基于运动矢量的MPEG视频镜头边界检测

计算机应用 ›› 2012, Vol. 32 ›› Issue (05): 1269-1271.

基于运动矢量的MPEG视频镜头边界检测

王成儒,王微微

燕山大学信息科学与工程学院，河北秦皇岛 066004

收稿日期:2011-10-17 修回日期:2011-12-10 发布日期:2012-05-01 出版日期:2012-05-01
通讯作者: 王微微
作者简介:王成儒（1949-），男，黑龙江宁安人，教授，主要研究方向：数字图像、视频处理、模式识别；王微微（1986-），女，河北定州人，硕士研究生，主要研究方向：视频处理、MPEG编解码。

MPEG video shot boundary detection based on motion vectors

WANG Cheng-ru,WANG weiWei-wei

College of Information science and Engineering, Yanshan University, Qinhuangdao Hebei 066004, China

Received:2011-10-17 Revised:2011-12-10 Online:2012-05-01 Published:2012-05-01
Contact: WANG weiWei-wei

摘要/Abstract

摘要： 首先提取I帧的DC图进行镜头的粗略检测，然后提取P帧的前向运动补偿矢量，利用扩展矢量中值(EVM)滤波对运动矢量进行滤波预处理，并且进一步提取三个运动特征：运动强度值、运动强度差和运动矢量方向直方图绝对差，最后用模糊逻辑对上述三个特征进行综合，推理得出突变、渐变镜头和非镜头，实现镜头的检测。由于不需要对视频完全解压，直接从MPEG压缩码流中提取信息，所以计算复杂度低，提取速度较快。最后通过实验验证了该方法。

关键词: MPEG, 运动矢量, 运动特征, 镜头边界检测, 模糊推理

Abstract: First,DC map of I frame was extracted for rough detection of the shots.And then the forward motion compensation vector of P frame was extracted, and Extended Vector Median (EVM) filtering was used for the preprocessing of motion vector.Finally the characteristics of three sports features,exercise intensity value, exercise intensity difference and the direction of motion vector histogram, absolute difference were calculated. Fuzzy inference was introduced to synthesize these three characteristics and classified shots to abrupt-change,gradual-change and no-change ones.The MPEG video shot boundary detection method do not need to decompress the video fully,and extracts information directly from MPEG compressed bit stream,so it is of low computation complexity and high extration speed,which is verified by the experimental results.

Key words: MPEG, motion vector, sports feature, shot boundary detection, fuzzy inference

中图分类号:

TP391.413

王成儒王微微. 基于运动矢量的MPEG视频镜头边界检测[J]. 计算机应用, 2012, 32(05): 1269-1271.

WANG Cheng-ru WANG weiWei-wei. MPEG video shot boundary detection based on motion vectors[J]. Journal of Computer Applications, 2012, 32(05): 1269-1271.

参考文献

［1］YEO B L, LIU B. A unified approach to temporal segmentation of motion JPEG and MPEG compressed video［C］//Proceedings of the International Conference on Multimedia Computing and Systems.Washington, DC: IEEE Computer Society, 1995: 81-88.

［2］FENG J, LO K T, MEHRPOUR H. A scene change detection algorithm for MPEG video sequence［C］// International Conference on Image Processing. Washington, DC: IEEE Computer Society,1996: 821-824.

［3］WANG XUEJUN, WANG SHIGANG, CHEN HEXIN. A fast algorithm for MPEG video segmentation based on macroblock［C］// Fourth International Conference on Fuzzy Systems and Knowledge Discovery.Washington, DC: IEEE Computer Society，2007,2:28-32.

［4］ZHANG MINGXIN, ZHANG JINLONG, LI HUA,et al. A novel shot segmentation algorithm based on grid-mapping dynamic windows in compressed videos［C］// Proceedings of the 2009 International Conference on Wavelet Analysis and Pattern Recognition. Washington, DC: IEEE Computer Society,2009: 16-21.

［5］LIU H C, ZICK G. Automatic determination of scene change in MPEG compressed video［C］// 1995 IEEE International Symposium on Circuits and Systems.Washington, DC: IEEE Computer Society,1995,1: 764-767.

［6］KOBLA V, DOERMANN D S, ROSENFELD A. Compressed domain video segmentation［EB/OL］. ［2011-10-01］.http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.46.3987&rep=rep1&type=pdf.

［7］薛向阳,肖友能,丁长明. 压缩视频流中主要运动的定性分析［J］.计算机学报,2002,25(12):1428-1433.

［8］薛立勤,张秀娟. 基于运动分析的视频检索方法［J］. 计算机工程与应用, 2008,44(25):152-154.

［9］ASTOLA J, HAAVISTO P, NEUVO Y. Vector median filters［J］. Proceedings of the IEEE,1990,78(4): 678-689.

［10］金红,周源华. 一种基于模糊逻辑的MPEG压缩视频场景转换检测方法［J］. 通信学报, 2000,21(7):57-62.

［11］AMEL A M, ABDESSALEM B A, ABDELLATIF M. Video shot boundary detection using motion activity descriptor［J］. Journal of Telecommunications, 2010,2(1):54-59.

[1]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[2]	曹建荣, 吕俊杰, 武欣莹, 张旭, 杨红娟. 融合运动特征和深度学习的跌倒检测算法[J]. 计算机应用, 2021, 41(2): 583-589.
[3]	郇战, 陈学杰, 吕士云, 耿宏杨. 基于多分类器融合的步态识别方法[J]. 计算机应用, 2019, 39(3): 712-718.
[4]	侯文慧, 王俊峰. 面向云桌面协议的视频区域侦测算法[J]. 计算机应用, 2018, 38(5): 1463-1469.
[5]	付眸, 杨贺昆, 吴唐美, 何润, 冯朝胜, 康胜. 基于Spark Streaming的快速视频转码方法[J]. 计算机应用, 2018, 38(12): 3500-3508.
[6]	苏建军, 慕世友, 杨波, 孙晓斌, 赵海武, 顾晓. 数字视频转码失真分析[J]. 计算机应用, 2017, 37(10): 2899-2902.
[7]	邹洪中, 许悦雷, 马时平, 李帅, 张文达. 基于视皮层V1模型的随机点视频序列运动特征提取[J]. 计算机应用, 2016, 36(6): 1677-1681.
[8]	王松韩永国吴亚东张赛楠. 基于图像主色彩的视频关键帧提取方法[J]. 计算机应用, 2013, 33(09): 2631-2635.
[9]	胡波戴万长肖志坚吴建平胡杰. 均值偏移的多视点视差估计新方法[J]. 计算机应用, 2013, 33(08): 2297-2299.
[10]	段继忠张立毅刘昱孙云山. 基于压缩感知的改进MPEG-2编码方案[J]. 计算机应用, 2012, 32(12): 3411-3414.
[11]	张立东贾磊朱文兴. 基于模糊理论的交通溢流识别算法[J]. 计算机应用, 2012, 32(08): 2378-2384.
[12]	崔宁海刘丽萍. 马尔可夫边缘描述符的图像特征提取算法[J]. 计算机应用, 2012, 32(04): 1104-1107.
[13]	阮若林胡瑞敏陈皓尹黎明. 基于AVS-P2的自适应时空域错误隐藏方法[J]. 计算机应用, 2012, 32(03): 780-782.
[14]	高立春徐叶强. MEPG-7分块加权主颜色及相关反馈的图像检索方法[J]. 计算机应用, 2011, 31(06): 1549-1551.
[15]	杨鹏魏立线杨晓元. 基于运动矢量相位角和卷积码的大容量视频隐写算法[J]. 计算机应用, 2011, 31(04): 960-962.