Super-resolution reconstruction method based on blackboard features in online classroom scene

A super-resolution reconstruction and blackboard technology, which is applied in the field of image super-resolution reconstruction, can solve problems such as the inability to accurately extract blackboard writing areas, image reconstruction index interference, and less attention to reconstruction speed, etc., to improve reconstruction effects and reduce calculations. and inference time, the effect of reducing the amount of data

Pending Publication Date: 2022-05-24
SOUTH CHINA UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the blackboards in some classrooms are movable, and in the online open class scene, the shooting camera generally moves with the movement of the teacher's body. The traditional image calibration method cannot achieve the effect of accurately extracting the writing area on the blackboard. This will not only cause the final image reconstruction index to be disturbed by irrelevant influence factors, but also cause a waste of equipment computing power
In addition, the chalk characters on the blackboard have obvious marginal features, but most of the existing super-resolution models are not designed for the marginal features, and the existing super-resolution reconstruction techniques pay less attention to the reconstruction speed, resulting in It is difficult to embed and use in the scene of high real-time requirements such as remote live teaching

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Super-resolution reconstruction method based on blackboard features in online classroom scene
  • Super-resolution reconstruction method based on blackboard features in online classroom scene
  • Super-resolution reconstruction method based on blackboard features in online classroom scene

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] as attached figure 2 As shown, what this embodiment provides is a super-resolution reconstruction method based on blackboard features in an online classroom scene, and the specific conditions are as follows:

[0043] S1, as attached image 3 As shown, the camera is installed on the wall in the back row of the classroom, collects video information including the complete blackboard writing area in real time, and transmits the video information to the computer.

[0044] S2. The blackboard video information collected by S1 is processed by the method of frame sampling, and the handwritten blackboard writing picture is obtained, which is used as the blackboard high-resolution data set of the online classroom scene, and the bicubic downsampling interpolation method and the video editing method are adopted. The decoding operation obtains the corresponding blackboard low-resolution data set, and then divides it into a training data set and a test data set for the image super-r...

Embodiment 2

[0075] As shown in Table 1, this embodiment provides a method of first performing blackboard blackboard area recognition and then performing super-resolution reconstruction based on blackboard features (identification first and then super-resolution) and a method of directly performing super-resolution reconstruction (direct super-resolution reconstruction). points) comparison,

[0076] Table 1. Comparison of performance indicators between the first-identify-then-over-score method and the direct over-score method

[0077]

[0078] The details are as follows:

[0079] For the 1080P test chart, when the area of ​​the blackboard writing area accounts for 1 / 2 of the entire test chart, the method of identifying first and then overscoring is more efficient than the method of direct overscoring in terms of multiplication and addition and time-consuming; when When the proportion decreases, the reduction in multiplier-adder and time-consuming increases further. The experimental re...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a super-resolution reconstruction method based on blackboard characteristics in an online classroom scene, and the method comprises the following steps: shooting a blackboard picture through a camera built in a classroom, accurately extracting a blackboard writing region through a target detection model, and carrying out the super-resolution reconstruction of an image. Besides, for the blackboard writing content with obvious edge features, gradient constraint is introduced into the super-resolution model to enhance feature learning, and the resolution of the blackboard writing content is effectively improved, so that the class learning efficiency of students is improved. The method has the characteristics of high running speed, low cost, convenience in use and the like, and ensures that online live teaching of the campus classroom is carried out smoothly.

Description

technical field [0001] The invention relates to the technical field of image super-resolution reconstruction, in particular to a super-resolution reconstruction method based on blackboard features in an online classroom scene. Background technique [0002] With the popularization of Internet technology, online education is quietly changing the way everyone learns, and more and more people are participating in live online teaching of campus classrooms through the Internet. At the same time, with the increase of the number of participants and the improvement of video quality requirements, the real-time performance required for live teaching is challenged under the limited network bandwidth. In addition, due to factors such as shooting angle or distance, non-knowledge content areas such as podiums and walls will appear, which is not friendly when bandwidth is limited. With the development of image processing technology, the traditional image calibration method can be used to r...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T3/40G06T7/13G06V10/44G06V10/774G06V10/80G06V10/82G06K9/62G06N3/04G06N3/08
CPCG06T3/4053G06T7/13G06N3/08G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30168G06N3/045G06F18/253G06F18/214
Inventor 冯颖林尹雁
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap