A Rapid and Effective Method for Shot Boundary Detection

GENG Yu-liang; XU De; FENG Song-he

您当前的位置：

首页 >

文章列表页 >

A Rapid and Effective Method for Shot Boundary Detection

更新时间：2025-07-16

- A Rapid and Effective Method for Shot Boundary Detection
- Acta Electronica Sinica Vol. 34, Issue 12, Pages: 2272-2277(2006)
- 作者机构：
  
  北京交通大学计算机研究所,北京,100044
- 作者简介：
- 基金信息：
- DOI：
  CLC： TN911.73
- Published：2006
- 稿件说明：
移动端阅览
GENG Yu-liang, XU De, FENG Song-he. A Rapid and Effective Method for Shot Boundary Detection[J]. Acta Electronica Sinica, 2006, 34(12): 2272-2277.
DOI：

GENG Yu-liang, XU De, FENG Song-he. A Rapid and Effective Method for Shot Boundary Detection[J]. Acta Electronica Sinica, 2006, 34(12): 2272-2277. DOI：

摘要

本文在分析现有的镜头边界检测方法的基础上

提出了一种层次化镜头边界检测方法.首先我们利用小波变换对信号奇异点的检测能力和对噪声具有较强的鲁棒性

实现了镜头边界的预检测.然后我们通过对候选镜头边界的虚警分析

有效地降低了闪光灯和快速运动对镜头边界检测产生的影响

并实现了镜头突变检测.在渐变类型分类中

我们分别实现了淡入淡出、扫换和溶解等三种重要镜头边界类型的检测.实验结果表明

本文方法能够快速、有效地实现视频镜头边界类型的检测

对运动和光线变化有较强的鲁棒性.

Abstract

A rapid and effective shot boundary detection algorithm is proposed.First

the video sequence is mapped into a temporal evolution curve (TEC) by using the

-norm of HS histogram.Then singularity detection with wavelet is employed to identify the potential shot boundaries in TEC curve.Next then

we utilize intensity of motion intensity and block-based edge direction histogram to distinguish shot boundaries from the false positives caused by rapid motion and complex flashlight scenes.At last

gradual transition is further classified into dissolve

wipe and fade in/fade out.The experimental results compared with other methods achieve satisfying precision and recall of detecting shot boundaries in this algorithm.

关键词

Keywords

references

Views

906

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Algorithm for Shot Boundary Detection Based on Support Vector Machine in Compressed Domain

A Method for Shot Boundary Detection Using Adaptive Threshold

Video Defogging Algorithm Based on Fog Theory

Multiple Classifier Based Walking Pattern Recognizing Algorithm Using Acceleration Signals

Related Author

CAO Jian-rong

CAI An-ni

CHENG Yong

XU De

谢斌

XIE Bin

CAI Zi-xing

GUO Fan

Related Institution

Shandong Jianzhu University

Beijing University of Posts and Telecommunications

Shandong Jianzhu UniversityJinanShandong 250101China

Beijing University of Posts and TelecommunicationsBeijing 100876China

北京交通大学计算机与信息技术学院

⁰