Online invigilation remote video cheating determination system and method
A remote video, research and judgment technology, applied in the field of video recognition, can solve problems such as the inability to accurately judge students’ cheating behaviors and the waste of invigilation resources, and achieve the effects of real-time and accurate invigilation, reduced labor costs, and fast image processing
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0035] Specific implementation mode 1: In conjunction with the description of Figure 1-2, an online invigilation remote video cheating research and judgment system of the present invention, the specific implementation process is as follows:
[0036] The system includes a video acquisition module, a video stream synthesis module, a video push module, a judgment center server, and an invigilator terminal. The judgment center server includes a video analysis module, a video stream judgment cheating module, and a suspected cheating notification module. Each module is in the above logical order. Submit to further levels of implementation;
[0037] Among them, the video acquisition module is connected with the video stream synthesis module through wireless signals; the video stream synthesis module establishes a connection with the research and judgment center server through remote data transmission; the research and judgment center server is wirelessly connected with the invigilator...
specific Embodiment approach 2
[0040] Specific implementation mode 2: In combination with the description of Figure 1-2, the specific implementation process of an online invigilation remote video cheating research and judgment method is as follows:
[0041] Step 1: The server of the research and judgment center obtains and stores the synthesized multi-screen video stream transmitted remotely in real time. The video stream comes from the video data obtained from the examinee's main station and multiple auxiliary station devices;
[0042] Step 2: Filter the image (action, posture, line of sight) feature points for each picture in the video stream;
[0043] Step 3: Determine and mark the stored feature points as suspected cheating;
[0044] Step 4: Push the video equipment terminal corresponding to the video stream marked as suspected cheating to the invigilator terminal.
specific Embodiment approach 3
[0045] Embodiment 3: In addition to the online invigilation remote video cheating method described in Step 1 of Embodiment 2, it also includes performing image output and storage of the video stream in the form of video frames, and then extracting single-screen images from the output multi-screen images. Finally, the extracted image is subjected to feature classification, including main position and auxiliary position, and image data;
[0046] Use ffmpeg to realize the video splicing task, and use the demuxer in ffmpeg to splice the input multi-channel video. The splicing based on the demuxer requires exactly the same video and audio attributes. This method will not cause decode->encode to the video and audio streams. influences;
[0047] Use opencv's built-in face recognizer to judge the authenticity of candidates, and use opencv's classic visual tracking algorithm camshift algorithm to track the vision to judge whether the eyes are focused on the test paper.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com