CN111223343B - Artificial intelligence scoring experimental equipment and scoring method for lever balance experiment - Google Patents
Artificial intelligence scoring experimental equipment and scoring method for lever balance experiment Download PDFInfo
- Publication number
- CN111223343B CN111223343B CN202010154326.5A CN202010154326A CN111223343B CN 111223343 B CN111223343 B CN 111223343B CN 202010154326 A CN202010154326 A CN 202010154326A CN 111223343 B CN111223343 B CN 111223343B
- Authority
- CN
- China
- Prior art keywords
- lever
- hook
- scoring
- balance
- bounding box
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention discloses an artificial intelligence scoring experimental device for a lever balance experiment and a scoring method, belonging to the technical field of experimental teaching equipment. According to the artificial intelligence scoring experimental equipment and the scoring method for the lever balance experiment, the scoring method uses an image processing and deep learning method to adjust the lever, so that the initial position is balanced, different numbers of hook codes are hung at different positions at two ends of the lever, so that the lever balance is verified, the lever balance three scoring points are scored by using the spring dynamometer, the artificial intelligence scoring system is more beneficial to accurately positioning the scoring points, and the scoring effect is more accurate.
Description
Technical Field
The invention relates to the technical field of experimental teaching equipment, in particular to artificial intelligence scoring experimental equipment and a scoring method for a lever balance experiment.
Background
At present, in various domestic provinces, experiment operations such as physical, chemical and biological are brought into the examination range of middle examination, at present, the teacher scores the experiments subjectively mainly according to the scoring points, the scoring scale of each teacher is different, so that the scoring does not have good objectivity, and the traditional lever balance experiment equipment cannot extract key points well due to the influence of factors such as environmental background illumination and the like, so that the accuracy of artificial intelligence scoring is influenced.
Disclosure of Invention
The invention aims to provide artificial intelligence scoring experimental equipment and a scoring method for a lever balance experiment, which are beneficial to an artificial intelligence scoring system to accurately position a scoring point, enable the scoring effect to be more accurate and solve the problems in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: the utility model provides an artificial intelligence of lever balance experiment experimental apparatus that scores, includes the lever, the aperture that the lever passes through the lever center is installed on the iron stand platform, and the metal pole position of iron stand platform is the mid point of lever, the below of lever has hung white angle indicator board, be provided with the pointer on the white angle indicator board, the peg is all installed as the starting point to a fixed distance at both ends every to the dead opposite use lever mid point aperture of lever, and the white stripe that is the rectangle form all is scribbled on the same position of each peg at the back of lever, balance nut is all installed at the both ends of lever, still install the knob on the lever.
Further, the lever is coated with black matte paint or frosted paint.
Further, the length of lever is 110cm, and the quantity of peg is 20, and wherein both ends are each 10 about lever central point, and the interval between two adjacent pegs is 5 cm.
Furthermore, a hook code is arranged at the position of the hanging nail, the hook code is hung on the hanging nail through a cotton thread, and a spring dynamometer is also hung at the position of the hanging nail.
Furthermore, an overlooking camera is installed above the iron support, a foresight camera is installed in front of the iron support, and output ends of the overlooking camera and the foresight camera are electrically connected with an input end of a deep learning and image processing method which is arranged in the student cloud terminal through a Bluetooth module.
According to another aspect of the invention, a method for artificial intelligence scoring of a lever balance experiment is provided, which comprises the following steps:
s1: adjusting balance nuts at two ends of the lever to balance the lever before judging the experiment;
s2: judging the hook codes hung at two ends of the lever fulcrum, and adjusting the number and the positions of the hook codes to balance the lever;
s3: the hook code was hung at one end and the lever was balanced using a spring load cell at the other end of the lever.
Further, each frame of image in the front-view video uses a deep learning detection algorithm to detect a hook code, a hand, a lever, a balance nut and a metal rod on an iron stand, and uses a circumscribed rectangle to represent the position of the metal rod, if a Bounding Box marking the position of the hand and a Bounding Box IOU marking the balance nut are greater than a specified threshold, the student is judged to finish the operation of adjusting the balance nut, and compares the length-width ratio of the lever Bounding Box at the moment, if the length-width ratio is greater than the preset threshold in a certain continuous frame, the lever is considered to be balanced, if the length-width ratio is less than the specified threshold, the hook code is considered to be hung under the lever and is recorded as a time point, and the student finishes adjusting the balance nut before the time point and considers that the scoring point is correct if the lever is balanced.
Further, extracting a metal rod and a hook code of an iron stand and a bounding box of a lever from an image acquired by a front-view camera by using a target detection method, recording the position of the metal rod of the support as the position of the middle point of the lever, when the distance between the upper edge of the bounding box with the hook code at both ends of the middle point of the lever and the lower edge of the bounding box of the lever is detected to be smaller than a preset threshold value, considering that a student starts to perform the experimental operation related to the scoring point, and marking as a time point, when the distance between the upper edge of the bounding box with the hook code at both ends of the middle point of the lever and the lower edge of the bounding box of the lever exceeds a specified threshold value, considering that the operation related to the scoring point is completed, and marking as the time point, and performing the following operations on each frame image before the time point and the time point;
extracting the hook codes of the lever, the hook codes and the hook codes of the metal rod of the iron stand from the images read by the front-view camera and the top-view camera by using a target detection method, determining the number of the hook codes hung on the left side and the right side of the lever according to the hook codes, then segmenting white stripes on the back of all the levers by using a watershed algorithm, calculating the number of the white stripes between the hook codes on the left side and the right side of the left lever and the metal rod at the center of the lever and recording the distance between the hook codes and the center of the lever, judging whether the current condition meets a lever balance condition by using a lever balance formula (F1L 1= F2L 2), and if the balance condition is met, considering that the scoring point operates correctly.
Further, extracting the lever, the hook code, the iron stand metal rod and the bounding box of the spring dynamometer in the image read by the front-view camera by using a target detection method, firstly segmenting white stripes on the back of all the levers by using a watershed algorithm, obtaining the number of the hook codes and the positions of the hook codes according to the bounding box of the hook codes, finding the bounding box closest to the hook code along the lower edge of the lever, recording the white stripe closest to the middle point of the long edge of the hook code bounding box as the position where the hook code is suspended, obtaining the position of the spring dynamometer according to the bounding box of the spring dynamometer, recording the white stripe closest to the middle point of the long edge of the spring dynamometer as the force application position of the spring dynamometer, then calculating the numbers of the hook code and the white stripes of the spring dynamometer from the iron stand metal rod, calculating the reading of the spring dynamometer which theoretically balances the lever at the moment according to a lever balance formula, and comparing the reading error with the reading of the student on the student cloud terminal, and if the reading error is smaller than a set range, determining that the reading error is correct.
Further, if the spring dynamometer bounding box appears above the lever bounding box, a judgment algorithm is started, the target detection algorithm is used for extracting the bounding box of the spring dynamometer from an image acquired by the front-view camera, the length-width ratio of the spring dynamometer bounding box is larger than a set threshold value in a frame where all the spring dynamometer bounding boxes appear above the lever bounding box, the spring dynamometer is considered to be used correctly, and otherwise, the operation of the scoring point is considered to be wrong even if the reading is correct.
Compared with the prior art, the invention has the beneficial effects that:
according to the artificial intelligence scoring experimental equipment and the scoring method for the lever balance experiment, the scoring method uses an image processing and deep learning method to adjust the lever, so that the initial position is balanced, different numbers of hook codes are hung at different positions at two ends of the lever, so that the lever balance is verified, the lever balance three scoring points are scored by using the spring dynamometer, the scoring is mainly carried out by extracting key points in a video acquired by the overlooking camera arranged above the experiment table and the foresight camera arranged in front of the experiment table, the accurate positioning of the scoring points by an artificial intelligence scoring system is facilitated, and the scoring effect is more accurate.
Drawings
FIG. 1 is a schematic view of the back side of an artificial intelligence scoring experimental apparatus for a lever balance experiment according to the present invention;
FIG. 2 is a schematic front view of an experimental device with hook weights hung at both ends of a lever according to the present invention;
FIG. 3 is a schematic front view of an experimental device for hanging a hook weight at one end of a lever and a spring dynamometer at the other end of the lever according to the present invention;
FIG. 4 is a flow chart of the present invention.
In the figure: 1. a lever; 2. an iron stand; 3. a white angle indicator board; 31. a pointer; 4. hanging nails; 5. hooking codes; 51. cotton threads; 6. white stripes; 7. a balance nut; 8. a knob; 9. a spring load cell; 10. looking down the camera; 11. a front-view 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. 1-4, an artificial intelligence scoring experimental device for a lever balance experiment comprises a lever 1, wherein the lever 1 is coated by black matte paint or frosted paint, the lever 1 is installed on an iron stand 2 through a small hole in the center of the lever 1, a downward-looking camera 10 is installed above the iron stand 2, a forward-looking camera 11 is installed in front of the iron stand 2, output ends of the downward-looking camera 10 and the forward-looking camera 11 are electrically connected with an input end of a deep learning and image processing method built in a student cloud terminal through a Bluetooth module, the scoring method is used for adjusting the lever 1 by using the image processing and deep learning methods, the initial position is balanced, hook codes 5 in different numbers are hung at two ends of the lever 1 at different positions to enable the lever 1 to balance and verify the balance rule of the lever 1, the lever 1 is scored by using a spring dynamometer 9 to balance three scoring points, and mainly by extracting the downward-looking camera 10 arranged above the experiment table and the forward-looking camera 11 arranged in front of the experiment table The method is characterized in that key points in a video are taken for scoring, the scoring effect is more accurate due to the fact that a scoring system can accurately position the scoring points, the position of a metal rod of an iron stand 2 is the middle point of a lever 1, a white angle indicating plate 3 is hung below the lever 1, a pointer 31 is arranged on the white angle indicating plate 3, hanging nails 4 are arranged on the right side and the opposite side of the lever 1 at intervals of a fixed distance from the middle point small hole of the lever 1 to the two ends of the lever 1, the length of the lever 1 is 110cm, the number of the hanging nails 4 is 20, 10 hanging nails are arranged on the left end and the right end of the center point of the lever 1 respectively, the distance between every two adjacent hanging nails 4 is 5cm, hook codes 5 are arranged on the hanging nails 4, the hook codes 5 are hung on the hanging nails 4 through cotton threads 51, spring forcemeters 9 are also hung on the hanging nails 4, rectangular white stripes 6 are coated on the back of the lever 1 at the same position of each hanging nail 4, balance nuts 7 are mounted at two ends of the lever 1, and a knob 8 is further mounted on the lever 1.
In order to better show the process of artificial intelligence scoring in the lever balance experiment, the embodiment provides a method for artificial intelligence scoring in the lever balance experiment, which includes the following steps:
s1: before the evaluation experiment, balance nuts 7 at two ends of the lever 1 are adjusted to balance the lever 1.
Detecting the hook code 5, the hand, the lever 1, the balance nut 7 and the metal rod on the iron stand 2 by using a deep learning detection algorithm for each frame of image in the front-view video, and representing the positions of the hook code, the hand, the balance nut 7 and the metal rod on the iron stand 2 by using a circumscribed rectangle of the metal rod, judging that the student finishes the operation of adjusting the balance nut 7 when a Bounding Box marking the position of the hand and a Bounding Box IOU marking the balance nut 7 are greater than a specified threshold value, comparing the length-width ratio of the lever 1Bounding Box at the moment, considering that the lever 1 is balanced when the length-width ratio is greater than the preset threshold value in a certain continuous frame, considering that the hook code 5 is hung under the lever 1 when the position of the hook code 5 and the position of the lever 1 are less than the specified threshold value, and marking as time point 1, and considering that the evaluation point 1 is correct when the student finishes adjusting the balance nut 7 before the time point 1 and the lever 1 is balanced.
S2: and judging that hook codes 5 are hung at two ends of the fulcrum of the lever 1, and adjusting the number and the positions of the hook codes 5 to balance the lever 1.
Extracting a metal rod of a stand 2, a hook code 5 and a bounding box of a lever 1 from an image acquired by a front-view camera 11 by using an object detection method, recording the position of the metal rod of a support as the position of the middle point of the lever 1, when the distance between the upper edge of the bounding box with the hook code 5 at both ends of the middle point of the lever 1 and the lower edge of the bounding box of the lever 1 is detected to be less than a preset threshold value, considering that a student starts to perform the experimental operation related to the scoring point and records as a time point 2, when the distance between the upper edge of the bounding box with the hook code 5 at both ends of the middle point of the lever 1 and the lower edge of the bounding box of the lever 1 exceeds a specified threshold value, considering that the operation related to the scoring point is completed and records as a time point 3, and performing the following operations on each frame image before the time point 2 and the time point 3.
Extracting the hook boxes of the lever 1, the hook codes 5 and the metal rods of the iron stand 2 from the images read by the front-view camera 11 and the top-view camera 10 by using an object detection method, determining the number of the hook codes 5 hung on the left side and the right side of the lever 1 according to the hook boxes of the hook codes 5, then segmenting all white stripes 6 on the back side of the lever 1 by using a watershed algorithm, calculating the number of the white stripes 6 between the hook codes 5 on the left side and the right side of the lever 1 and the metal rod at the center of the lever 1 to be recorded as the distance between the hook codes 5 and the center of the lever 1, judging whether the current situation meets the balance condition of the lever 1 by using a lever balance formula F1L1= F2L2, and if the balance condition is met, judging that the scoring point operates correctly.
S3: the hook code 5 is hung at one end and the lever 1 is balanced at the other end of the lever using a spring load cell 9.
Extracting the lever 1, the hook code 5, the metal rod of the iron stand 2 and the bounding box of the spring dynamometer 9 in the image read from the front-view camera 11 by using a target detection method, firstly segmenting white stripes 6 on the back of all the lever 1 by using a watershed algorithm, obtaining the number of the hook codes 5 and the positions of the hook codes 5 according to the bounding box of the hook codes 5, finding the bounding box of the hook code 5 closest to the lower edge of the lever 1, marking the white stripe 6 closest to the middle point of the long side of the hook code 5bounding box as the position where the hook code 5 is hung, obtaining the position of the spring dynamometer 9 according to the bounding box of the spring dynamometer 9, marking the white stripe 6 closest to the middle point of the long side of the spring dynamometer 9 as the force application position of the spring dynamometer 9, then calculating the number of the white stripes 6 of the hook codes 5 and the spring dynamometer 9 from the metal rod of the iron stand 2, and calculating the reading of the spring dynamometer 9 which theoretically balances the lever 1 at the moment according to the balance formula of the lever dynamometer 1, and comparing the reading error with the reading of the student on the student cloud terminal, and if the reading error is smaller than a set range, determining that the reading error is correct.
And starting a judging algorithm if the spring load cell 9bounding box appears above the lever 1bounding box, extracting the bounding box of the spring load cell 9 from an image acquired by the front-view camera 11 by using a target detection algorithm, and considering that the spring load cell 9 is used correctly if the length-width ratio of the spring load cell 9bounding box is greater than a set threshold value in a frame of all the spring load cells 9bounding boxes appearing above the lever 1bounding box, otherwise, considering that the operation of the scoring point is wrong even if the reading is correct.
In summary, according to the artificial intelligence scoring experiment equipment and the scoring method for the lever balance experiment, the scoring method uses an image processing and deep learning method to adjust the lever 1 to balance the initial position, different numbers of hook codes 5 are hung at different positions at two ends of the lever 1 to balance and verify the balance rule of the lever 1, the spring dynamometer 9 is used to balance three scoring points of the lever 1 to score, the key points in the video acquired by the overlooking camera 10 arranged above the experiment table and the foresight camera 11 arranged in front of the experiment table are mainly extracted to score, the accurate positioning of the scoring points by an artificial intelligence scoring system is facilitated, and the scoring effect is more accurate.
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 (7)
1. The utility model provides a method that artifical intelligence of lever balance experiment was graded, experimental device include lever (1), install on iron stand platform (2) through the aperture at lever (1) center in lever (1), the metal rod position of iron stand platform (2) is the mid point of lever (1), white angle indicator board (3) have been hung to the below of lever (1), be provided with pointer (31) on white angle indicator board (3), peg (4) are all installed to the fixed distance of both ends every other with lever (1) mid point aperture as the starting point to the positive and opposite face of lever (1), and the back of lever (1) all scribbles white stripe (6) that are the rectangle form on the same position of each peg (4), balanced nut (7) are all installed at the both ends of lever (1), still install knob (8) on lever (1), overlook camera (10) are installed to the top of iron stand platform (2), the front view camera (11) is installed in the place ahead of iron stand platform (2), the output of looking down camera (10) and front view camera (11) all is connected with the built-in degree of depth study of student's cloud terminal and the input electricity of image processing method through bluetooth module, its characterized in that includes following step:
s1: adjusting balance nuts (7) at two ends of the lever (1) before judging an experiment to balance the lever (1);
s2: judging that hook codes (5) are hung at two ends of a fulcrum of the lever (1), and adjusting the number and the position of the hook codes (5) to balance the lever (1);
s3: judging the hook weight (5) hung at one end and balancing the lever (1) by using a spring dynamometer (9) at the other end of the lever;
the specific steps for S1 are as follows:
each frame of image in the front-view video uses a deep learning detection algorithm to detect a hook code (5), a hand, a lever (1), a balance nut (7) and a metal rod on an iron stand (2), and the position is represented by the circumscribed rectangle, if the Bounding Box marking the hand position and the Bounding Box IOU marking the balance nut (7) are larger than the specified threshold value, the student is judged to finish the operation of adjusting the balance nut (7), and comparing the length-width ratio of the lever (1) bounding box at the moment, if the length-width ratio is larger than a preset threshold value in a certain continuous frame, considering that the lever (1) is balanced, and when the position of the hook code (5) and the position of the lever (1) are smaller than a specified threshold value, considering that the hook code (5) is suspended under the lever (1) and recording as a time point 1, wherein a student finishes adjusting a balance nut (7) before the time point 1 and considers that the evaluation point 1 is correct when the lever (1) is balanced.
2. The method for artificial intelligence scoring in a lever balance test as claimed in claim 1, wherein the specific steps of S2 are as follows:
s21: extracting a metal rod, a hook code (5) and a bounding box of a lever (1) from an image acquired by a front-view camera (11) by using a target detection method, recording the position of the metal rod of a support as the position of the middle point of the lever (1), when the distance between the upper edge of the bounding box, which is detected that the hook code (5) is arranged at both ends of the middle point of the lever (1), and the lower edge of the bounding box of the lever (1) is smaller than a preset threshold value, considering that a student starts to perform the experimental operation related to the scoring point, and recording as a time point 2, when the distance between the upper edge of the bounding box, which is arranged at both ends of the hook code (5), and the lower edge of the bounding box of the lever (1) exceeds the preset threshold value, considering that the operation related to the scoring point is completed, and recording as a time point 3, and performing the following operations on each frame image before the time point 2 and the time point 3;
s22: the method comprises the steps of extracting a bounding box of a lever (1), a hook code (5) and a metal rod of a frame (2) from images read by a front-view camera (11) and a top-view camera (10) by using an object detection method, determining the number of the hook codes (5) hung on the left side and the right side of the lever (1) according to the bounding box of the hook code (5), then dividing white stripes (6) on the back of all the levers (1) by using a watershed algorithm, calculating the number of the white stripes (6) between the hook codes (5) on the left side and the right side of the lever (1) and the metal rod at the center of the lever (1), recording the number of the white stripes (6) between the hook codes (5) on the left side and the right side of the lever (1) as the distance between the hook codes (5) and the center of the lever (1), judging whether the current situation meets a balance condition of the lever (1) by using a lever balance formula (F1L 1= F2L 2), and if the balance condition is met, judging that the scoring point operates correctly.
3. The method for artificial intelligence scoring in a lever balance test as claimed in claim 1, wherein the specific steps of S3 are as follows:
extracting a lever (1), a hook code (5), a metal rod of a frame table (2) and a bounding box of a spring dynamometer (9) in an image read from a front-view camera (11) by using a target detection method, firstly segmenting white stripes (6) on the back of all the levers (1) by using a watershed algorithm, obtaining the number of the hook codes (5) and the position of the hook codes (5) according to the bounding box of the hook codes (5), finding the bounding box of the hook code (5) closest to the lower edge of the lever (1), marking the white stripe (6) closest to the middle point of the long edge of the hook code (5) as the hanging position of the hook code (5), obtaining the position of the spring dynamometer (9) according to the bounding box of the spring dynamometer (9), and marking the spring of the white stripe (6) closest to the middle point of the long edge of the spring dynamometer (9) as the force applying position of the spring dynamometer (9), and then calculating the number of the hook codes (5) and the number of the white stripes (6) of the spring dynamometer (9) away from the metal rod of the iron support (2), calculating the reading of the spring dynamometer (9) which theoretically balances the lever (1) at the moment according to a lever (1) balance formula, comparing the reading with the reading of a student on a student cloud terminal, and judging the reading to be correct if the reading error is smaller than a set range.
4. The artificial intelligence scoring method for the lever balance test as claimed in claim 3, further comprising a judgment of whether the spring dynamometer (9) is used correctly, the specific steps are as follows:
and if the spring load cell (9) is arranged above the lever (1), starting a judgment algorithm, extracting the spring load cell of the spring load cell (9) from an image acquired by the front-view camera (11) by using a target detection algorithm, and if all the spring load cells (9) are arranged in a frame above the lever (1), and the length-width ratio of the spring load cell (9) is larger than a set threshold value, considering that the spring load cell (9) is used correctly, otherwise, considering that the scoring point is operated incorrectly even if the reading is correct.
5. The artificial intelligence scoring method for the lever balance test is characterized in that the lever (1) is coated by black matte paint or frosted paint.
6. The artificial intelligence scoring method for the lever balance experiment is characterized in that the length of the lever (1) is 110cm, the number of the hanging nails (4) is 20, the left end and the right end of the center point of the lever (1) are respectively 10, and the distance between every two adjacent hanging nails (4) is 5 cm.
7. The artificial intelligence scoring method for the lever balance test is characterized in that a hook code (5) is arranged at the position of the hanging nail (4), the hook code (5) is hung on the hanging nail (4) through a cotton thread (51), and a spring dynamometer (9) is also hung at the position of the hanging nail (4).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010154326.5A CN111223343B (en) | 2020-03-07 | 2020-03-07 | Artificial intelligence scoring experimental equipment and scoring method for lever balance experiment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010154326.5A CN111223343B (en) | 2020-03-07 | 2020-03-07 | Artificial intelligence scoring experimental equipment and scoring method for lever balance experiment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111223343A CN111223343A (en) | 2020-06-02 |
| CN111223343B true CN111223343B (en) | 2022-01-28 |
Family
ID=70827310
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010154326.5A Active CN111223343B (en) | 2020-03-07 | 2020-03-07 | Artificial intelligence scoring experimental equipment and scoring method for lever balance experiment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111223343B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11778804B2 (en) | 2021-04-02 | 2023-10-03 | Changxin Memory Technologies, Inc. | Capacitor array structure and fabrication method thereof |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107368890A (en) * | 2016-05-11 | 2017-11-21 | Tcl集团股份有限公司 | A kind of road condition analyzing method and system based on deep learning centered on vision |
| KR20180052868A (en) * | 2016-11-11 | 2018-05-21 | 최은준 | Electric balance for education |
| CN109816725A (en) * | 2019-01-17 | 2019-05-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of monocular camera object pose estimation method and device based on deep learning |
| CN209000319U (en) * | 2018-08-03 | 2019-06-18 | 杭州海康威视数字技术股份有限公司 | A kind of lever balance experimental provision and experimental facilities |
| CN209000322U (en) * | 2018-08-23 | 2019-06-18 | 杭州海康威视数字技术股份有限公司 | A kind of lever balance experimental provision and experimental facilities |
| CN109977943A (en) * | 2019-02-14 | 2019-07-05 | 平安科技（深圳）有限公司 | A kind of images steganalysis method, system and storage medium based on YOLO |
| CN209447383U (en) * | 2018-05-25 | 2019-09-27 | 杨淳铄 | A kind of lever used for physics teaching |
| CN110689005A (en) * | 2019-09-05 | 2020-01-14 | 上海零眸智能科技有限公司 | Commodity identification method based on deep learning fusion position and shape information |
| CN110837795A (en) * | 2019-11-04 | 2020-02-25 | 防灾科技学院 | Teaching condition intelligent monitoring method, device and equipment based on classroom monitoring video |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2017332287A1 (en) * | 2016-09-22 | 2019-05-16 | Shadecraft, LLC | Mobile computing device control of shading object |
-
2020
- 2020-03-07 CN CN202010154326.5A patent/CN111223343B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107368890A (en) * | 2016-05-11 | 2017-11-21 | Tcl集团股份有限公司 | A kind of road condition analyzing method and system based on deep learning centered on vision |
| KR20180052868A (en) * | 2016-11-11 | 2018-05-21 | 최은준 | Electric balance for education |
| CN209447383U (en) * | 2018-05-25 | 2019-09-27 | 杨淳铄 | A kind of lever used for physics teaching |
| CN209000319U (en) * | 2018-08-03 | 2019-06-18 | 杭州海康威视数字技术股份有限公司 | A kind of lever balance experimental provision and experimental facilities |
| CN209000322U (en) * | 2018-08-23 | 2019-06-18 | 杭州海康威视数字技术股份有限公司 | A kind of lever balance experimental provision and experimental facilities |
| CN109816725A (en) * | 2019-01-17 | 2019-05-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of monocular camera object pose estimation method and device based on deep learning |
| CN109977943A (en) * | 2019-02-14 | 2019-07-05 | 平安科技（深圳）有限公司 | A kind of images steganalysis method, system and storage medium based on YOLO |
| CN110689005A (en) * | 2019-09-05 | 2020-01-14 | 上海零眸智能科技有限公司 | Commodity identification method based on deep learning fusion position and shape information |
| CN110837795A (en) * | 2019-11-04 | 2020-02-25 | 防灾科技学院 | Teaching condition intelligent monitoring method, device and equipment based on classroom monitoring video |
Non-Patent Citations (1)
| Title |
|---|
| 基于YOLO的驾驶视频目标检测方法;文浩彬，张国辉;《汽车科技》;20190228;第73-76页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111223343A (en) | 2020-06-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112818988B (en) | Automatic identification reading method and system for pointer instrument | |
| CN102521560B (en) | Instrument pointer image identification method of high-robustness rod | |
| CN105139023B (en) | A kind of seed recognition methods based on multi-scale feature fusion and extreme learning machine | |
| CN106557764B (en) | A kind of water level recognition methods based on binary-coded character water gauge and image procossing | |
| CN106778734A (en) | A kind of insulator based on rarefaction representation falls to go here and there defect inspection method | |
| CN103325122B (en) | Based on the pedestrian retrieval method of Bidirectional sort | |
| CN110378232B (en) | Improved test room examinee position rapid detection method of SSD dual-network | |
| CN106127205A (en) | A kind of recognition methods of the digital instrument image being applicable to indoor track machine people | |
| CN105404867B (en) | A kind of substation isolating-switch state identification method of view-based access control model | |
| CN113139500B (en) | Smoke detection method, system, medium and equipment | |
| CN105930852B (en) | A kind of bubble image-recognizing method | |
| CN108875794A (en) | Image visibility detection method based on transfer learning | |
| CN111554149B (en) | System and method for copybook scoring | |
| CN109344835A (en) | Altering detecting method based on vehicle VIN code character position | |
| WO2018032626A1 (en) | Teaching toy kit and number identification method thereof | |
| CN111223343B (en) | Artificial intelligence scoring experimental equipment and scoring method for lever balance experiment | |
| CN112488047A (en) | Piano fingering intelligent identification method | |
| CN115359295A (en) | Decoupling knowledge distillation hardware target detection method and system | |
| CN107944340B (en) | Pedestrian re-identification method combining direct measurement and indirect measurement | |
| CN202204479U (en) | Virtual optical extensometer | |
| CN110411439A (en) | A kind of method, apparatus and medium generating emulation asterism according to star energy grade | |
| CN110096708A (en) | A kind of determining method and device of calibration collection | |
| CN112183163A (en) | Natural scene text detection method based on full convolution residual error network | |
| CN111189826B (en) | Intelligent scoring experimental equipment and method for measuring pH value of solution to be measured by pH test paper | |
| CN115931895A (en) | Method and device for checking defects of power transmission line |
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 |