CN111223147A - Intelligent scoring system and method for convex lens imaging principle experiment - Google Patents
Intelligent scoring system and method for convex lens imaging principle experiment Download PDFInfo
- Publication number
- CN111223147A CN111223147A CN202010154325.0A CN202010154325A CN111223147A CN 111223147 A CN111223147 A CN 111223147A CN 202010154325 A CN202010154325 A CN 202010154325A CN 111223147 A CN111223147 A CN 111223147A
- Authority
- CN
- China
- Prior art keywords
- convex lens
- experiment
- base
- camera
- experimental
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000002474 experimental method Methods 0.000 title claims abstract description 96
- 238000003384 imaging method Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000013135 deep learning Methods 0.000 claims abstract description 25
- 238000012360 testing method Methods 0.000 claims abstract description 19
- 238000013136 deep learning model Methods 0.000 claims abstract description 6
- 239000002184 metal Substances 0.000 claims description 20
- 239000003086 colorant Substances 0.000 claims description 7
- 238000005259 measurement Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000003062 neural network model Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 238000013077 scoring method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B23/00—Models for scientific, medical, or mathematical purposes, e.g. full-sized devices for demonstration purposes
- G09B23/24—Models for scientific, medical, or mathematical purposes, e.g. full-sized devices for demonstration purposes for chemistry
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Social Psychology (AREA)
- Computational Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Chemical & Material Sciences (AREA)
- Medicinal Chemistry (AREA)
- Algebra (AREA)
- Psychiatry (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses an intelligent scoring system and method for convex lens imaging principle experiments, which comprises a physical test table, wherein the physical test table comprises a support column, an experiment table plate and an experiment table top, the experiment table plate is arranged on the support column, the experiment table top is arranged above the rear end of the experiment table plate, a deep learning server, a physical convex lens experimental instrument and a network camera are arranged on the physical test table, the deep learning server is connected with the network camera and an operation terminal, is positioned in the same local area network, belongs to the technical field of teaching and examination of educational middle-school experiments, passes through a trained deep learning model and then passes through a camera to calibrate and restore an actual target position, and aiming at an unmanned intelligent scoring system for the physical convex lens imaging principle experiments, the deep learning neural network model and the camera calibration technology are utilized to match with an experiment algorithm formulated according to examination operation specifications specified by an education department, unmanned intelligent scoring of the physical convex lens experiment is realized.
Description
Technical Field
The invention relates to the technical field of teaching and examination of educational middle school experiments, in particular to an intelligent scoring system and method for a convex lens imaging principle experiment.
Background
In the teaching and examination process of the middle school experiment, a teacher needs to guide or judge the experiment operation of students. However, because of the large number of students, the teacher has no time to perform one-to-one teaching instruction on the students. When in examination, the teacher scores students one by one, which is time-consuming and labor-consuming. Therefore, how to reduce the teaching pressure of teachers and make the experimental operation of each student be effectively guided and accurately judged is a problem that needs to be solved by those skilled in the art.
To date, there are many deep learning frameworks that are successfully applied to the fields of computer vision, natural language processing, etc. and achieve excellent effects, but in the education industry, there are few sophisticated technologies developed to combine deep learning with traditional education equipment. Therefore, the deep learning technology is successfully applied to the middle school experiment examination system by the company, and the computer intelligent scoring of the middle school experiment examination is realized.
Disclosure of Invention
The invention aims to provide an intelligent scoring system and method for a convex lens imaging principle experiment, which are used for intelligently scoring examination operations of students, and aiming at an unmanned intelligent scoring system for a physical convex lens imaging principle experiment, the unmanned intelligent scoring system realizes unmanned intelligent scoring of the physical convex lens experiment by utilizing a deep learning neural network model and a camera calibration technology and matching with an experiment algorithm formulated according to an examination operation specification specified by an education department so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
the utility model provides an intelligence system of grading of convex lens imaging principle experiment, includes the physical test table, the physical test table includes support column, experiment table and experiment table top, and the experiment table is installed on the support column, and experiment table rear end top installation experiment table top, set up degree of deep learning server, physics convex lens laboratory glassware and network camera on the physical test table, degree of deep learning server is connected with network camera and operation terminal, is in same LAN, and network camera installs on the experiment table of physical test table.
Preferably, the physical convex lens experimental instrument comprises an experimental base, an experimental light source table, a convex lens component and a projection light screen;
the experimental base comprises two cylindrical metal strips, two metal graduated scales and two plastic bases; the two cylindrical metal strips are placed between the two metal graduated scales and are respectively fixed on the two plastic bases;
the experimental light source table comprises a circular table top and a light source table base, wherein a lifting support is arranged in the circular table top, and the circular table top is inserted into the top of the light source table base and is fixed by a bolt;
the convex lens assembly comprises a convex lens, a convex lens frame and a convex lens base, wherein the convex lens is embedded in the black convex lens frame, and the convex lens frame is arranged on the convex lens base;
the projection light screen comprises a white light screen and a projection light screen base, and the white light screen is installed on the projection light screen base.
Preferably, the area on the laboratory table is divided into: instrument placement area, experimental operation area and measurement area.
Preferably, the lens of the network camera is a fisheye lens and is divided into a top view camera, a front view camera and a side view camera;
the top-view camera is supported by the camera bracket, is arranged at the top of the experiment table and is directly opposite to the center of the experiment operation area;
the front-view camera is supported by the camera bracket, is arranged on the wider side surface of the experiment table plate and is right opposite to the center of the experiment operation area;
the side-looking camera is supported by a camera support, is arranged at the top angle of the experiment table board and is right opposite to the center of the experiment operation area.
Preferably, the convex lenses are provided with a plurality of convex lenses, each focal length is different, the top frames of the convex lenses with different focal lengths are coated with different colors, and the side surfaces of each convex lens, which are equal in height to the center of the convex lens, are coated with red strips.
Preferably, the bottom of the light source table base, the bottom of the convex lens base and the bottom of the projection light screen base are all provided with circular grooves, the side faces of the light source table base, the side faces of the convex lens base and the side faces of the projection light screen base are all provided with red conical pointers, and the red conical pointers vertically point to the metal graduated scale downwards.
Preferably, the surface of the metal graduated scale is a background color with alternate white and orange colors, and the length of each section of the background color is equal to the minimum focal length of the convex lens.
The invention provides another technical scheme: a method of an intelligent scoring system for a convex lens imaging principle experiment comprises the following steps:
the method comprises the following steps: the assembled physical convex lens experimental instrument and the network camera are installed on an experimental table board, the angle of the top-view camera, the front-view camera and the side-view camera is adjusted to be right opposite to the center of an experimental operation area, student operation videos are collected through the cameras, and the videos are transmitted into a deep learning server through a local area network.
Step two: and detecting the operation action and the instrument position of the student in the video through the trained deep learning model.
Step three: and calibrating and restoring the actual target position through a camera.
Step four: the examination operation of the student is intelligently graded according to the examination operation standard specified by the education department.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an intelligent scoring system and method for a convex lens imaging principle experiment, which are characterized in that a camera is used for collecting student operation videos, the videos are transmitted to a deep learning server through a local area network, operation actions and instrument positions of students are detected through a trained deep learning model, then an actual target position is restored through camera calibration, finally, examination operation of the students is intelligently scored according to examination operation specifications specified by an education department, and unmanned intelligent scoring system for the physical convex lens imaging principle experiment utilizes a deep learning neural network model and a camera calibration technology and is matched with an experiment algorithm formulated according to the examination operation specifications specified by the education department to realize unmanned intelligent scoring of the physical convex lens experiment.
Drawings
FIG. 1 is a schematic view of the overall structure of the present invention;
FIG. 2 is a schematic view of a webcam structure according to the present invention;
FIG. 3 is a schematic structural view of a physical test table according to the present invention;
FIG. 4 is a schematic diagram of an inverted magnified real image of a physical convex lens experimental instrument experiment of the present invention;
FIG. 5 is a schematic view of a physical convex lens experimental instrument for experimental inverted reduced real image;
FIG. 6 is a schematic diagram of the experimental base structure of the present invention;
FIG. 7 is a schematic structural diagram of an experimental light source table according to the present invention;
FIG. 8 is a schematic view of a convex lens assembly of the present invention;
fig. 9 is a schematic structural diagram of a projection screen according to the present invention.
In the figure: 1. a physical test table; 11. a support pillar; 12. a laboratory table; 121. an instrument placement area; 122. an experimental operating area; 123. a measurement zone; 13. a laboratory table top; 2. a deep learning server; 3. a physical convex lens experimental instrument; 31. an experiment base; 311. a cylindrical metal strip; 312. a metal graduated scale; 3121. base color; 313. a plastic base; 32. an experimental light source table; 321. a circular table top; 322. a light source stage base; 33. a convex lens assembly; 331. a convex lens; 3311. a red bar; 332. a convex lens frame; 333. a convex lens base; 34. a projection screen; 341. a white light screen; 342. a projection screen base; 4. a network camera; 41. a head-up view camera; 42. a forward looking camera; 43. a side-looking camera; 44. a camera head bracket; 5. a circular groove; 6. a red conical pointer; 7. and operating the terminal.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, the intelligent scoring system for the convex lens imaging principle experiment comprises a physical test table 1, wherein the physical test table 1 comprises a support column 11, an experiment table plate 12 and an experiment table top 13, the experiment table plate 12 is installed on the support column 11, the experiment table top 13 is installed above the rear end of the experiment table plate 12, and a deep learning server 2, a physical convex lens experiment instrument 3 and a network camera 4 are arranged on the physical test table 1.
Referring to fig. 2-3, the deep learning server 2 is connected to the network camera 4 and the operation terminal 7 and is in the same lan, and the network camera 4 is installed on the experiment table 12 of the physical experiment table 1, and the area on the experiment table 12 is divided into: the instrument placing area 121, the experiment operation area 122 and the measuring area 123, the lens of the network camera 4 uses a fisheye lens, and is divided into three of a top view camera 41, a front view camera 42 and a side view camera 43, the top view camera 41 is supported by a camera bracket 44, is installed at the top 13 of the experiment table and faces the center of the experiment operation area 122, the front view camera 42 is supported by the camera bracket 44, is installed at the wider side of the experiment table 12 and faces the center of the experiment operation area 122, the side view camera 43 is supported by the camera bracket 44, is installed at the top corner of the experiment table 12 and faces the center of the experiment operation area 122, and the experiment table top camera installation mode of the system is as follows: the look ahead camera 42 is installed in the below of degree of deep learning server 2, apart from 16 cm's position above the test bench desktop, the top view camera 41 is installed on the support behind degree of deep learning server 2, apart from 94 cm's position above the test bench desktop to vertical downwards, just to experiment desktop center, look sideways at camera 43 and install in the experiment table upper left corner, apart from 40 cm's position above the test bench desktop, and be 45 degrees angles with vertical direction, just to experiment desktop center.
Referring to fig. 4-5, the physical convex lens experimental apparatus 3 includes an experimental base 31, an experimental light source table 32, a convex lens assembly 33 and a projection light screen 34, the experimental base 31 includes two cylindrical metal bars 311, two metal scales 312 and two plastic bases 313, the two cylindrical metal bars 311 are placed between the two metal scales 312 and fixed on the two plastic bases 313 respectively, the experimental light source table 32 includes a circular table 321 and a light source table base 322, a liftable bracket is provided in the circular table 321, the circular table 321 is inserted into the top of the light source table base 322 and fixed by bolts, the convex lens assembly 33 includes a convex lens 331, a convex lens frame 332 and a convex lens base 333, the convex lens 331 is embedded in the black convex lens frame 332, the convex lens frame 332 is installed on the convex lens base 333, the projection light screen 34 includes a white light screen 341 and a projection light screen base 342, the white light screen 341 is installed on the projection light screen base 342, the candle is placed on the experiment light source table 32, the red conical pointer 6 is arranged on the side surface of the base, during experiment operation, the projection light screen 34, the convex lens component 33, the experiment light source table 32 and the candle are moved, so that the inverted and enlarged real image is presented on the light screen, and the projection light screen 34, the convex lens component 33, the experiment light source table 32 and the candle are moved, so that the inverted and reduced real image is presented on the light screen.
Referring to fig. 6-9, a plurality of convex lenses 331 are provided, each of which has a different focal length, and the top rims of the convex lenses 331 with different focal lengths are painted with different colors, and the side of each convex lens 331, which is equal to the center of the convex lens 331, is painted with a red strip 3311, the bottoms of the light source base 322, the convex lens base 333 and the projection screen base 342 are all provided with circular grooves 5, and the sides of the light source base 322, the convex lens base 333 and the projection screen base 342 are all provided with red cone pointers 6, and the red cone pointers 6 all point vertically downwards to the metal scale 312, the surface of the metal scale 312 is a white and orange ground color 3121, the length of each section of the ground color 3121 is equal to the minimum focal length of the convex lens 331, the side of the base of the projection screen 34 is provided with the red cone pointer 6, the top of the convex lens 331 is provided with a red strip 3311 for distinguishing the focal lengths, the convex lens 331 with different focal lengths uses different strip colors, the side surface is provided with a red strip 3311 with the same height as the center of the convex lens 331, the side surface of the base is provided with a red conical pointer 6, a candle is placed on the experiment light source table 32, and the side surface of the base is provided with the red conical pointer 6.
In order to better show the process of the intelligent scoring system for the convex lens imaging principle experiment, the embodiment provides an intelligent scoring method for the convex lens imaging principle experiment, which includes the following steps:
s1: the assembled physical convex lens experimental instrument 3 and the network camera 4 are installed on the experiment table board 12, the angles of the top view camera 41, the front view camera 42 and the side view camera 43 are adjusted to be right opposite to the center of the experiment operation area 122, the operation videos of students are collected through the cameras, and the videos are transmitted into the deep learning server 2 through the local area network.
S2: detecting the operation action and the instrument position of a student in a video through a trained deep learning model;
according to S2, the deep learning convolutional neural network framework is modified on the existing deep learning framework, and the deep learning convolutional neural network framework can be used for aiming at the experimental instrument and the operation action, under the framework, a network can learn image characteristics, each experimental instrument can be identified with high precision and high efficiency, the experimental instrument comprises an experimental base 31, an experimental light source table 32, a convex lens 331 and a projection light screen 34, and special operation actions including the actions of moving the experimental instrument by hands are identified; the network framework adopts target detection as a technical route, a specific detection flow is to use a convolutional neural network to extract features on a single-frame image, wherein each convolutional block is designed as: the convolution layer, the active layer and the connecting layer, the convolution kernel of the convolution layer is designed to be 3 x 3, and the convolution layer comprises 19 convolution layers in total; and, starting at layer 5, taking the output of each layer as an input one layer back-spaced; thus being beneficial to dealing with the network performance degradation caused by the disappearance of the gradient; using an RPNRegion Proposal Networks network to preliminarily judge the possible position of the target; wherein, the input of RPN is the output of last convolution neural network; pooling the extracted feature maps, and calculating the position and the category of the target; in the single frame image, carrying out final position adjustment on the identified target; the specific operation is realized through steps 2.1 to 2.5:
step 2.1, intercepting the student experiment video recorded in advance into 512 × 3, and storing the student experiment video in a database in a JPG format;
step 2.2, analyzing the JPG picture in the step 2.1 by using an image analysis library carried by the pytorech, wherein the analyzed picture is a gray scale map of 512 × 1;
step 2.3, randomly selecting pictures, randomly cutting, translating, turning and adjusting contrast, learning on the basis of using fast-Rcnn as a baseline, setting the learning rate to be 0.002, setting the attenuation to be 0.001, and setting the aspect ratio of the anchor to be: 1:1,1:1.5 and 1.5:1, and three groups are provided, wherein each group is provided with three widths;
step 2.4, stopping training, evaluating and screening out the best model after the learning loss is kept below 0.2 all the time;
and 2.5, inputting each frame of the video into a network, and carrying out target detection to obtain the pixel coordinates of each experimental instrument and each hand.
S3: calibrating and restoring the actual target position through a camera;
according to S3, shooting 20 chessboard calibration board photos at different positions according to the chessboard calibration principle; extracting world coordinates of an inner corner point of the calibration plate; extracting image coordinates of the angular point of the calibration plate; calibrating the corner points of the acquired world coordinates and the corresponding pixel coordinates to obtain a parameter matrix; the instrument position and the hand position detected in S2 are restored to real world coordinates.
S4: the examination operation of the students is intelligently graded according to the examination operation standard specified by the education department;
according to S4, the score points of the operation are judged according to the positions of the hands and instruments of the students and the time sequence of the appearance: whether an inverted amplified real image appears on the light screen or not; whether an inverted and reduced real image appears on the light screen or not; the specific implementation mode is realized through steps 4.1 to 4:
step 4.1, judging whether the convex lens 331, the experimental light source table 32 and the projection screen 34 are at the same horizontal height according to the real world coordinates of the instrument obtained in the step S3;
step 4.2, if the real images are at the same horizontal height, judging whether the real images with inverted amplification or inverted reduction exist on the projection, and extracting the real images by using a target detection method;
step 4.3, if the real image is detected, restoring the actual world coordinate position according to the step S3; judging whether the position of the real image is included in the actual position of the optical screen, and if the position of the real image is within the range of the optical screen, considering the video frame to be effective; wherein, the intersection of the range of the real image and the range of the light screen is larger than 90% of the range of the real image, and then whether the position of the real image is included in the actual position of the light screen is determined;
step 4.5, according to the time sequence, finding out whether the position range of the hand appearing in the front frame of the effective frame is coincident with the position of the light screen or the convex lens 331; wherein, the intersection of the position range of the hand and the range of the light screen or the convex lens 331 is larger than 80% of the intersection of the position range of the hand and the range of the light screen or the convex lens 331, and the position range of the hand is considered to be coincident with the position of the light screen or the convex lens 331;
and 4.6, if each scoring point obtains a correct result through the above 5 steps, judging that the scoring point is correct, and storing the judgment result of the system into a database to be used as the examination score of the student.
In summary, the intelligent scoring system and method for the convex lens imaging principle experiment provided by the invention collect student operation videos through the camera, the videos are transmitted to the deep learning server 2 through the local area network, the operation actions and the instrument positions of students are detected through a trained deep learning model, then the actual target positions are restored through camera calibration, and finally the examination operation of the students is intelligently scored according to the examination operation specifications specified by the education department.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be able to cover the technical solutions and the inventive concepts of the present invention within the technical scope of the present invention.
Claims (8)
1. The utility model provides an intelligence system of grading of convex lens imaging principle experiment, includes physical test table (1), its characterized in that: physical test table (1) includes support column (11), experiment table (12) and experiment table top (13), and experiment table (12) are installed on support column (11), and experiment table (12) rear end top of the installing experiment table (13), set up degree of deep learning server (2), physics convex lens laboratory glassware (3) and network camera (4) on physical test table (1), degree of deep learning server (2) are connected with network camera (4) and operation terminal (7), are in same LAN, and install on experiment table (12) of physical test table (1) network camera (4).
2. The intelligent scoring system for convex lens imaging principle experiments according to claim 1, characterized in that: the physical convex lens experimental instrument (3) comprises an experimental base (31), an experimental light source table (32), a convex lens component (33) and a projection light screen (34);
the experiment base (31) comprises two cylindrical metal strips (311), two metal graduated scales (312) and two plastic bases (313); the two cylindrical metal strips (311) are placed between the two metal graduated scales (312) and are respectively fixed on the two plastic bases (313);
the experimental light source table (32) comprises a circular table top (321) and a light source table base (322), a lifting support is arranged in the circular table top (321), and the circular table top (321) is inserted into the top of the light source table base (322) and fixed by bolts;
the convex lens assembly (33) comprises a convex lens (331), a convex lens frame (332) and a convex lens base (333), wherein the convex lens (331) is embedded in the black convex lens frame (332), and the convex lens frame (332) is arranged on the convex lens base (333);
the projection light screen (34) comprises a white light screen (341) and a projection light screen base (342), and the white light screen (341) is installed on the projection light screen base (342).
3. The intelligent scoring system for convex lens imaging principle experiments according to claim 1, characterized in that: the area on the laboratory table (12) is divided into: an instrument placement area (121), an experimental operation area (122) and a measurement area (123).
4. The intelligent scoring system for convex lens imaging principle experiments according to claim 1, characterized in that: the lens of the network camera (4) uses a fisheye lens and is divided into a top view camera (41), a front view camera (42) and a side view camera (43);
the top-view camera (41) is supported by a camera bracket (44), is arranged at the top (13) of the experiment table and is right opposite to the center of the experiment operation area (122);
the front-view camera (42) is supported by a camera bracket (44), is arranged on the wider side of the experiment table plate (12), and is right opposite to the center of the experiment operation area (122);
the side-view camera (43) is supported by a camera bracket (44), is arranged at the top corner of the experiment table board (12) and is right opposite to the center of the experiment operation area (122).
5. The intelligent scoring system for convex lens imaging principle experiments according to claim 2, characterized in that: the number of the convex lenses (331) is set to be a plurality, each focal length is different, the top frame of the convex lens (331) with different focal lengths is coated with different colors, and the side face of each convex lens (331) is coated with a red strip (3311) at the position with the same height as the center of the convex lens (331).
6. The intelligent scoring system for convex lens imaging principle experiments according to claim 2, characterized in that: the bottom of the light source table base (322), the bottom of the convex lens base (333) and the bottom of the projection light screen base (342) are provided with circular grooves (5), the side faces of the light source table base (322), the side faces of the convex lens base (333) and the side faces of the projection light screen base (342) are provided with red conical pointers (6), and the red conical pointers (6) point to the metal graduated scale (312) vertically and downwards.
7. The intelligent scoring system for convex lens imaging principle experiments according to claim 2, characterized in that: the surface of the metal graduated scale (312) is provided with alternate white and orange base colors (3121), and the length of each section of the base colors (3121) is equal to the minimum focal length of the convex lens (331).
8. A method for intelligent scoring of convex lens imaging principle experiments according to claim 1, characterized in that: the method comprises the following steps:
the method comprises the following steps: the assembled physical convex lens experimental instrument (3) and the network camera (4) are installed on an experimental table board (12), the angles of a top view camera (41), a front view camera (42) and a side view camera (43) are adjusted to be right opposite to the center of an experimental operation area (122), student operation videos are collected through the cameras, and the videos are transmitted into a deep learning server (2) through a local area network;
step two: detecting the operation action and the instrument position of a student in a video through a trained deep learning model;
step three: calibrating and restoring the actual target position through a camera;
step four: the examination operation of the student is intelligently graded according to the examination operation standard specified by the education department.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010154325.0A CN111223147A (en) | 2020-03-07 | 2020-03-07 | Intelligent scoring system and method for convex lens imaging principle experiment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010154325.0A CN111223147A (en) | 2020-03-07 | 2020-03-07 | Intelligent scoring system and method for convex lens imaging principle experiment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111223147A true CN111223147A (en) | 2020-06-02 |
Family
ID=70808124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010154325.0A Pending CN111223147A (en) | 2020-03-07 | 2020-03-07 | Intelligent scoring system and method for convex lens imaging principle experiment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111223147A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882961A (en) * | 2020-09-09 | 2020-11-03 | 河南四季竹信息科技有限公司 | Optical bench experimental instrument and optical bench experimental instrument teaching data acquisition system |
| CN112233479A (en) * | 2020-10-20 | 2021-01-15 | 上海锡鼎实业有限公司 | Automatic examination equipment of tin pot |
| CN113034989A (en) * | 2021-02-20 | 2021-06-25 | 广州颐寿科技有限公司 | Nursing training method and system and storage device |
| CN113192389A (en) * | 2021-05-06 | 2021-07-30 | 临沂市拓普网络股份有限公司 | Platform is used in teaching based on wisdom classroom |
| CN114998339A (en) * | 2022-08-03 | 2022-09-02 | 成都西交智汇大数据科技有限公司 | Plane mirror imaging scoring method, device and equipment and readable storage medium |
-
2020
- 2020-03-07 CN CN202010154325.0A patent/CN111223147A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882961A (en) * | 2020-09-09 | 2020-11-03 | 河南四季竹信息科技有限公司 | Optical bench experimental instrument and optical bench experimental instrument teaching data acquisition system |
| CN112233479A (en) * | 2020-10-20 | 2021-01-15 | 上海锡鼎实业有限公司 | Automatic examination equipment of tin pot |
| CN113034989A (en) * | 2021-02-20 | 2021-06-25 | 广州颐寿科技有限公司 | Nursing training method and system and storage device |
| CN113192389A (en) * | 2021-05-06 | 2021-07-30 | 临沂市拓普网络股份有限公司 | Platform is used in teaching based on wisdom classroom |
| CN114998339A (en) * | 2022-08-03 | 2022-09-02 | 成都西交智汇大数据科技有限公司 | Plane mirror imaging scoring method, device and equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111223147A (en) | Intelligent scoring system and method for convex lens imaging principle experiment | |
| JP6892558B2 (en) | Theological assistance method and the theological assistance system that adopts the method | |
| CN102411854B (en) | Classroom teaching mixing technology application system based on enhanced reality and method thereof | |
| CN110059611B (en) | Intelligent classroom vacant seat identification method | |
| KR20220111634A (en) | Online offline combined multidimensional education AI school system | |
| CN105709434B (en) | A kind of Educational toy external member and its mirror position detection method | |
| Andriyandi et al. | Augmented reality using features accelerated segment test for learning tajweed | |
| CN108229352B (en) | Standing detection method based on deep learning | |
| CN105809716A (en) | Superpixel and three-dimensional self-organizing background subtraction algorithm-combined foreground extraction method | |
| CN109544504A (en) | Screen picture quality evaluating method based on rarefaction representation | |
| CN111126330A (en) | Pupil membrane center positioning method and student class attendance fatigue degree detection method | |
| CN113988563A (en) | A intelligent endow branch system for level crossing imaging experiment | |
| CN114022761A (en) | Detection and positioning method and device for power transmission line tower based on satellite remote sensing image | |
| CN114998308A (en) | Defect detection method and system based on photometric stereo | |
| CN104216147A (en) | Image quality assessment based LCD (Liquid Crystal Display) display screen motion blur detection method | |
| CN107977998B (en) | Light field correction splicing device and method based on multi-view sampling | |
| CN110728178A (en) | Event camera lane line extraction method based on deep learning | |
| CN113989608A (en) | Student experiment classroom behavior identification method based on top vision | |
| CN111666882B (en) | Method for extracting answers of handwriting test questions | |
| CN110163090A (en) | It is a kind of that tracking is identified based on the pcb board of multiple features and size estimation | |
| CN115289982A (en) | Aruco code-based structural plane displacement visual monitoring method | |
| CN114783242A (en) | Drawing teaching method and device for online education | |
| RU2627019C2 (en) | Methods for determining weapon aiming point on focal point situation image in shooting simulators and device for their implementation | |
| CN108583115B (en) | Manufacturing system of mouse early embryo model | |
| CN111189826B (en) | Intelligent scoring experimental equipment and method for measuring pH value of solution to be measured by pH test paper |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200602 |
|
| WD01 | Invention patent application deemed withdrawn after publication |