计算机科学 ›› 2016, Vol. 43 ›› Issue (7): 46-50.doi: 10.11896/j.issn.1002-137X.2016.07.007

• 2015年第二十四届全国多媒体学术会议 • 上一篇    下一篇

AVS监控档视频的压缩域摘要研究

赵磊,黄华   

  1. 北京理工大学计算机学院 北京100081,北京理工大学计算机学院 北京100081
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金重点项目(61133008)资助

Compressed Domain Synopsis Research in AVS Surveillance Profile

ZHAO Lei and HUANG Hua   

  • Online:2018-12-01 Published:2018-12-01

摘要: 传统的像素域视频摘要方法需要完全解码视频,计算时间长。因此提出了一种在不解码的前提下直接在压缩域生成AVS格式摘要视频的算法。首先对AVS码流中的运动向量(MV)进行分析,提取前景运动宏块;然后跟踪前景宏块,得到有效的运动目标轨迹;最后提取AVS监控档视频中的背景帧,并将它与运动目标轨迹相结合,生成摘要视频。实验表明,该算法能够在压缩域下有效地生成摘要视频,相比于传统方法具有更快的处理速度。

关键词: 监控视频摘要,压缩域,AVS

Abstract: The traditional methods of video synopsis need completely decoding video in pixel domain which costs too much time.Without decoding,a video synopsis algorithm was proposed for AVS surveillance video in compressed domain.To do so,this algorithm first analyzes the motion vector in AVS bit stream to extract foreground motion macroblocks.Then the valid moving object trajectories are obatained through tracking the foreground macroblocks.At last,the trajectories are recombined with the background frame,which is extracted from the source surveillance video,to gene-rate video synopsis.Comparing with the algorithm in pixel domain,experiments prove that this algorithm achieves similar effect but faster processing speed.

Key words: Surveillance video synopsis,Compressed domain,AVS

[1] Rav-Acha A,Pritch Y,Peleg S.Making a Long Video Short:Dynamic Video Synopsis[C]∥CVPR 2006.2006:435-441
[2] Cullen D,Konrad J,Little T D C.Detection and summarization of salient events in coastal environments[C]∥2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance (AVSS).IEEE,2012:7-12
[3] Yun S,Yun K,Kim S W,et al.Visual surveillance briefing system:Event-based video retrieval and summarization[C]∥2014 11th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS).IEEE,2014:204-209
[4] Liu G,Zhao J.Key frame extraction from MPEG video stream[C]∥2010 Third International Symposium on Information Processing (ISIP).IEEE,2010:423-427
[5] Shi F,Guo X.Keyframe extraction based on kmeas results to adjacent DC images similarity[C]∥2010 2nd International Conference on Signal Processing Systems (ICSPS).IEEE,2010,1:V1-611-V1-613
[6] Yao Hong-ying,Fan Tie-sheng.Technique Research of VideoAbstract Based on Compressed[J].Journal of Anshan Normal University,2004,6(2):67-68(in Chinese) 姚洪英,范铁生.基于压缩域的视频摘要技术的研究[J].鞍山师范学院学报,2004,6(2):67-68
[7] Ouyang Jian-quan.Research on Sports Video Abstraction in the Compressed Domain[D].Beijing:Institute Of Computing Technology Chinese Academy of Sciences,2005(in Chinese) 欧阳建权.压缩域体育视频摘要技术研究[D].北京:中国科学院计算技术研究所,2005
[8] Babu R V,Tom M,Wadekar P.A survey on compressed domain video analysis techniques[J].Multimedia Tools and Applications,2016,75(2):1043-1078
[9] Gao Wen,Wang Qiang,Ma Si-wei.Digital Audio Video Coding Standard of AVS[J].ZTE Technology Journal,2006,2(3):6-9(in Chinese) 高文,王强,马思伟.AVS数字音视频编解码标准[J].中兴通讯技术,2006,12(3):6-9
[10] 张贤国,张莉,梁路宏,等.面向监控应用的 AVS 视频编码标准技术[J].中国安防,2011(5):38-42
[11] 信息技术先进音视频编码:第2部分 视频:GB/T 20090.2-2006[S].2006
[12] Zhang X,Huang T,Tian Y,et al.Background-modeling-basedadaptive prediction for surveillance video coding[J].IEEE Tran-sactions on Image Processing,2014,23(2):769-784
[13] Liang Fan.Technical Features of the AVS Video Standard[J].Digital TV & Digital Video,2006(7):12-15(in Chinese) 梁凡.AVS 视频标准的技术特点[J].电视技术,2006(7):12-15
[14] Hua Shan.Moving Object Segmentation Combinining H.264Compression Domain and Pixel Domain[J].Computer Applications and Software,2014(12):51(in Chinese) 华山.结合 H.264压缩域和像素域运动目标分割[J].计算机应用与软件,2014(12):51
[15] Hess R,Fern A.Improved video registration using non-distinctive local image features[C]∥IEEE Conference on Computer Vision and Pattern Recognition,2007(CVPR’07).IEEE,2007:1-8
[16] Szeliski R.Video mosaics for virtual environments[J].Computer Graphics and Applications,IEEE,1996,16(2):22-30
[17] Papadourakis V,Argyros A.Multiple objects tracking in thepresence of long-term occlusions[J].Computer Vision and Ima-ge Understanding,2010,114(7):835-846
[18] Fisher R B.The PETS04 Surveillance Ground-Truth Data Sets[C]∥PETS.2004:1-5
[19] Pritch Y,Ratovitch S,Hendel A,et al.Clustered Synopsis ofSurveillance Video[C]∥6th IEEE Int.Conf.on Advanced Videoand Signal Based Surveillance (AVSS’09).Genoa,Italy,Sept.2009
[20] Zhong R,Hu R,Wang Z,et al.Fast Synopsis for Moving Objects Using Compressed Video[J].Signal Processing Letters,IEEE,2014,21(7):834-838
[21] Chen Y M,Baji′ I V,Saeedi P.Moving region segmentation from compressed video using global motion estimation and Markov random fields[J].IEEE Transactions on Multimedia,2011,13(3):421-431
[22] http://trace.eas.asu.edu/yuv/hall_monitor/hall_cif.7z
[23] ftp://159.226.42.57/AVS_FTP/incoming/dropbox/VideoTest-Sequences/surveillance/yuv420_w320_h240_1.rar

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!