Check patentability & draft patents in minutes with Patsnap Eureka AI!

Video shot boundary detection method based on progressive bisection and adaptive threshold

A lens boundary detection and adaptive threshold technology, applied in image analysis, image data processing, instruments, etc., can solve the problems of gradient type lens detection, large amount of calculation, etc.

Active Publication Date: 2016-12-28
COMMUNICATION UNIVERSITY OF CHINA
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0014] The progressive dichotomy strategy mainly solves the problem of large amount of calculation in video shot detection and the detection of gradient type shots. It gradually uses the dichotomy method for video shot detection within the scope of the video sequence.

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
  • Video shot boundary detection method based on progressive bisection and adaptive threshold
  • Video shot boundary detection method based on progressive bisection and adaptive threshold
  • Video shot boundary detection method based on progressive bisection and adaptive threshold

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0055] In this embodiment, 20 video segments were randomly selected from the video collection provided by TRECVID2001-2005 for experimentation, including a total of 306321 frames and 2140 shots. The test model is Intel Core i3-2100CPU, memory 2G, operating system is Windows 7, and Matlab is used for programming.

[0056] The scope of gradient lens is 3~30 frames, such as figure 2 As shown, the starting frame of the first detection is 1, the left frame=starting frame+3, and the right frame=starting frame+30. The purpose of setting the left frame and the right frame in this way is to be consistent with the scope of the gradient interval, so that the transition lens can be detected by the shear threshold.

[0057] figure 1 It is a flowchart of the method of the present invention, comprising the following steps:

[0058] Step 1, adaptively adj...

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 belongs to the field of multimedia retrieval and discloses a video shot boundary detection method based on progressive dichotomy and adaptive thresholds. The method includes: firstly, adaptively adjusting the length of a detection unit according to different video types; secondly, dividing a to-be-detected video into a group of sub-videos equal in length, sequentially establishing inter-frame difference histograms, and determining shot detection thresholds of the sub-videos according to the inter-frame difference histograms; and thirdly, performing progressive dichotomy strategy based video shot boundary detection on each sub-video by the aid of the detection thresholds obtained in the second step. By the aid of a progressive dichotomy strategy, amount of computation can be decreased by logarithmic order; dichotomy detection is performed within a video gradual shot change interval, so that the problem of difficulty in gradual shot detection in video shot boundary detection is solved. Thresholds in cut and gradual detection can be separated by an adaptive threshold method, and the length of the detection unit can be adjusted adaptively according to the video types.

Description

technical field [0001] The invention belongs to the field of multimedia retrieval and relates to a video shot boundary detection method based on progressive dichotomy and self-adaptive threshold. Background technique [0002] Current video shot boundary detection algorithms generally adopt a linear calculation method to sequentially calculate the difference between frames and study the change value. Because linear calculation needs to compare the difference between every two adjacent frames of a given video, it takes a long time, so it is not suitable for large-scale video libraries. [0003] In order to solve this problem, in the paper "Detecting Video Shot Boundaries up to 16Times Faster" published by Kien A. Hua on ACM Multimedia 2000 in 2000, it was proposed to use the similarity of context between frames in the shot to ignore some unnecessary comparison calculations. , thus reducing the time complexity of two nonlinear algorithms. The first is rule skipping, that is, ...

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): G06T7/00
Inventor 张鹏洲霍奕王艳峰温宇俊龚隽鹏张弛
Owner COMMUNICATION UNIVERSITY OF CHINA
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com