一种新的基于背景色度的镜头边界探测算法

应用科学学报 ›› 2004, Vol. 22 ›› Issue (3): 318-321.

一种新的基于背景色度的镜头边界探测算法

雷震, 吴玲达, 老松杨

国防科技大学多媒体研究开发中心湖南长沙 410073

收稿日期:2003-06-09 修回日期:2003-12-16 出版日期:2004-09-30 发布日期:2004-09-30
作者简介:雷震(1976-),男,河南项城人,博士生;吴玲达(1962-),女,湖北武汉人,教授,博导.
基金资助:
国家863项目;十五国防预研项目

A Novel Background-Hue-Based Shot Boundary Detection Algorithm

LEI Zhen, WU Ling-da, LAO Song-yang

Multimedia Research and Development Center, National University of Defense Technology, Changsha 410073, China

Received:2003-06-09 Revised:2003-12-16 Online:2004-09-30 Published:2004-09-30

摘要/Abstract

摘要： 提出了一种基于背景颜色不变量的改进双直方图算法进行镜头边界探测.该方法首先采用连续帧间差的4次统计量假设检验分离出背景区域,然后选用L^*a^*b^*彩色模型来计算背景区域的色度,再利用改进的双直方图算法进行镜头边界探测.本方法所需计算量较小,且可保证较高的精度.实验结果表明,该算法的分割效果明显优于其他几种算法,更加准确高效.

关键词: 镜头边界探测, 突变模型和闪光灯模型探测器, 色度直方图, 双直方图法

Abstract: A background-color-invariable-based improved twin-histogram algorithm is presented to detect shot boundary in this paper. Firstly, a fourth-orders statistic hypothesis testing in inter-frame difference is used to separate background from a general video sequence. Secondly, (L^*a^*b^*) color model is used to calculate the hue in the background areas. Lastly, the improved twin-histogram algorithm is used to detect shot boundary. This method needs fewer calculations and has a higher precision ratio. The experimental results show that the method is more accurate and effective in shot detection than other algorithms.

Key words: shot boundary detection, hue histogram, twin-histogram algorithm, cut model and flashlight model detector

中图分类号:

TP311

雷震, 吴玲达, 老松杨. 一种新的基于背景色度的镜头边界探测算法[J]. 应用科学学报, 2004, 22(3): 318-321.

LEI Zhen, WU Ling-da, LAO Song-yang. A Novel Background-Hue-Based Shot Boundary Detection Algorithm[J]. Journal of Applied Sciences, 2004, 22(3): 318-321.