CN111314665A - Key video segment extraction system and method for video post-scoring - Google Patents
Key video segment extraction system and method for video post-scoring Download PDFInfo
- Publication number
- CN111314665A CN111314665A CN202010154313.8A CN202010154313A CN111314665A CN 111314665 A CN111314665 A CN 111314665A CN 202010154313 A CN202010154313 A CN 202010154313A CN 111314665 A CN111314665 A CN 111314665A
- Authority
- CN
- China
- Prior art keywords
- video
- key
- student
- cloud terminal
- network camera
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- 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
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/23418—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving operations for analysing video streams, e.g. detecting features or characteristics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/472—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content
- H04N21/47202—End-user interface for requesting content, additional data or services; End-user interface for interacting with content, e.g. for content reservation or setting reminders, for requesting event notification, for manipulating displayed content for requesting content on demand, e.g. video on demand
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention discloses a key video segment extraction system and method for video post scoring, which comprises a video server, a video multi-stream cloud terminal, a network camera and a student cloud terminal, wherein the video server is connected with the video multi-stream cloud terminal; the network camera comprises a front-view network camera and a top-view network camera, the front-view network camera is installed at the front end of the student cloud terminal, and the top-view network camera is installed at the top of the experiment table. According to the invention, the network camera is used for capturing the experiment operation process of the student, the video multi-stream cloud terminal stores the operation video of the student, and finally the operation video of each experiment is intelligently intercepted through the video server. And the key time points in each time period are extracted through an intelligent analysis algorithm, and the marked key time points are displayed when the teacher scores according to the student operation videos, so that the manual scoring and teaching guidance efficiency of the teacher can be greatly improved.
Description
Technical Field
The invention relates to the technical field of teaching and examination of middle school experiments, in particular to a key video segment extraction system and method for video post-event scoring.
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, since there are too many students, the teacher needs to guide or judge the experimental operation of the students on site for a long time. Many students cannot get one-to-one guidance due to time problems, and the energy of the teacher is also enormous.
Therefore, how to alleviate the teaching pressure of teachers and effectively guide and judge the experiment operation of each student is a problem that needs to be solved urgently by those skilled in the art.
Disclosure of Invention
The invention aims to provide a key video segment extraction system and method for video post-scoring, which can relieve the teaching pressure of teachers, effectively guide and judge the experimental operation of each student and solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a key video segment extraction system for video post-scoring comprises a video server, a video multi-stream cloud terminal, a network camera and a student cloud terminal, wherein the student cloud terminal is installed on an experiment table;
the video server is connected with the video multi-stream cloud terminal, and the video multi-stream cloud terminal is connected with the network camera;
the network camera comprises a foresight network camera and a top-view network camera, the foresight network camera is installed at the front end of the student cloud terminal, the top-view network camera is installed at the top of the experiment table, and the foresight network camera and the top-view network camera respectively record foresight and top-view videos of student experiment operations.
Furthermore, the video server, the video multi-stream cloud terminal and the network camera are all in the same local area network environment.
Further, the video server stores key video segments of the student examination operation and extraction algorithms for deploying the key video segments and key time points.
Further, the video multi-stream cloud terminal simultaneously records all camera videos of one laboratory.
The invention also provides another technical scheme: a method for extracting key video segments of video post-scoring comprises the following steps:
s1: a Ubuntu operating system is equipped in a computer, all network cameras are connected with a video multi-stream cloud terminal through a switch, and the video multi-stream cloud terminal is connected with a video server equipped with the operating system;
s2: building a video server framework and a video service database based on a Linux operating system;
s3: setting safety access, setting IP address verification, and registering access only by the IP address in the school;
s4: video service clients are installed on the experiment table and the teacher machine, students on the experiment table log in through student accounts registered in the video server, and teachers on the teacher machine log in through teacher accounts;
s5: the video server utilizes the graphics processor to train the deep learning network model; and (4) optimizing the deep learning network model, and embedding the optimal model into a video service algorithm so as to extract key sections and key points of the video.
Further, step S2 specifically includes:
s21: installing a packed video service algorithm, configuring a video server, a video multi-stream cloud terminal, a network camera and a student machine IP on a laboratory bench, installing and configuring a database, configuring a PHP, and installing and configuring a phpMyAdmin;
s22: and setting a database to store the IP of all machines and cameras, and intercepting the path and key points of the key video according to an intelligent algorithm.
Further, the specific steps of the key video segment extraction and time point algorithm in S5 are as follows:
s51: training a depth network model capable of identifying and segmenting experimental equipment and student actions by using a graphic processor configured to a video service aiming at middle-school physical and chemical experiment operation;
s52: matching the recognition and segmentation results with experiment operation steps specified by the education outline, recording the time point of each operation action in the experiment video, taking the difference between the time points of the first action and the last action as the key time period of the whole experiment, and taking the time point of the middle action as the key time point;
s53: and intercepting the key video segment by using OpenCV and storing the key video segment to the hard disk. Storing the path and the key point of the key video segment to a database;
s54: and displaying the path and the time point of the video segment stored in the database at the Web front end, so that students and teachers can access and check the video segment by using the account numbers of the students and the teachers.
Further, S51 includes the following steps:
s511: training a deep learning network for identifying and segmenting experimental instruments and experimental actions by using the labeled student experiment operation images;
s512: and automatically identifying and segmenting experimental equipment and experimental operation actions by using the trained deep learning model.
Further, S512 includes the steps of:
s5121: screening marked student operation and equipment images from a video server to serve as a training set, and storing the training set in a JPG format;
s5122: analyzing the image in the jpg format of the step by using an image library carried by Tensorflow, and converting the image into a 448 x 3 color image;
s5123: during training, random selection is carried out, and contrast enhancement, inversion, stretching, translation and Gaussian noise addition are carried out on an input image to enhance the data set. Learning by adopting a target detection model and adding a residual error structure;
s5124: adding the characteristic pyramid mode into a backbone network, sampling 4 scales of characteristic graphs in total, performing characteristic extraction on each characteristic graph through a non-global convolution network, normalizing to the same size, and adding images to obtain a fused characteristic graph;
s5125: and carrying out target detection and example segmentation on the fused feature graph, and finally carrying out non-maximum value inhibition to obtain a final identification and segmentation result.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the network camera is used for capturing the experiment operation process of the student, the video multi-stream cloud terminal stores the operation video of the student, and finally the operation video of each experiment is intelligently intercepted through the video server. And the key time points in each time period are extracted through an intelligent analysis algorithm, and the marked key time points are displayed when the teacher scores according to the student operation videos, so that the manual scoring and teaching guidance efficiency of the teacher can be greatly improved.
Drawings
Fig. 1 is a schematic structural diagram of a key video segment extraction system for video post-scoring according to the present invention;
FIG. 2 is a schematic top view and front view of the camera mounting of the present invention;
FIG. 3 is a block schematic diagram of the present invention;
FIG. 4 is a flow chart of the method of the present invention.
In the figure: 1. a video server; 2. a video multi-stream cloud terminal; 3. a network camera; 31. a forward-looking web camera; 32. a top view network camera; 4. a student cloud terminal; 5. experiment table.
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 and 3, a key video segment extraction system for video post scoring comprises a video server 1, a video multi-stream cloud terminal 2, a network camera 3 and a student cloud terminal 4, wherein the student cloud terminal 4 is installed on an experiment table 5. The video server 1 is connected with the video multi-stream cloud terminal 2, and the video multi-stream cloud terminal 2 is connected with the network camera 3. The video server 1 is used for storing key video segments of examination operations of students, deploying key video segments and extracting algorithms of key time points, and marking the key time points on the video segments for display of a teacher end, so that the teacher can conveniently check the key video segments. By using the video multi-stream cloud terminal 2, a plurality of network cameras 3 can be controlled to stably record videos. The answer sheet process of the students is completed on the student cloud terminal 4.
Referring to fig. 2, the network camera 3 includes a front view network camera 31 and a top view network camera 32, the front view network camera 31 is installed at the front end of the student cloud terminal 4, the top view network camera 32 is installed at the top of the experiment table 5, and the front view network camera 31 and the top view network camera 32 respectively record front view and top view videos of the student experiment operation. The top-looking and forward-looking fisheye wide-angle cameras can record the operation process of students in an all-around manner, and a teacher can conveniently score the students afterwards.
The video server 1, the video multi-stream cloud terminal 2 and the network camera 3 are all in the same local area network environment. The video multi-stream cloud terminal 2 simultaneously records all camera videos of one laboratory.
By adopting the technical scheme, the experiment operation video of the student can be rapidly and stably acquired, and the intelligent cutting and intelligent analysis operation process is carried out in the video server 1, so that the key operation nodes are marked. The efficiency of teacher's evaluation student examination operation after the fact is improved, alleviateed teacher's work burden.
Referring to fig. 4, in order to better show the process of extracting the key video segment for video post-scoring, the present embodiment provides a method for extracting the key video segment for video post-scoring, which includes the following steps:
s1: a Ubuntu operating system, specifically a Ubuntu16.04 operating system, is equipped in a computer, all network cameras 3 are connected with a video multi-stream cloud terminal 2 through a switch, and the video multi-stream cloud terminal 2 is connected with a video server 1 equipped with the operating system; the SDK, algorithm, and graphics processor are installed to the video server.
S2: building a video server framework and a video service database based on a Linux operating system;
s3: setting safety access, setting IP address verification, and registering access only by the IP address in the school;
s4: video service clients are installed on the experiment table and the teacher machine, students on the experiment table log in through student accounts registered in the video server, and teachers on the teacher machine log in through teacher accounts;
s5: the video server utilizes the graphics processor to train the deep learning network model; and (4) optimizing the deep learning network model, and embedding the optimal model into a video service algorithm so as to extract key sections and key points of the video.
To further optimize the above solution, step S2 specifically includes:
installing a packaged video service algorithm, configuring a video server 1, a video multi-stream cloud terminal 2, a network camera 3 and a student machine IP on a laboratory bench, and installing and configuring a database, wherein the database can be MySQL; configuring PHP, installing and configuring phpMyAdmin;
and setting a database to store the IP of all machines and cameras, and intercepting the path and key points of the key video according to an intelligent algorithm. The format for storing to the database is generally in DICOM format.
The specific steps of extracting the key video segment and the time point algorithm are as follows:
1. training a depth network model capable of identifying and segmenting experimental equipment and student actions by using a graphic processor configured to a video service aiming at middle-school physical and chemical experiment operation; the specific steps can be realized through step 1.1 to step 1.2.
Step 1.1, training a deep learning network for identifying and segmenting experimental instruments and experimental actions by using labeled student experiment operation images;
and 1.2, automatically identifying and segmenting experimental equipment and experimental operation actions by using the trained deep learning model.
In order to further improve the technical scheme, the recognition and segmentation effects of the step 1.2 are optimized. Specifically, the steps can be carried out by 2.1 to 2.5.
Step 2.1, screening out marked student operation and equipment images from the video server as a training set, and storing the training set in a JPG format;
step 2.2, analyzing the image in the jpg format obtained in the step by using an image library carried by Tensorflow, and converting the image into a 448 x 3 color image;
and 2.3, randomly selecting during training, and performing contrast enhancement, inversion, stretching, translation and Gaussian noise addition on the input image to enhance the data set. And learning by adopting a target detection model and adding a residual error structure.
And 2.4, adding the characteristic pyramid mode into the backbone network, sampling 4 scales of characteristic graphs in total, performing characteristic extraction on each characteristic graph through a non-global convolution network, normalizing to the same size, and adding images to obtain a fused characteristic graph.
And 2.5, carrying out target detection and example segmentation on the fused feature map, and finally carrying out non-maximum value inhibition to obtain a final identification and segmentation result.
S52: matching the recognition and segmentation results with experiment operation steps specified by the education outline, recording the time point of each operation action in the experiment video, taking the difference between the time points of the first action and the last action as the key time period of the whole experiment, and taking the time point of the middle action as the key time point;
s53: and intercepting the key video segment by using OpenCV and storing the key video segment to the hard disk. Storing the path and the key point of the key video segment to a database;
s54: and displaying the path and the time point of the video segment stored in the database at the Web front end, so that students and teachers can access and check the video segment by using the account numbers of the students and the teachers.
The key video segment extraction system for video post-scoring comprises a video server 1, a video multi-stream cloud terminal 2, a network camera 3 and a student cloud terminal 4, wherein the student cloud terminal 4 is installed on an experiment table 5. The video server 1 is connected with the video multi-stream cloud terminal 2, the video multi-stream cloud terminal 2 is connected with the network camera 3, the video multi-stream cloud terminal 2 stores key video segments of student examination operations and deploys key video segments and key time point extraction algorithms, the network camera 3 respectively records foresight videos and top view videos of student experiment operations, and key video bases can be provided for an artificial intelligence scoring system, teacher artificial scoring and teacher backtracking examinations afterwards. The student examination videos are intelligently cut and extracted into key time periods and key time points, and the post-mortem manual scoring and examination backtracking efficiency of teachers is greatly improved.
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. A key video segment extraction system for video post-scoring is characterized by comprising a video server (1), a video multi-stream cloud terminal (2), a network camera (3) and a student cloud terminal (4), wherein the student cloud terminal (4) is installed on an experiment table (5);
the video server (1) is connected with the video multi-stream cloud terminal (2), and the video multi-stream cloud terminal (2) is connected with the network camera (3);
network camera (3) are including foresight network camera (31) and top vision network camera (32), foresight network camera (31) install in the front end of student cloud terminal (4), top vision network camera (32) install in the top of experiment table (5), foresight network camera (31) and top vision network camera (32) take the foresight and the top vision video of student's experiment operation respectively.
2. The system for extracting key video segments for video post-event scoring as claimed in claim 1, wherein the video server (1), the video multi-stream cloud terminal (2) and the network camera (3) are all in the same local area network environment.
3. The key video segment extraction system for video post-mortem rating according to claim 1, wherein the video server (1) stores key video segments of student exam operations and extraction algorithms deploying key video segments, key time points.
4. The key video segment extraction system for video post-mortem scoring as claimed in claim 1, wherein the video multi-streaming cloud terminal (2) simultaneously takes all camera videos of one laboratory.
5. A method for key video segment extraction for video post-event scoring as claimed in claim 1, comprising the steps of:
s1: a Ubuntu operating system is equipped in a computer, all network cameras (3) are connected with a video multi-stream cloud terminal (2) through a switch, and the video multi-stream cloud terminal (2) is connected with a video server (1) equipped with the operating system;
s2: building a video server framework and a video service database based on a Linux operating system;
s3: setting safety access, setting IP address verification, and registering access only by the IP address in the school;
s4: video service clients are installed on the experiment table and the teacher machine, students on the experiment table log in through student accounts registered in the video server, and teachers on the teacher machine log in through teacher accounts;
s5: the video server utilizes the graphics processor to train the deep learning network model; and (4) optimizing the deep learning network model, and embedding the optimal model into a video service algorithm so as to extract key sections and key points of the video.
6. The method for extracting key video segments for video post-event rating as claimed in claim 5, wherein the step S2 specifically comprises:
s21: installing a packaged video service algorithm, configuring a video server (1), a video multi-stream cloud terminal (2), a network camera (3) and a student machine IP on a laboratory bench, installing and configuring a database, configuring a PHP (physical layer protocol), and installing and configuring a phpMyAdmin;
s22: and setting a database to store the IP of all machines and cameras, and intercepting the path and key points of the key video according to an intelligent algorithm.
7. The method for extracting key video segments for video post-event rating as claimed in claim 5, wherein the key video segments extraction and time point algorithm in S5 comprises the following specific steps:
s51: training a depth network model capable of identifying and segmenting experimental equipment and student actions by using a graphic processor configured to a video service aiming at middle-school physical and chemical experiment operation;
s52: matching the recognition and segmentation results with experiment operation steps specified by the education outline, recording the time point of each operation action in the experiment video, taking the difference between the time points of the first action and the last action as the key time period of the whole experiment, and taking the time point of the middle action as the key time point;
s53: intercepting a key video segment by using OpenCV, storing the key video segment to a hard disk, and storing a path and a key point of the key video segment to a database;
s54: and displaying the path and the time point of the video segment stored in the database at the Web front end, so that students and teachers can access and check the video segment by using the account numbers of the students and the teachers.
8. The method for key video segment extraction for video post-event rating according to claim 7, wherein S51 comprises the steps of:
s511: training a deep learning network for identifying and segmenting experimental instruments and experimental actions by using the labeled student experiment operation images;
s512: and automatically identifying and segmenting experimental equipment and experimental operation actions by using the trained deep learning model.
9. The method for key video segment extraction for video post-event rating according to claim 8, wherein S512 comprises the steps of:
s5121: screening marked student operation and equipment images from a video server to serve as a training set, and storing the training set in a JPG format;
s5122: analyzing the image in the jpg format of the step by using an image library carried by Tensorflow, and converting the image into a 448 x 3 color image;
s5123: randomly selecting during training, performing contrast enhancement, inversion, stretching, translation and Gaussian noise addition on an input image to enhance a data set, and learning by adopting a target detection model and adding a residual error structure;
s5124: adding the characteristic pyramid mode into a backbone network, sampling 4 scales of characteristic graphs in total, performing characteristic extraction on each characteristic graph through a non-global convolution network, normalizing to the same size, and adding images to obtain a fused characteristic graph;
s5125: and carrying out target detection and example segmentation on the fused feature graph, and finally carrying out non-maximum value inhibition to obtain a final identification and segmentation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010154313.8A CN111314665A (en) | 2020-03-07 | 2020-03-07 | Key video segment extraction system and method for video post-scoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010154313.8A CN111314665A (en) | 2020-03-07 | 2020-03-07 | Key video segment extraction system and method for video post-scoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111314665A true CN111314665A (en) | 2020-06-19 |
Family
ID=71160512
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010154313.8A Pending CN111314665A (en) | 2020-03-07 | 2020-03-07 | Key video segment extraction system and method for video post-scoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111314665A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113257062A (en) * | 2021-04-19 | 2021-08-13 | 上海知汇云信息技术股份有限公司 | Self-service student experiment evaluation system and method |
| CN113313984A (en) * | 2021-05-07 | 2021-08-27 | 广州市锐星信息科技有限公司 | Experimental examination scoring system, method and computer readable storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050271251A1 (en) * | 2004-03-16 | 2005-12-08 | Russell Stephen G | Method for automatically reducing stored data in a surveillance system |
| US20130201329A1 (en) * | 2011-11-14 | 2013-08-08 | Massachusetts Institute Of Technology | Assisted video surveillance of persons-of-interest |
| US20130235224A1 (en) * | 2012-03-09 | 2013-09-12 | Minwoo Park | Video camera providing a composite video sequence |
| CN109063568A (en) * | 2018-07-04 | 2018-12-21 | 复旦大学 | A method of the figure skating video auto-scoring based on deep learning |
| CN109378054A (en) * | 2018-12-13 | 2019-02-22 | 山西医科大学第医院 | A kind of multi-modality images assistant diagnosis system and its building method |
| 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 |
| CN109740530A (en) * | 2018-12-29 | 2019-05-10 | 深圳Tcl新技术有限公司 | Extracting method, device, equipment and the computer readable storage medium of video-frequency band |
| CN109829442A (en) * | 2019-02-22 | 2019-05-31 | 焦点科技股份有限公司 | A kind of method and system of the human action scoring based on camera |
| CN109829893A (en) * | 2019-01-03 | 2019-05-31 | 武汉精测电子集团股份有限公司 | A kind of defect object detection method based on attention mechanism |
| CN110516749A (en) * | 2019-08-29 | 2019-11-29 | 网易传媒科技（北京）有限公司 | Model training method, method for processing video frequency, device, medium and calculating equipment |
| CN110867099A (en) * | 2019-08-23 | 2020-03-06 | 广东工业大学 | Device and method for scoring and teaching exercise and fitness postures |
-
2020
- 2020-03-07 CN CN202010154313.8A patent/CN111314665A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050271251A1 (en) * | 2004-03-16 | 2005-12-08 | Russell Stephen G | Method for automatically reducing stored data in a surveillance system |
| US20130201329A1 (en) * | 2011-11-14 | 2013-08-08 | Massachusetts Institute Of Technology | Assisted video surveillance of persons-of-interest |
| US20130235224A1 (en) * | 2012-03-09 | 2013-09-12 | Minwoo Park | Video camera providing a composite video sequence |
| CN109063568A (en) * | 2018-07-04 | 2018-12-21 | 复旦大学 | A method of the figure skating video auto-scoring based on deep learning |
| CN109378054A (en) * | 2018-12-13 | 2019-02-22 | 山西医科大学第医院 | A kind of multi-modality images assistant diagnosis system and its building method |
| CN109740530A (en) * | 2018-12-29 | 2019-05-10 | 深圳Tcl新技术有限公司 | Extracting method, device, equipment and the computer readable storage medium of video-frequency band |
| CN109829893A (en) * | 2019-01-03 | 2019-05-31 | 武汉精测电子集团股份有限公司 | A kind of defect object detection method based on attention mechanism |
| CN109829442A (en) * | 2019-02-22 | 2019-05-31 | 焦点科技股份有限公司 | A kind of method and system of the human action scoring based on camera |
| 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 |
| CN110867099A (en) * | 2019-08-23 | 2020-03-06 | 广东工业大学 | Device and method for scoring and teaching exercise and fitness postures |
| CN110516749A (en) * | 2019-08-29 | 2019-11-29 | 网易传媒科技（北京）有限公司 | Model training method, method for processing video frequency, device, medium and calculating equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113257062A (en) * | 2021-04-19 | 2021-08-13 | 上海知汇云信息技术股份有限公司 | Self-service student experiment evaluation system and method |
| CN113313984A (en) * | 2021-05-07 | 2021-08-27 | 广州市锐星信息科技有限公司 | Experimental examination scoring system, method and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709409B (en) | Face living body detection method, device, equipment and medium | |
| CN107240047B (en) | Score evaluation method and device for teaching video | |
| CN111144191B (en) | Font identification method, font identification device, electronic equipment and storage medium | |
| CN109740446A (en) | Classroom students ' behavior analysis method and device | |
| CN110765907A (en) | System and method for extracting paper document information of test paper in video based on deep learning | |
| CN108090857A (en) | A kind of multi-modal student classroom behavior analysis system and method | |
| CN107918755A (en) | A kind of real-time focus analysis method and system based on face recognition technology | |
| CN105869085A (en) | Transcript inputting system and method for processing images | |
| CN111314665A (en) | Key video segment extraction system and method for video post-scoring | |
| CN110163211B (en) | Image recognition method, device and storage medium | |
| CN110465089B (en) | Map exploration method, map exploration device, map exploration medium and electronic equipment based on image recognition | |
| CN108345833A (en) | The recognition methods of mathematical formulae and system and computer equipment | |
| CN111368808A (en) | Method, device and system for acquiring answer data and teaching equipment | |
| CN112347997A (en) | Test question detection and identification method and device, electronic equipment and medium | |
| CN114005019B (en) | Method for identifying flip image and related equipment thereof | |
| CN104574434B (en) | Object detecting method and device | |
| CN117422695A (en) | CR-deep-based anomaly detection method | |
| CN110889460A (en) | Mechanical arm specified object grabbing method based on cooperative attention mechanism | |
| KR102416714B1 (en) | System and method for city-scale tree mapping using 3-channel images and multiple deep learning | |
| CN115659221A (en) | Teaching quality assessment method and device and computer readable storage medium | |
| CN111199378A (en) | Student management method, student management device, electronic equipment and storage medium | |
| CN115050039A (en) | Automatic test paper analysis method, system, electronic device and storage medium | |
| US10032079B2 (en) | Evaluation of models generated from objects in video | |
| CN114022905A (en) | Attribute-aware domain expansion pedestrian re-identification method and system | |
| CN113837167A (en) | Text image recognition method, device, equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200619 |
|
| RJ01 | Rejection of invention patent application after publication |