pre-stored photos one by one, and if the similarity degree of the two photos is greater than or equal to Q%, and the value range of Q may be 80-95, a student in the single video clip may be considered as a student associated with the photo. The personal information preferably includes, but is not limited to, student names and/or school numbers, etc.
In this embodiment, the method for obtaining the single classroom state of the student by performing state recognition on the first partial image and/or the second partial image (i.e. only the first partial image, only the second partial image, or both the first partial image and the second partial image) is as follows:
establishing a state recognition model, inputting the first partial image and/or the second partial image into the state recognition model, and outputting the state of the student in the first partial image and/or the second partial image by the state recognition model;
the process of establishing the state recognition model comprises the following steps:
step S31, constructing a training data set marked as Vlabled(ii) a Training data set VlabledThe system comprises a plurality of single-person video clips provided with status labels;
and step S32, training and verifying the random forest classifier by taking the single video segment in the training data set as input and the state label of the single video segment as a classification result to obtain a state recognition model.
In the embodiment, the state recognition model is trained by adopting a random forest classification method based on deep learning, the intelligent degree is high, and manual participation is not needed.
In this embodiment, a random forest classifier is used, the number of base decision trees is 10, the upper limit of the length of all predicted paths per tree is 5, and this trained classifier is used to classify the state of the video.
In step S31, the specific process of constructing the training data set includes:
step S311, a plurality of video clips are cut from the existing student classroom video, single video clips of all students in each video clip are cut, all the single video clips are constructed into a single video clip set and recorded as Vunlabled；
Step S312, presetting a plurality of states, the states
s belongs to { listen and talk over head, read and write with head down, sleep on table, answer questions when standing up, meet ears when crossing left and right, play mobile phone };
sending each single video clip in the single video clip set to a plurality of visitors respectively, scoring the coincidence degree of the single video clip and each state by the visitors, and calculating the average value of the coincidence degree score of each single video clip and each state:
wherein the content of the first and second substances,
an average value representing the score of the degree of coincidence of the ith' single-person video clip in the single-person video clip set with the mth state s (m); n ispRepresenting the number of visitors scored for the i' th single-person video clip; i ', m and j ' are positive integers, m is more than or equal to 1 and less than or equal to 6, j ' is more than or equal to 1 and less than or equal to np；
Step S313, setting a status tag for the single video clip:
if the average of the score for the degree of coincidence of the ith' single person video clip with the mth state s (m) satisfies:
then a status tag s is set for the ith' single person video clipi'And adding the ith' single person video clip into the training data set VlabledStatus label si'Comprises the following steps:
wherein the content of the first and second substances,
is a preset score threshold;
if the average of the score of the matching degree of the ith' single-person video clip and the mth state s (m) is not satisfied
Or the average of the scores of the coincidence degree of the ith' single-person video clip with more than one state satisfiesNot adding the ith' single person video clip to the training data set Vlabled。
In this embodiment, the multiple visitors score the 6 states of the single video clip respectively corresponding to head-up listening and speaking, head-down reading and writing, table-lying sleeping, question answering, left-right head-crossing and ear-catching and mobile phone playing by 5-point or 10-point full scale, wherein full scale indicates that the visitors consider the complete correspondence, and 0 point indicates that the visitors consider the complete non-correspondence.
The preset score threshold may be 70% of full score, such as when a 5-point full score system is used,
the score threshold for the preset may be 3.5.
In the embodiment, the label classification is carried out on the existing data set by utilizing the scoring system of the interviewee, so that the method is more humanized and accurate.
In the present embodiment, in step S4, the procedure of processing a plurality of single classroom states for each student is:
set for different values for different classroom states, set for classroom state including the new head is listened to and is spoken, the lower head is read and is write, the table of lying prone sleep, answer the question immediately, control the crossover ear and play the cell-phone, classroom state score s is:
therefore, the classroom evaluation of each student is obtained by performing averaging processing or weighted averaging processing for a plurality of single classroom states of the student in the whole classroom.
In the present embodiment, it is preferable that the above-described state recognition method be employed to determine whether the abnormal object is a student standing answer question.
In the present embodiment, it is preferable to establish a student set S { (S)1a',S1b'),...,(Sja',Sjb'),...,(Sma',Smb') }; wherein m is the total number of people that the curriculum should attend, j and m are positive integers, and j is more than or equal to 1 and less than or equal to m; sja' personal information of jth student, Sjb' denotes the classroom performance of the jth student, which includes attendance information and classroom assessments. And storing the historical classroom performance of the students through the student set.
In a preferred embodiment, in step S2, the routing inspection route adopts a sequential walking manner, or a random walking manner, or a combination of the sequential walking manner and the random walking manner.
In a preferred embodiment, the sequential walking mode is to patrol the desks in the ascending order of the x axis and the y axis from the desk with the smallest coordinate of the x axis and the y axis, as shown in fig. 4;
and/or the random walk manner comprises one or more of a complete random walk, a key-seat random walk, a key-student random walk, a BFS walk, and a DFS walk; the form of DFS migration is shown in fig. 5, where fig. 5(a) is a number diagram of a classroom desk, and fig. 5(b) is a simplified BFS routing inspection route diagram of the classroom desk.
And/or a completely random walk: randomly drawing K desks, rotating the second cameras 2 at intervals, and sequentially performing inspection shooting on the K desks to obtain a first local image and perform local image processing;
and/or the key seat random walk is: recording the back H class desk in the classroom as class A desk, recording the rest desks as class B desk, and adopting probability PaExtracting part of class A desks from class A desks, and adopting probability PbExtracting part of class B desks from the class B desks, and sequentially carrying out inspection shooting on the part of class A desks and the part of class B desks to obtain a first local image and carrying out local image processing; pa+Pb＝1，0<Pb<Pa<1; h is a positive integer less than the total number of rows of the desk;
and/or the key students randomly walk as: after polling all desks to obtain personal information of students on attendance, sequencing historical classroom evaluation of the students on attendance, dividing the students two thirds of the first ranking into class C, dividing the students one third of the second ranking into class D, and adopting probability PcExtracting part of C-class desk from C-class desk by using probability PdExtracting part of the D-class desks from the D-class desks, and sequentially performing inspection shooting on the part of the C-class desks and the part of the D-class desks to obtain a first local image and perform local image processing; pc+Pd＝1，0<Pc<Pd<1。
In a preferred embodiment, the routing inspection route is multi-round routing inspection, the first round routing inspection and the last round routing inspection adopt a sequential walking mode, and the other round routing inspection randomly adopts any random walking mode.
In a preferred embodiment, in step S2, as shown in fig. 3, the rotation angle includes a horizontal rotation angle and a vertical rotation angle;
horizontal rotation angle alpha of ith desk is patrolled and examined by second camera 2ivpComprises the following steps:
wherein, TixIs the x-axis coordinate of the center point of the ith desk top; t isiyIs the y-axis coordinate of the center point of the desktop of the ith desk;
vertical rotation angle beta of the ith desk is patrolled and examined by the second camera 2ivpComprises the following steps:
wherein, TizIs the z-axis coordinate of the center point of the ith desk top; hsThe average value of the height of the human body higher than the desktop when sitting down.
In the present embodiment, preferably, in the process of polling the second camera 2, the rotation angle is accumulated, and after obtaining the next rotation angle according to the three-dimensional coordinate of the center point of the desktop of the next polling desk, the accumulated rotation angle is subtracted from the next rotation angle to obtain the required rotation angle.
In a preferred embodiment, as shown in fig. 1, 3 and 4, the first camera 1 and the second camera 2 are arranged close to each other and side by side;
in a three-dimensional coordinate system, an x axis is transversely arranged along a classroom, the right side of a student facing a platform is taken as the positive direction of the x axis, and the left side of the student facing the platform is correspondingly taken as the negative direction of the x axis; the y axis is arranged longitudinally along the classroom, the rear side of the student facing the platform is taken as the positive y axis direction, and the front side of the student facing the platform is taken as the negative y axis direction correspondingly; the z-axis is arranged in the vertical direction.
In a preferred embodiment, in step S4, the method further comprises the step of notifying the students who are not on attendance of the students after obtaining the attendance information of each student;
and/or after each round of inspection, reminding students whose classroom state does not reach the standard in the round of inspection in step S4;
and/or the step of saving attendance information and classroom assessment of each student after the classroom is finished can be saved in the student set S'.
In a preferred embodiment, the process of performing abnormal target identification on the global image and obtaining an abnormal target area includes:
subtracting the pixel matrix of the current global image from the pixel matrix of the global image at the previous moment to obtain a difference matrix, recording the area occupied by non-zero pixels with continuous positions in the difference matrix as an abnormal target area, judging whether the abnormal target area is larger than a threshold area, if the abnormal target area is larger than the threshold area, considering that an abnormal target exists, and if the abnormal target area is not larger than the threshold area, considering that no abnormal target exists.
In this embodiment, the continuous positions refer to continuous vertical coordinates and/or continuous horizontal coordinates of the pixels in the image plane, such as increasing or decreasing sequentially. The threshold value area can be preset, for example, M × N matrix pixel points are provided, and M and N are positive integers; certainly, to simplify the calculation, the threshold region may also be characterized by the number of pixel points, for example, P, where P is a positive integer, after the abnormal target region is found, the number of pixel points in the abnormal target region is counted, if the number is less than or equal to P, it is determined that an abnormal target does not exist, and if the number is greater than P, it is determined that an abnormal target exists.
The invention also discloses a double-camera classroom inspection system, which comprises a first camera 1 and a second camera 2 which are arranged on the front wall of a classroom and a server 3 in a preferred embodiment as shown in figure 1;
the first camera 1 shoots a global image containing all desks; the second camera 2 can rotate, can be a tripod head camera and is used for polling and shooting local images of each desk;
the server 3 comprises an image processing module which is respectively connected and communicated with the first camera 1 and the second camera 2;
according to the double-camera class inspection method, the image processing module controls the second camera 2 to perform inspection shooting on desks in a classroom, controls the first camera 1 to perform overall shooting on the classroom, and obtains attendance information and classroom evaluation of each student in the classroom.
In a preferred embodiment, the student terminal device 4 is further included, and the student terminal device 4 is in wireless connection communication with the server 3.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. The double-camera class inspection method is characterized by comprising the following steps:
step S1, establishing a three-dimensional coordinate system by taking the position of the first camera and/or the second camera as an origin; initializing shooting parameters of a first camera, capturing a global image of a classroom through the first camera, and acquiring three-dimensional coordinates of center points of desk tops of all desks in the classroom based on the global image;
step S2, setting an inspection route for a second camera, and acquiring a rotation angle of the second camera when the second camera inspects the desk according to a three-dimensional coordinate of a desk desktop central point on the inspection route;
step S3, in the classroom, the second camera is rotated at intervals, so that the second camera can shoot the desk on the inspection route in sequence to obtain the first local image and process the local image;
synchronously, a first camera shoots a global image of a classroom in real time or at intervals, and performs abnormal target identification on the global image to obtain an abnormal target area:
if the abnormal target exists, further carrying out human body posture recognition on the abnormal target area, if the result of the human body posture recognition on the abnormal target area is that the human body stands, pausing the inspection by the second camera, rotating the second camera to shoot the abnormal target, obtaining a second local image and carrying out local image processing, and continuing the inspection by the second camera;
if the result of the human body posture recognition on the abnormal target area is that the human body does not stand or an abnormal target does not exist, the first camera continues to shoot the overall image of the classroom and carries out abnormal target recognition;
the local image processing of the first and/or second local image comprises: carrying out face recognition on the first partial image and/or the second partial image to obtain single personal information of the student, and carrying out state recognition on the first partial image and/or the second partial image to obtain a single classroom state of the student;
step S4, processing the single personal information to obtain the attendance information of each student; and processing a plurality of single classroom states of each student to obtain classroom evaluation of the student.
2. The dual-camera classroom inspection method according to claim 1, wherein in the step S2, the inspection route is sequentially walked, or randomly walked, or a combination of sequentially walked and randomly walked.
3. The dual-camera classroom inspection method according to claim 2, wherein the sequential walking manner is to inspect the desks in an increasing order of x-axis and y-axis coordinates, starting from the desk with the smallest x-axis and y-axis coordinates;
and/or the random walk manner comprises one or more of a complete random walk, a key-seat random walk, a key-student random walk, a BFS walk, and a DFS walk;
and/or the fully random walk is: randomly drawing K desks, rotating a second camera at intervals, and sequentially carrying out inspection shooting on the K desks to obtain a first local image and carry out local image processing;
and/or the key seat random walk is: recording the back H class desk in the classroom as class A desk, recording the rest desks as class B desk, and adopting probability PaExtracting part of class A desks from class A desks, and adopting probability PbExtracting part of class B desks from the class B desks, and sequentially carrying out inspection shooting on the part of class A desks and the part of class B desks to obtain a first local image and carrying out local image processing; pa+Pb＝1，0<Pb<Pa<1; h is a positive integer less than the total number of rows of the desk;
and/or the key students randomly walk as follows: after all desks are patrolled to obtain personal information of students on attendance, historical classroom evaluation of the students on attendance is rankedThe first two thirds of the students are classified into class C, the last one third of the students are classified into class D, and the probability P is adoptedcExtracting part of C-class desk from C-class desk by using probability PdExtracting part of the D-class desks from the D-class desks, and sequentially performing inspection shooting on the part of the C-class desks and the part of the D-class desks to obtain a first local image and perform local image processing; pc+Pd＝1，0<Pc<Pd<1。
4. The dual-camera classroom inspection method according to claim 3, wherein the inspection route is a multi-round inspection, the first round and the last round of inspection adopt a sequential walking mode, and the remaining rounds of inspection adopt any random walking mode at random.
5. The dual-camera classroom inspection method according to claim 1, wherein in the step S2, the rotation angles include a horizontal rotation angle and a vertical rotation angle;
horizontal rotation angle alpha of ith desk is patrolled and examined by second cameraivpComprises the following steps:
wherein, TixIs the x-axis coordinate of the center point of the ith desk top; t isiyIs the y-axis coordinate of the center point of the desktop of the ith desk;
vertical rotation angle beta of ith desk is patrolled and examined by second cameraivpComprises the following steps:
wherein, TizIs the z-axis coordinate of the center point of the ith desk top; hsThe average value of the height of the human body higher than the desktop when sitting down.
6. The double-camera classroom inspection method according to claim 1, wherein the first camera and the second camera are disposed adjacent to each other and in parallel;
in the three-dimensional coordinate system, an x axis is transversely arranged along a classroom, and the right side of a student facing a platform is taken as the positive direction of the x axis; the y axis is arranged longitudinally along the classroom and takes the rear side of the student facing the platform as the positive direction of the y axis; the z-axis is arranged in the vertical direction.
7. The dual-camera classroom inspection method according to claim 1, wherein in the step S4, the method further includes a step of notifying students not on attendance of additional labels after obtaining attendance information of each student;
and/or after each round of inspection, reminding students whose classroom state does not reach the standard in the round of inspection in the step S4;
and/or the step of saving attendance information and classroom evaluation of each student after the classroom is finished.
8. The dual-camera classroom inspection method according to claim 1, wherein the process of performing abnormal target recognition on the global image and obtaining abnormal target areas includes:
subtracting a pixel matrix of the current global image from a pixel matrix of the global image at the previous moment to obtain a difference matrix, recording areas occupied by non-zero pixel points with continuous positions in the difference matrix as abnormal target areas, judging whether the abnormal target areas are larger than a threshold area, if the abnormal target areas are larger than the threshold area, considering that abnormal targets exist, and if the abnormal target areas are not larger than the threshold area, considering that the abnormal targets do not exist.
9. A double-camera classroom inspection system is characterized by comprising a first camera, a second camera and a server, wherein the first camera and the second camera are arranged on the front wall of a classroom;
the first camera shoots a global image containing all desks; the second camera can rotate and is used for polling and shooting local images of each desk;
the server comprises an image processing module, and the image processing module is respectively connected and communicated with the first camera and the second camera;
the image processing module controls the second camera to perform inspection shooting on desks in a classroom, controls the first camera to perform overall shooting on the classroom, and obtains attendance information and classroom evaluation of each student in the classroom according to the double-camera classroom inspection method as claimed in any one of claims 1-8.
10. The dual-camera classroom inspection system according to claim 9, further comprising student terminal devices in wireless connection communication with the server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910893948.7A CN110647842B (en) | 2019-09-20 | 2019-09-20 | Double-camera classroom inspection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910893948.7A CN110647842B (en) | 2019-09-20 | 2019-09-20 | Double-camera classroom inspection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110647842A true CN110647842A (en) | 2020-01-03 |
| CN110647842B CN110647842B (en) | 2022-02-15 |
Family
ID=69010912
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910893948.7A Active CN110647842B (en) | 2019-09-20 | 2019-09-20 | Double-camera classroom inspection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110647842B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111259824A (en) * | 2020-01-19 | 2020-06-09 | 成都依能科技股份有限公司 | Method for automatically generating scanning path based on classroom size |
| CN111985817A (en) * | 2020-08-21 | 2020-11-24 | 扬州大学 | Monitoring method for monitoring students in online live broadcast teaching |
| CN112036257A (en) * | 2020-08-07 | 2020-12-04 | 华中师范大学 | Non-perception face image acquisition method and system |
| CN112911150A (en) * | 2021-01-29 | 2021-06-04 | 广州合易威视信息科技有限公司 | Automatic snapshot method for high-definition human face in target area |
| CN113542672A (en) * | 2021-05-25 | 2021-10-22 | 浙江大华技术股份有限公司 | Camera cruising method, electronic device and storage medium |
| CN113963453A (en) * | 2021-09-03 | 2022-01-21 | 福建星网物联信息***有限公司 | Classroom attendance checking method and system based on double-camera face recognition technology |
| CN114040115A (en) * | 2021-11-29 | 2022-02-11 | 海南哦课教育科技有限公司 | Method, device, medium and electronic equipment for capturing abnormal action of target object |
| CN114998844A (en) * | 2022-08-08 | 2022-09-02 | 北京师范大学 | Online class patrol and supervision system and method based on AI classroom |
| CN115035587A (en) * | 2022-08-09 | 2022-09-09 | 深圳天海宸光科技有限公司 | System and method for generating efficient automatic cruise roll-call track |
| CN117201742A (en) * | 2023-09-11 | 2023-12-08 | 江苏财经职业技术学院 | Video monitoring system for intelligent classroom |
| CN117475466A (en) * | 2023-05-05 | 2024-01-30 | 广州乐庚信息科技有限公司 | Real-time monitoring method and system for learning state of classroom students |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102148965A (en) * | 2011-05-09 | 2011-08-10 | 上海芯启电子科技有限公司 | Video monitoring system for multi-target tracking close-up shooting |
| CN202159375U (en) * | 2011-03-14 | 2012-03-07 | 惠州学院 | Classroom roll-call system |
| CN104517102A (en) * | 2014-12-26 | 2015-04-15 | 华中师范大学 | Method and system for detecting classroom attention of student |
| CN106713772A (en) * | 2017-03-31 | 2017-05-24 | 维沃移动通信有限公司 | Photographing method and mobile terminal |
| CN107133611A (en) * | 2017-06-06 | 2017-09-05 | 南京信息工程大学 | A kind of classroom student nod rate identification with statistical method and device |
| CN107230187A (en) * | 2016-03-25 | 2017-10-03 | 北京三星通信技术研究有限公司 | The method and apparatus of multimedia signal processing |
| CN207946952U (en) * | 2016-07-31 | 2018-10-09 | 北京华文众合科技有限公司 | A kind of tutoring system and painting and calligraphy tutoring system |
| 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 |
| CN109118512A (en) * | 2018-08-13 | 2019-01-01 | 中国矿业大学 | A kind of classroom based on machine vision is come to work late and leave early detection method |
| CN109410098A (en) * | 2018-09-04 | 2019-03-01 | 四川文轩教育科技有限公司 | A kind of student classroom behavioural analysis and monitoring method |
| CN109461104A (en) * | 2018-10-22 | 2019-03-12 | 杭州闪宝科技有限公司 | Classroom monitoring method, device and electronic equipment |
-
2019
- 2019-09-20 CN CN201910893948.7A patent/CN110647842B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202159375U (en) * | 2011-03-14 | 2012-03-07 | 惠州学院 | Classroom roll-call system |
| CN102148965A (en) * | 2011-05-09 | 2011-08-10 | 上海芯启电子科技有限公司 | Video monitoring system for multi-target tracking close-up shooting |
| CN104517102A (en) * | 2014-12-26 | 2015-04-15 | 华中师范大学 | Method and system for detecting classroom attention of student |
| CN107230187A (en) * | 2016-03-25 | 2017-10-03 | 北京三星通信技术研究有限公司 | The method and apparatus of multimedia signal processing |
| CN207946952U (en) * | 2016-07-31 | 2018-10-09 | 北京华文众合科技有限公司 | A kind of tutoring system and painting and calligraphy tutoring system |
| CN106713772A (en) * | 2017-03-31 | 2017-05-24 | 维沃移动通信有限公司 | Photographing method and mobile terminal |
| CN107133611A (en) * | 2017-06-06 | 2017-09-05 | 南京信息工程大学 | A kind of classroom student nod rate identification with statistical method and device |
| 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 |
| CN109118512A (en) * | 2018-08-13 | 2019-01-01 | 中国矿业大学 | A kind of classroom based on machine vision is come to work late and leave early detection method |
| CN109410098A (en) * | 2018-09-04 | 2019-03-01 | 四川文轩教育科技有限公司 | A kind of student classroom behavioural analysis and monitoring method |
| CN109461104A (en) * | 2018-10-22 | 2019-03-12 | 杭州闪宝科技有限公司 | Classroom monitoring method, device and electronic equipment |
Non-Patent Citations (2)
| Title |
|---|
| 李从利等: "《《数据结构》学习参考》", 30 June 2003, 南京大学出版社 * |
| 欧温暖等: ""基于教室监控视频的课堂行为计数分析"", 《图学学报》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111259824A (en) * | 2020-01-19 | 2020-06-09 | 成都依能科技股份有限公司 | Method for automatically generating scanning path based on classroom size |
| CN111259824B (en) * | 2020-01-19 | 2023-04-14 | 成都依能科技股份有限公司 | Method for automatically generating scanning path based on classroom size |
| CN112036257A (en) * | 2020-08-07 | 2020-12-04 | 华中师范大学 | Non-perception face image acquisition method and system |
| CN111985817A (en) * | 2020-08-21 | 2020-11-24 | 扬州大学 | Monitoring method for monitoring students in online live broadcast teaching |
| CN112911150A (en) * | 2021-01-29 | 2021-06-04 | 广州合易威视信息科技有限公司 | Automatic snapshot method for high-definition human face in target area |
| CN113542672B (en) * | 2021-05-25 | 2023-08-18 | 浙江大华技术股份有限公司 | Camera cruising method, electronic device and storage medium |
| CN113542672A (en) * | 2021-05-25 | 2021-10-22 | 浙江大华技术股份有限公司 | Camera cruising method, electronic device and storage medium |
| CN113963453A (en) * | 2021-09-03 | 2022-01-21 | 福建星网物联信息***有限公司 | Classroom attendance checking method and system based on double-camera face recognition technology |
| CN113963453B (en) * | 2021-09-03 | 2024-04-05 | 福建星网物联信息***有限公司 | Classroom attendance checking method and system based on double-camera face recognition technology |
| CN114040115A (en) * | 2021-11-29 | 2022-02-11 | 海南哦课教育科技有限公司 | Method, device, medium and electronic equipment for capturing abnormal action of target object |
| CN114998844A (en) * | 2022-08-08 | 2022-09-02 | 北京师范大学 | Online class patrol and supervision system and method based on AI classroom |
| CN115035587A (en) * | 2022-08-09 | 2022-09-09 | 深圳天海宸光科技有限公司 | System and method for generating efficient automatic cruise roll-call track |
| CN115035587B (en) * | 2022-08-09 | 2022-11-15 | 深圳天海宸光科技有限公司 | System and method for generating efficient automatic cruise roll-call track |
| CN117475466A (en) * | 2023-05-05 | 2024-01-30 | 广州乐庚信息科技有限公司 | Real-time monitoring method and system for learning state of classroom students |
| CN117201742A (en) * | 2023-09-11 | 2023-12-08 | 江苏财经职业技术学院 | Video monitoring system for intelligent classroom |
| CN117201742B (en) * | 2023-09-11 | 2024-06-25 | 江苏财经职业技术学院 | Video monitoring system for intelligent classroom |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110647842B (en) | 2022-02-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110647842B (en) | Double-camera classroom inspection method and system | |
| CN108399376B (en) | Intelligent analysis method and system for classroom learning interest of students | |
| CN110443226B (en) | Student state evaluation method and system based on posture recognition | |
| CN109359521A (en) | The two-way assessment system of Classroom instruction quality based on deep learning | |
| US20210233262A1 (en) | Multi-camera kiosk | |
| CN205334563U (en) | Student classroom participation detecting system | |
| CN111046823A (en) | Student classroom participation degree analysis system based on classroom video | |
| CN111275345B (en) | Classroom informatization evaluation and management system and method based on deep learning | |
| CN111291613B (en) | Classroom performance evaluation method and system | |
| CN111507592B (en) | Evaluation method for active modification behaviors of prisoners | |
| CN111339801B (en) | Personnel attention detection method, device, equipment and system | |
| CN110349667A (en) | The autism assessment system analyzed in conjunction with questionnaire and multi-modal normal form behavioral data | |
| CN108259752A (en) | A kind of image pickup method and system | |
| CN108229352B (en) | Standing detection method based on deep learning | |
| CN112257591A (en) | Remote video teaching quality evaluation method and system based on machine vision | |
| CN112036257A (en) | Non-perception face image acquisition method and system | |
| JP6859640B2 (en) | Information processing equipment, evaluation systems and programs | |
| CN110619460A (en) | Classroom quality assessment system and method based on deep learning target detection | |
| CN108735020A (en) | A kind of on-line teaching system with prompting function | |
| CN111160277A (en) | Behavior recognition analysis method and system, and computer-readable storage medium | |
| CN113705510A (en) | Target identification tracking method, device, equipment and storage medium | |
| CN109934097A (en) | A kind of expression and mental health management system based on artificial intelligence | |
| CN113963453B (en) | Classroom attendance checking method and system based on double-camera face recognition technology | |
| US20220327732A1 (en) | Information processing apparatus, information processing method, and program | |
| JP6819194B2 (en) | Information processing systems, information processing equipment and programs |
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 |