Unlock instant, AI-driven research and patent intelligence for your innovation.

A slide transition detection method based on sparse time-varying graph

A detection method and slideshow technology, applied in image analysis, image enhancement, image data processing, etc., can solve problems such as inability to handle camera switching, application limitations, etc., to achieve the effect of high accuracy and widening range

Active Publication Date: 2021-08-06
SHANGHAI UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, a method of tracking and matching feature point trajectories to detect slide transitions, but this method cannot handle camera switching, and its application is limited

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
  • A slide transition detection method based on sparse time-varying graph
  • A slide transition detection method based on sparse time-varying graph
  • A slide transition detection method based on sparse time-varying graph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings. This embodiment is implemented on the premise of the technical solution of the present invention, but the protection scope of the present invention is not limited to the following embodiments.

[0044] The application environment of the embodiment of the present invention is as follows: see figure 2 , enter the lecture video footage to switch between the speaker and slides.

[0045] see figure 1 , a method for detecting slide transitions based on sparse time-varying graphs, including the following steps:

[0046] Step 1: Video segmentation: extract the SIFT feature points of each video frame, and match the video frame with the feature points of the first frame of the current segment. If the similarity is higher than m, the image is considered to match and belong to the same segment; where m is the judgment Threshold on whether two video frames are simi...

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 slide switching detection method based on a sparse time-varying graph. For multi-camera speech videos with speakers, slides and audiences, the video is first segmented by feature point detection and matching, and the slides can be switched by using each segment of video as a node to establish a sparse graph for each time point The detection problem is transformed into a speculative graph adjacency matrix problem. Changes between adjacency matrices reflect slide transitions. The present invention is a method for overcoming the interference of lens movement, speaker movement and multiple PTZ lens switching in the speech video with better accuracy. Using the adjacency matrix deduced at each moment, the obtained detection results do not appear to detect people and Problems with people and slide transitions. And the accuracy is higher than the existing method, and the scope of speech video types that can be processed is expanded.

Description

technical field [0001] The invention relates to a method for detecting slide transitions of speech videos, in particular to a method for detecting transitions of slides based on sparse time-varying graphs. Background technique [0002] Now, online learning has become a very important way to acquire knowledge. Due to the visibility, convenience, and ability to convey rich information, lecture videos have become an important means of knowledge sharing and learning. People can access lecture videos for free through the Internet and learn from them. However, due to the popularity of consumer electronic devices and the development of the Internet, video data has exploded. For example, the total video data volume of the video sharing website YouTube has reached the order of petabytes (1PB=106GB), and the upload volume is still increasing at 300 hours per minute. If these videos are presented directly to users without screening and summarizing, users will waste a lot of time on ...

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 Patents(China)
IPC IPC(8): G06T7/246G06K9/00G06K9/46G06K9/62
CPCG06T7/246G06T2207/10016G06V20/48G06V20/49G06V20/46G06V10/462G06F18/22
Inventor 李凯刘致金沈礼权安平
Owner SHANGHAI UNIV