CN111243410A - Chemical funnel device construction experiment operation device and intelligent scoring method - Google Patents
Chemical funnel device construction experiment operation device and intelligent scoring method Download PDFInfo
- Publication number
- CN111243410A CN111243410A CN202010203774.XA CN202010203774A CN111243410A CN 111243410 A CN111243410 A CN 111243410A CN 202010203774 A CN202010203774 A CN 202010203774A CN 111243410 A CN111243410 A CN 111243410A
- Authority
- CN
- China
- Prior art keywords
- funnel
- long
- beaker
- experiment
- neck
- 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
- 238000002474 experimental method Methods 0.000 title claims abstract description 64
- 239000000126 substance Substances 0.000 title claims abstract description 31
- 238000010276 construction Methods 0.000 title claims abstract description 7
- 238000013077 scoring method Methods 0.000 title claims description 8
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 claims abstract description 82
- 229910052742 iron Inorganic materials 0.000 claims abstract description 41
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000001514 detection method Methods 0.000 claims abstract description 16
- 230000000007 visual effect Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 4
- 239000000706 filtrate Substances 0.000 claims description 2
- 230000001629 suppression Effects 0.000 claims description 2
- 239000007788 liquid Substances 0.000 claims 1
- 238000013135 deep learning Methods 0.000 abstract description 8
- 239000011159 matrix material Substances 0.000 description 6
- 238000012937 correction Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000012153 distilled water Substances 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000007514 turning Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Educational Technology (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Multimedia (AREA)
- Primary Health Care (AREA)
- Chemical & Material Sciences (AREA)
- Medicinal Chemistry (AREA)
- Algebra (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an experimental operation device built by a chemical funnel device and an intelligent grading method, wherein the experimental operation device comprises an experimental table, an operation component, a student cloud terminal display screen and a network camera, wherein the operation component is placed on the experimental table, the student cloud terminal display screen is installed right above the experimental table, and the network camera is also installed on the experimental table; the operation assembly comprises an iron support, a long-neck funnel, a beaker and filter paper, wherein the long-neck funnel is placed on the iron support. The invention adopts the foresight camera and the overlook camera to collect the video of the experiment operation process of the student, utilizes the deep learning target detection algorithm to identify the target object in the collected video, scores the funnel device building experiment of the student according to the current scoring rule of the funnel building experiment, and obtains the final operation score, thereby solving the problems of high quality requirement of scoring personnel, large scoring workload and difficult unification of scoring standards in the current construction operation experiment process of the chemical funnel device.
Description
Technical Field
The invention relates to the technical field of student experiment equipment, in particular to an experiment operation device for building a chemical funnel device and an intelligent scoring method.
Background
The experiment is an important teaching means for testing the mastery level of students on theoretical knowledge. The existing chemical experiment skill scoring method is that a scoring teacher carries out subjective scoring according to scoring key points required by certain experiment operation, the experiment operation in the scoring process relates to judgment of fine operation, operation sequence and experiment conclusion, and the professional chemical experiment subject teacher with rich experience of chemical experiment operation can finish evaluation on the operation.
For example, in the experimental process of building the operation of the filtering device in the chemical experiment, when the grading key points of the operation are reached, field grading teachers need to confirm one by one, so that the field manual grading workload is huge, and the grading scales of different grading teachers in the same operation are different, and the obtained grading result cannot achieve certain objectivity.
Meanwhile, in recent years, with the rapid application of big data and an artificial intelligence technology on machine vision and image processing technologies, based on a large amount of data collected in the experimental process of students, a latest artificial intelligence algorithm and a latest deep learning algorithm are combined, and according to a scoring rule of construction operation of a chemical funnel device, a series of problems that the quality requirement of scoring personnel is high, the scoring workload is extremely large, the scoring standard is difficult to unify, and the like in the experimental process of construction operation of the chemical funnel device at present are to be improved.
Disclosure of Invention
The invention aims to provide an experimental operation device for building a chemical funnel device and an intelligent scoring method, wherein the chemical filter device is built by utilizing instruments such as an iron support, a long-neck funnel, a beaker, filter paper and the like, a video of an experimental operation process of a student is collected by adopting a front-view camera and a overlook camera, a target object in the collected video is identified by utilizing a deep learning target detection algorithm, the experimental building of the funnel device of the student is scored according to the current scoring rule of the experimental building of the funnel, and a final operation score is obtained.
In order to achieve the purpose, the invention provides the following technical scheme:
an experimental operation device for building a chemical funnel device comprises an experimental table, an operation component, a student cloud terminal display screen and a network camera, wherein the operation component is placed on the experimental table, the student cloud terminal display screen is installed right above the experimental table, and the network camera is also installed on the experimental table;
the operating assembly comprises an iron stand, a long-neck funnel, a beaker and filter paper, the long-neck funnel is placed on the iron stand, an outlet at the bottom of the long-neck funnel extends into the beaker right below the long-neck funnel, and the filter paper which is rolled up to be conical is attached to the inner wall of the long-neck funnel.
Further, the experiment table is divided into an experiment operation area and an article placing area, a beaker is placed on the experiment operation area, and an iron support is placed on the article placing area.
Further, the iron support comprises base, balanced landing leg, locking bolt A, iron stand montant, latch segment, locking bolt B and long neck funnel bracket, the balanced landing leg of four turnings of base equal fixedly connected with, vertically insert the iron stand montant and lock through locking bolt A in the slotted hole of base, through the fixed latch segment of locking bolt B on the iron stand montant, fixed mounting long neck funnel bracket on the latch segment.
Further, the locking block is of an arc-shaped structure and surrounds the iron frame vertical rod, and a V-shaped groove is formed in the locking block.
Furthermore, the inner wall of the V-shaped groove is provided with anti-skidding teeth.
Further, the student cloud terminal display screen is electrically connected with a host computer located inside the experiment table.
Furthermore, the network camera comprises a front-view camera and an overlook camera, the front-view camera is arranged on the lower portion of the center of the student cloud terminal display screen, the overlook camera is arranged behind the student cloud terminal display screen and is connected with the experiment table, the front-view camera adopts a fisheye camera with 180 degrees, and the visual field range comprises the whole table top.
The other technical scheme to be solved by the invention is as follows: the intelligent scoring method for the construction experiment operation of the chemical funnel device comprises the following steps:
s1: extracting bounding boxes of the long-neck funnel, the iron stand and the beaker from video images recorded by the forward-looking camera and the downward-looking camera by using a target detection algorithm;
s2: for the forward-looking video image and the detected bounding box information of the target object, judging the position relationship between the iron stand platform and the bounding boxes of the long-neck funnel and the beaker, and judging that the long-neck funnel and the beaker are in proper height when the bounding boxes of the long-neck funnel and the beaker are in the interior of the bounding box of the iron stand platform and the upper part of the beaker frame is strictly higher than the lower edge of the long-neck funnel frame by a certain distance;
s3: when the requirement of S2 is met, according to the overlooking video image and the detected bounding box information of each object, extracting image blocks of the area where the bounding boxes of the long-neck funnel and the beaker are located, extracting a mark made in the long-neck funnel by using an image processing algorithm, firstly judging whether the inside of the long-neck funnel contains filter paper or not, then judging whether the filter paper in the long-neck funnel is higher than the upper edge of the mouth of the long-neck funnel or not, and when the long-neck funnel contains the filter paper and the green mark of the upper edge is not covered by the filter paper, considering that the filter paper placing operation is correct;
s4: extracting approximate circles of a funnel mouth and a beaker mouth in image blocks of a long-neck funnel and a beaker in an overlook image by utilizing a Hough circle detection and non-maximum suppression algorithm, obtaining the accurate distance between the centers of the two circles according to the distance between the centers of the two circles in the image, the height difference information of the planes of the round mouths of the two objects and the internal parameters of an overlook camera, and judging whether the lower end of the funnel is tightly attached to the inner wall of the beaker at the moment according to the distance and the radius of the beaker mouth;
s5: and obtaining coordinates of the mass center at the green color code point of the funnel opening by utilizing an image processing technology, and considering the coordinates, coordinates of the circle center of the funnel opening and the angle of three points of the circle center coordinates of the beaker opening, wherein when the angle is more than 120 degrees, the tip mouth at the lower end of the funnel is tightly attached to the inner wall of the beaker.
Further, the following two evaluation points are required to be evaluated, firstly, the filter paper is folded and inserted into the long-neck funnel, and if the upper edge of the filter paper is higher than the mouth of the long-neck funnel, no evaluation is carried out; adjusting the long-neck funnel to a proper height, wherein a leakage opening at the lower end of the long-neck funnel is lower than a beaker opening for collecting filtrate, a tip at the lower end of the long-neck funnel is abutted against the inner wall of the beaker, the operation of the scoring point is considered to be wrong if the requirement is not met, when S3 is correct, the scoring point is considered to be correct, otherwise, the scoring point is incorrect; if and only if steps S1, S2, S4, S5 are all correct, then the score two may be considered correct.
Compared with the prior art, the invention has the beneficial effects that:
the chemical filtering device is built by utilizing instruments such as an iron support, a long-neck funnel, a beaker, filter paper and the like, a front-view camera and a top-view camera are adopted to collect videos of an experimental operation process of students, a target object in the collected videos is identified by utilizing a deep learning target detection algorithm, the experimental building of the funnel device of the student is graded according to the current grading rule of the experimental building of the funnel, and a final operation score is obtained, so that the problems that grading personnel have high quality requirements, the grading workload is large and the grading standard is difficult to unify in the experimental building operation process of the current chemical funnel device are solved.
Drawings
FIG. 1 is an overall structure diagram of a chemical funnel device for constructing an experimental operation device;
FIG. 2 is a schematic structural diagram of an operating assembly of the present invention:
FIG. 3 is a top view of the operating assembly of the present invention;
FIG. 4 is a side view of the operating assembly of the present invention;
FIG. 5 is a schematic top view of a modified funnel of the present invention without filter paper;
FIG. 6 is a schematic top view of a modified funnel of the present invention with filter paper;
FIG. 7 is a schematic front view of a modified funnel of the present invention without filter paper;
figure 8 is a front view of a modified funnel of the present invention with filter paper.
In the figure: 1. an experiment table; 2. an operating component; 21. an iron stand; 211. a base; 212. a balance leg; 213. locking the bolt A; 214. erecting a steel frame; 215. a locking block; 2151. a V-shaped groove; 216. locking the bolt B; 217. a long-neck funnel bracket; 22. a long-neck funnel; 23. a beaker; 24. filtering paper; 3. a student cloud terminal display screen; 4. a network camera; 41. a forward looking camera; 42. looking down the camera.
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, a chemistry funnel device builds experiment operating means, including experiment table 1, operating means 2, student's cloud terminal display screen 3 and network camera 4, operating means 2 is placed on experiment table 1, experiment table 1 is the standard 1.2m 0.8 m's experiment table, experiment table 1 divide into experiment operation area and article and places the district, experiment operation area is used for the student to carry out the experiment operation, install student's cloud terminal display screen 3 directly over experiment table 1, student's cloud terminal display screen 3 is connected with the host computer electricity that is located experiment table 1 inside, still install network camera 4 on the experiment table 1, gather student's experiment operation video through network camera 4, be used for the experiment to grade.
Referring to fig. 2-8, the operating assembly 2 includes an iron stand 21, a long-neck funnel 22, a beaker 23 and a filter paper 24, the long-neck funnel 22 is placed on the iron stand 21, a bottom outlet of the long-neck funnel 22 extends into the beaker 23 right below, the volume of the beaker 23 is 500ml, and the filter paper 24 which is rolled up to be conical is attached to the inner wall of the long-neck funnel 22.
A beaker 23 is placed on the experiment operation area, and an iron support 21 is placed on the article placing area.
The iron stand platform 21 comprises base 211, balanced landing leg 212, locking bolt A213, iron stand montant 214, latch segment 215, locking bolt B216 and long-neck funnel bracket 217, the balanced landing leg 212 of the equal fixedly connected with in four corners of base 211, the steadiness of base 211 can be guaranteed to balanced landing leg 212, vertically insert iron stand montant 214 in the slotted hole of base 211 and lock through locking bolt A213, can reciprocate iron stand montant 214 after locking bolt A213 unscrews, fix latch segment 215 through locking bolt B216 on the iron stand montant 214, locking bolt B216 pushes up on iron stand montant 214, iron stand montant 214 supports tightly each other with latch segment 215, prevent latch segment 215 from sliding on iron stand montant 214, the long-neck funnel bracket 217 of fixed mounting on latch segment 215.
The locking block 215 is an arc-shaped structure and surrounds the iron stand vertical rod 214, and a V-shaped groove 2151 is formed in the locking block 215. The inner wall of the V-shaped groove 2151 is provided with anti-skidding teeth, so that when the locking bolt B216 abuts against the iron stand vertical rod 214, friction force can be increased through the anti-skidding teeth on the inner wall of the V-shaped groove 2151 to prevent the locking block 215 from sliding.
The network camera 4 includes a foresight camera 41 and a overlook camera 42, the foresight camera 41 is arranged at the lower part of the center of the student cloud terminal display screen 3, the height of the foresight camera 41 from the desktop is 15cm, the overlook camera 42 is arranged at the rear of the student cloud terminal display screen 3 and is connected with the experiment table 1, the overlook camera 42 adopts a 180-degree fisheye camera, the whole experiment table desktop is shot from top to bottom, the height of the overlook camera 42 from the desktop of the experiment table 1 is 78cm, and the visual field range comprises the whole desktop. The examinee fills in examinee information and click start and end information through a computer and an experimental examination system, and obtains operation videos recorded by the two cameras according to the start and end marks.
In order to better show the intelligent scoring process of the experiment operation for building the chemical funnel device, the embodiment provides an intelligent scoring method of the experiment operation for building the chemical funnel device, which includes the following steps:
step 1: the hardware environment for acquiring the video data in the experimental process is built, the video data of the experiment built by the filtering device by students is acquired, and a front-view camera 41 and a top-view camera 42 are adopted according to the requirement of the visual field range. The overlooking camera 42 is a plane camera, the shooting visual angle is from top to bottom, the front-looking camera 41 is a fisheye camera, and the shooting visual angle is used for shooting the front of a student;
step 2: identifying a target object in the acquired video by using a deep learning target detection algorithm according to the acquired video of the student experiment operation process obtained in the step 1, and obtaining target frames of all targets in each frame of image in the acquired video;
and step 3: detecting the approximate circle positions of the funnel object target frame and the funnel conical outer edge and the beaker upper edge in the funnel object target frame and the beaker object target frame by utilizing a Hough circle detection algorithm according to the target frame information of each frame of the top view video and all targets obtained in the step 2, and obtaining the circle center coordinates of the funnel conical opening and the beaker opening in the image;
and 4, step 4: the funnel object is instrumented with corresponding markings, such as a green dot, at the tip of the handle of the long-neck funnel 22, relative to the conical surface of the long-neck funnel 22. Intercepting image blocks of corresponding target frames from the image frames by using each frame image and funnel target frame information of the top view video obtained in the step 2, extracting green dot mark areas on the funnel from the intercepted image blocks by using a threshold segmentation algorithm, calculating the mass center coordinates of the areas, and finally taking the mass center of the areas as the approximate position of the tip mouth of the funnel on the image;
and 5: marking the positions of the mass centers of the funnel opening approximate circle, the beaker opening approximate circle and the green dot in the top view video obtained in the steps 3 and 4 to obtain the pixel distance of the centers of the two circles at the visual angle and the angles of the three points of the funnel approximate circle center, the beaker approximate circle center and the mass center of the green dot;
step 6: converting the pixel distance between the two circle centers into an actual distance according to the internal reference, the external reference and the correction coefficient of the top-view camera and the depth of the two objects relative to the top-view camera by using the pixel distance between the circle centers of the approximate funnel opening circle and the approximate beaker opening circle obtained in the step 5;
and 7: and (4) scoring the funnel device building experiment of the student according to the angle and the actual distance obtained in the steps 5 and 6 and the current scoring rule of the funnel building experiment, and obtaining the final operation score.
The step 2 specifically comprises the following steps:
step 2-1: correcting the forward-looking fisheye video by a fisheye correction algorithm to obtain front _ video _fromthe top-looking viewing angle video top _ video and the forward-looking fisheye video front _ video obtained in the step 1;
step 2-2: inputting each frame of the two obtained videos into a deep learning target detection frame by the corrected front-looking video front _ video _ obtained in the step 2-1 and the top-looking visual angle video top _ video obtained in the step 1, performing target detection on experimental related objects in the two videos by a deep learning target detection algorithm, and obtaining circumscribed rectangular frames of all target objects on each frame of image in the front-looking video and the top-looking video;
the step 3 specifically comprises the following steps:
step 3-1: calculating depth information of a plane where a funnel opening and a beaker opening are located according to the forward-looking visual angle correction image obtained in the step 2-2 and corresponding target detection frame information through a pixel ratio of a target frame and actual length information from the beaker, the funnel and the top-looking camera to a desktop;
step 3-2: intercepting image blocks corresponding to the funnel target frame and the beaker target frame at the positions according to the positions of the video and the target frame of the corresponding target object under the top view angle obtained in the step 2-2, and detecting the intercepted image blocks by utilizing a Hough circle detection algorithm to obtain a possible approximate circle set of all funnel openings and beaker openings in the image; setting a reasonable threshold value in the approximate circle detection result set, and screening out an approximate circle result which accords with the characteristics of shape and area as the final approximate positions of the conical surface edge of the funnel and the upper edge of the beaker;
the step 5 specifically comprises the following steps:
step 5-1: according to a Zhang mark method, collecting top view camera images of a batch of calibration images at different angles, and calculating an internal reference matrix, an external reference matrix and a correction coefficient of the top view camera at the current position according to the collected images;
step 5-2: calculating the distance between the two circle center coordinates in the image according to the circle center coordinates of the funnel conical surface obtained in the step 3-2 and the approximate circle of the upper edge of the beaker in the image;
step 5-3: obtaining corresponding angles according to coordinates of three points by using the coordinates of the centroid of the green dot mark area obtained in the step 3-2 and the coordinates of the circle centers of the approximate circles of the funnel opening and the beaker opening;
the step 6 specifically comprises the following steps:
step 6-1: obtaining an internal reference matrix, an external reference matrix and a correction coefficient of the top-view camera from the step 5-1, obtaining depth information of the top-view camera from the plane where the funnel mouth and the beaker mouth are located from the step 3-1, calculating the actual distance between the centers of the two approximate circles according to the distance between the funnel mouth and the beaker mouth, which is obtained from the step 5-2, and the pixel coordinates of the approximate circle centers of the two approximate circles, wherein the specific calculation formula is as follows:
in the formula, u and v are pixel coordinates of a certain point in an image, f is the focal length of the top-view camera, R is a rotation matrix, t is a translation matrix, and X, Y and Z are coordinates of the pixel point in a world coordinate system;
the step 7 can be specifically divided into the following steps:
step 7-1: obtaining actual distance information of the angle and the circle center from the step 5-3 and the step 6-1, and when a student operates water pouring in the experimental operation process, using the actual distance information as a scoring point starting time set up by the device, wherein the water pouring action can be determined as the finishing moment of the action when a dropping bottle target frame filled with distilled water is detected to be separated from a desktop and overlapped with a small beaker target frame;
step 7-2: and (3) extracting top-view video data 5 seconds before the moment from the grading starting moment obtained in the step 7-1, and performing the operations of the steps 2-6 on each frame image within 5 seconds, wherein when the angles and distances in 80% of the image frames in the obtained video meet the set error threshold, the funnel device building operation of the student can be evaluated as correct operation, and otherwise, the experimental operation of the student can be evaluated as wrong operation.
In summary, the following steps: the invention utilizes instruments such as an iron stand 21, a long-neck funnel 22, a beaker 23, filter paper 24 and the like to build a chemical filtering device, adopts a front view camera 41 and a overlook camera 42 to collect videos of an experimental operation process of students, utilizes a deep learning target detection algorithm to identify target objects in the collected videos, scores the experimental building of the funnel device of the students according to the current scoring rules of the experimental building of the funnel, and obtains final operation scores, thereby solving the problems of high quality requirements of scoring personnel, great scoring workload and difficult unification of scoring standards in the experimental building operation process of the current chemical funnel device.
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 (9)
1. An experiment operating device for building a chemical funnel device is characterized by comprising an experiment table (1), an operating assembly (2), a student cloud terminal display screen (3) and a network camera (4), wherein the operating assembly (2) is placed on the experiment table (1), the student cloud terminal display screen (3) is installed right above the experiment table (1), and the network camera (4) is also installed on the experiment table (1);
the operation assembly (2) comprises an iron stand (21), a long-neck funnel (22), a beaker (23) and filter paper (24), the long-neck funnel (22) is placed on the iron stand (21), the bottom outlet of the long-neck funnel (22) extends into the beaker (23) right below, and the filter paper (24) which is rolled to be conical is attached to the inner wall of the long-neck funnel (22).
2. The chemical funnel device building experiment operation device according to claim 1, wherein the experiment table (1) is divided into an experiment operation area and an article placing area, a beaker (23) is placed on the experiment operation area, and an iron stand (21) is placed on the article placing area.
3. The chemical funnel device building experiment operating device according to claim 2, wherein the iron stand (21) is composed of a base (211), balance legs (212), locking bolts A (213), iron stand vertical rods (214), locking blocks (215), locking bolts B (216) and long-neck funnel brackets (217), the balance legs (212) are fixedly connected to four corners of the base (211), the iron stand vertical rods (214) are vertically inserted into slotted holes of the base (211) and locked through the locking bolts A (213), the locking blocks (215) are fixed on the iron stand vertical rods (214) through the locking bolts B (216), and the long-neck funnel brackets (217) are fixedly mounted on the locking blocks (215).
4. The chemical funnel device building experiment operating device according to claim 3, wherein the locking block (215) is in an arc structure and surrounds the iron stand vertical rod (214), and a V-shaped groove (2151) is formed in the locking block (215).
5. The chemical funnel device building experiment operating device according to claim 4, wherein the inner wall of the V-shaped groove (2151) is provided with anti-slip teeth.
6. The chemical funnel device building experiment operating device according to claim 1, wherein the student cloud terminal display screen (3) is electrically connected with a host machine located inside the experiment table (1).
7. The chemical funnel device building experiment operating device according to claim 1, wherein the network camera (4) comprises a front-view camera (41) and a overlook camera (42), the front-view camera (41) is arranged on a lower portion of the center of the student cloud terminal display screen (3), the overlook camera (42) is arranged behind the student cloud terminal display screen (3) and connected with the experiment table (1), the front-view camera (41) adopts a 180-degree fisheye camera, and the visual field range comprises the whole table top.
8. A method for intelligently scoring experimental set-up runs of a chemical hopper apparatus as claimed in any one of claims 1 to 7, comprising the steps of:
s1: extracting bounding boxes of the long-neck funnel (22), the iron stand (21) and the beaker (23) from video images recorded by the front-looking camera (41) and the top-looking camera (42) by using a target detection algorithm;
s2: for the forward-looking video image and the detected bounding box information of the target object, by judging the position relationship between the iron stand platform (21) and the bounding boxes of the long-neck funnel (22) and the beaker (23), when the bounding boxes of the long-neck funnel (22) and the beaker (23) are positioned inside the bounding box of the iron stand platform (21) and the upper edge of the frame of the beaker (23) is higher than the lower edge of the frame of the long-neck funnel (22) by a certain distance, the forward-looking video image and the detected bounding box information of the target object can be judged to be at proper heights;
s3: when the condition of S2 is met, extracting image blocks of areas where the bounding boxes of the long-neck funnel (22) and the beaker (23) are located according to the overlooking video image and the detected bounding box information of each object, extracting the marks made in the long-neck funnel (22) by using an image processing algorithm, firstly judging whether the inside of the long-neck funnel (22) contains the filter paper (24), then judging whether the filter paper (24) in the long-neck funnel (22) is higher than the upper edge of the opening of the long-neck funnel (22), and considering that the placing operation of the filter paper (24) is correct when the long-neck funnel (22) contains the filter paper (24) and the green mark of the upper edge is not covered by the filter paper (24);
s4: extracting approximate circles of a funnel mouth and a beaker mouth in image blocks of a long-neck funnel (22) and a beaker (23) in an overlook image by utilizing a Hough circle detection and non-maximum suppression algorithm, obtaining the accurate distance between the centers of two circles according to the distance between the centers of the two circles in the image, the height difference information of the planes of the round mouths of the two objects and the internal parameters of an overlook camera, and judging whether the lower end of the funnel is tightly attached to the inner wall of the beaker at the moment according to the distance and the radius of the beaker mouth;
s5: and obtaining coordinates of the mass center at the green color code point of the funnel opening by utilizing an image processing technology, and considering the coordinates, coordinates of the circle center of the funnel opening and the angle of three points of the circle center coordinates of the beaker opening, wherein when the angle is more than 120 degrees, the tip mouth at the lower end of the funnel is tightly attached to the inner wall of the beaker.
9. The intelligent scoring method for the construction experiment operation of the chemical hopper device as claimed in claim 8, wherein the two scoring points are judged, i.e. folding the filter paper (24) and inserting the filter paper (24) into the long-neck hopper (22), and if the upper edge of the filter paper (24) is higher than the mouth of the long-neck hopper (22), not scoring; adjusting the long-neck funnel (22) to a proper height, wherein a liquid leakage opening at the lower end of the long-neck funnel (22) is lower than a beaker opening for collecting filtrate, a tip at the lower end of the long-neck funnel (22) is close to the inner wall of the beaker, and if the tip does not meet the requirement, the scoring point is considered to be operated wrongly, if S3 is correct, the scoring point is considered to be correct, otherwise, the scoring point is incorrect; if and only if steps S1, S2, S4, S5 are all correct, then the score two may be considered correct.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010203774.XA CN111243410B (en) | 2020-03-20 | 2020-03-20 | Chemical funnel device construction experiment operation device and intelligent scoring method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010203774.XA CN111243410B (en) | 2020-03-20 | 2020-03-20 | Chemical funnel device construction experiment operation device and intelligent scoring method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111243410A true CN111243410A (en) | 2020-06-05 |
| CN111243410B CN111243410B (en) | 2022-01-28 |
Family
ID=70864620
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010203774.XA Active CN111243410B (en) | 2020-03-20 | 2020-03-20 | Chemical funnel device construction experiment operation device and intelligent scoring method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111243410B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114822160A (en) * | 2022-04-25 | 2022-07-29 | 上海瑞玛教育信息咨询有限公司 | Operation evaluation method of intelligent measuring cylinder for teaching |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160131592A1 (en) * | 2014-11-10 | 2016-05-12 | Donald Channing Cooper | Modular illumination and sensor chamber |
| CN107146237A (en) * | 2017-04-24 | 2017-09-08 | 西南交通大学 | A kind of method for tracking target learnt based on presence with estimating |
| CN207576460U (en) * | 2017-10-26 | 2018-07-06 | 广东中智源实验室装备制造有限公司 | A kind of chemical laboratory table |
| CN207708616U (en) * | 2017-10-25 | 2018-08-10 | 周蒙 | A kind of stent-type chemical filter unit |
| CN208432598U (en) * | 2018-08-03 | 2019-01-25 | 漳州龙文琪睿生物科技有限公司 | A kind of beaker heating frame for the detection of food reagent |
| WO2019031083A1 (en) * | 2017-08-07 | 2019-02-14 | Mitsubishi Electric Corporation | Method and system for detecting action |
| CN208770939U (en) * | 2018-06-29 | 2019-04-23 | 青岛纯晶稀有元素有限公司 | A kind of chemical experiment filtering experimental provision |
| CN109727172A (en) * | 2019-03-18 | 2019-05-07 | 上海中科教育装备集团有限公司 | A kind of artificial intelligence machine study experimental skill points-scoring system |
| CN209810224U (en) * | 2019-01-30 | 2019-12-20 | 刘宇昕 | Novel iron stand platform based on chemistry experiments are used |
| US20200026987A1 (en) * | 2018-03-05 | 2020-01-23 | Tata Consultancy Services Limited | Neural network based position estimation of target object of interest in video frames |
| CN110852204A (en) * | 2019-10-28 | 2020-02-28 | 乐山师范学院 | Intelligent remote calligraphy digital learning evaluation information processing system and method |
-
2020
- 2020-03-20 CN CN202010203774.XA patent/CN111243410B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160131592A1 (en) * | 2014-11-10 | 2016-05-12 | Donald Channing Cooper | Modular illumination and sensor chamber |
| CN107146237A (en) * | 2017-04-24 | 2017-09-08 | 西南交通大学 | A kind of method for tracking target learnt based on presence with estimating |
| WO2019031083A1 (en) * | 2017-08-07 | 2019-02-14 | Mitsubishi Electric Corporation | Method and system for detecting action |
| CN207708616U (en) * | 2017-10-25 | 2018-08-10 | 周蒙 | A kind of stent-type chemical filter unit |
| CN207576460U (en) * | 2017-10-26 | 2018-07-06 | 广东中智源实验室装备制造有限公司 | A kind of chemical laboratory table |
| US20200026987A1 (en) * | 2018-03-05 | 2020-01-23 | Tata Consultancy Services Limited | Neural network based position estimation of target object of interest in video frames |
| CN208770939U (en) * | 2018-06-29 | 2019-04-23 | 青岛纯晶稀有元素有限公司 | A kind of chemical experiment filtering experimental provision |
| CN208432598U (en) * | 2018-08-03 | 2019-01-25 | 漳州龙文琪睿生物科技有限公司 | A kind of beaker heating frame for the detection of food reagent |
| CN209810224U (en) * | 2019-01-30 | 2019-12-20 | 刘宇昕 | Novel iron stand platform based on chemistry experiments are used |
| CN109727172A (en) * | 2019-03-18 | 2019-05-07 | 上海中科教育装备集团有限公司 | A kind of artificial intelligence machine study experimental skill points-scoring system |
| CN110852204A (en) * | 2019-10-28 | 2020-02-28 | 乐山师范学院 | Intelligent remote calligraphy digital learning evaluation information processing system and method |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114822160A (en) * | 2022-04-25 | 2022-07-29 | 上海瑞玛教育信息咨询有限公司 | Operation evaluation method of intelligent measuring cylinder for teaching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111243410B (en) | 2022-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105279372B (en) | A kind of method and apparatus of determining depth of building | |
| CN111753635B (en) | Intelligent scoring method and device for chemical experiment operation and storage medium | |
| CN106485699B (en) | One kind is based on the matched reference mark localization method of point | |
| CN105498253B (en) | A kind of Educational toy external member and its positioning hole detection localization method | |
| CN108648169A (en) | The method and device of high voltage power transmission tower defects of insulator automatic identification | |
| CN105869085A (en) | Transcript inputting system and method for processing images | |
| CN110570422B (en) | Capsule defect visual detection method based on matrix analysis | |
| CN108665468B (en) | Device and method for extracting tangent tower insulator string | |
| CN109544504A (en) | Screen picture quality evaluating method based on rarefaction representation | |
| CN117152648B (en) | Auxiliary teaching picture recognition device based on augmented reality | |
| CN111312023B (en) | Device and method for automatically drawing middle school physics circuit experiment circuit diagram | |
| CN110119742B (en) | Container number identification method and device and mobile terminal | |
| CN111243410B (en) | Chemical funnel device construction experiment operation device and intelligent scoring method | |
| CN110689000A (en) | Vehicle license plate identification method based on vehicle license plate sample in complex environment | |
| CN106790898B (en) | A kind of mobile phone screen bad point automatic testing method and system based on significance analysis | |
| CN111340749A (en) | Image quality detection method, device, equipment and storage medium | |
| CN112308828A (en) | Artificial intelligence detection method and detection system for air tightness of sealing equipment | |
| CN115272474A (en) | Three-dimensional calibration plate for combined calibration of laser radar and camera and calibration method | |
| CN113378754A (en) | Construction site bare soil monitoring method | |
| CN106254850A (en) | The image matching method of double vision point three-dimensional video-frequency and device | |
| CN111811482B (en) | Unmanned aerial vehicle image-based overhead transmission line span and corner measuring method | |
| KR20200012373A (en) | Apparatus and method for calculating water lever based on image processing | |
| CN112634179A (en) | Transformer equipment image change detection method and system for preventing camera shake | |
| CN109035306A (en) | Moving-target automatic testing method and device | |
| CN114820492A (en) | Method for detecting excess on circuit board |
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 |