微信服务号

微信订阅号

2025-4-24- 8
Home > Archive>Volume 21, Issue 11, 2010 >2971-2984
PDF HTML XML Export Cite reminder
Near Duplicate Keyframes Identifying and Correlation Analyzing of News Video Stories
Author:
Affiliation:

  • Article
    • | |
  • Metrics
    • |
  • Reference [34]
    • |
  • Related [20]
    • |
  • Cited by [1]
    • | |
  • Comments
    Abstract:

    The quadratic complexity required for measuring the similarity of news stories makes it intractable in large-volume news videos. In this paper, an effective method is proposed to find a way to solve the problems. First, small partitions from the corpus and prune local keypoint are selected to accelerate matching speed. Then, a hierarchical approach for identifying near duplicate keyframes is proposed. Furthermore, this paper presents a method to identity correlation of stories based on near duplicate keyframes and transitivity of correlations. Finally, a method for calculating the similarity of news stories is presented based on near duplicate keyframes. Experimental results show that this approach greatly speeds up the matching speed and improves the matching accuracy. The similarity of stories is closer to users sensory.

    Reference
    [1] Li BL, Yu SW. Research on topic detection and tracking. Computer Engineering and Applications, 2003,39(17):7?10 (in Chinese with English abstract).
    [2] Jia ZY, He Q, Zhang HJ, Li JY, Shi ZZ. A news event detection and tracking algorithm based on dynamic evolution model. Journal of Computer Research and Development, 2004,41(17):1273?1280 (in Chinese with English abstract).
    [3] Ide I, Mo H, Katayama N. Threading news video topics. In: Proc. of the 5th ACM SIGMM Int’l Workshop on Multimedia Information Retrieval (MIR 2003). ACM, 2003. 239?246.
    [4] Ide I, Mo H, Katayama N, Satoh S. Exploiting topic thread structures in a news video archive for the semi-automatic generation of video summaries. In: Proc. of the IEEE Int’l Conf. on Multimedia and Expo (ICME 2006). Toronto: IEEE, 2006. 1473?1476.
    [5] Allan J, Wade C, Bolivar A. Retrieval and novelty detection at the sentence level. In: Proc. of the 26th Annual Int’l ACM SIGIR Conf. on Research and Development in Information Retrieval (SIGIR 2003). Toronto: ACM, 2003. 314?321.
    [6] Peng YX, Ngo CW, Dong QJ, Guo ZM, Xiao JG. An approach for video retrieval by video clip. Journal of Software, 2003,14(8): 1409?1417 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/14/1409.htm
    [7] Lin T, Zhang HJ, Feng JF, Shi QY. Shot content analysis for video retrieval applications. Journal of Software, 2002,13(8): 1577?1585 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/13/1577.pdf
    [8] Zhang DQ, Chang SF. Detecting image near-duplicate by stochastic attributed relational graph matching with learning. In: Proc. of the 12th Annual ACM Int’l Conf. on Multimedia (MM 2004). New York: ACM, 2004. 877?884.
    [9] Chang SF, Hsu W, Kennedy L, Xie LX, Yanagawa A, Zavesky E, Zhang DQ. Columbia university TRECVID-2005 video search and high-level feature extraction. In: Proc. of the NIST TRECVID Workshop. 2005.
    [10] Chua TS, Neo SY, Zheng YT, Goh HK, Tang S, Xiao Y, Zhao M. Trecvid 2006 by NUS-I2R. In: Proc. of the NIST TRECVID Workshop. 2006.
    [11] Hsu WH, Chang SF. Topic tracking across broadcast news videos with visual duplicates and semantic concepts. In: Proc. of the IEEE Int’l Conf. on Image Processing (ICIP 2006). Atlanta: IEEE, 2006. 141?144.
    [12] Duygulu P, Pan JY, Forsyth DA. Towards auto-documentary: Tracking the evolution of news stories. In: Proc. of the 12th Annual ACM Int’l Conf. on Multimedia (MM 2004). New York: ACM, 2004. 820?827.
    [13] Lowe DG. Distinctive image features from scale-invariant keypoints. Int’l Journal of Computer Vision, 2004,60(2):90?110.
    [14] Ngo CW, Zhao WL, Jiang YG. Fast tracking of near-duplicate keyframes in broadcast domain with transitivity propagation. In: Proc. of the 14th Annual ACM Int’l Conf. on Multimedia (MM 2006). Santa Barbara: ACM, 2006. 845?854.
    [15] Zhao WL, Ngo CW, Tan HK, Wu X. Near-Duplicate keyframe identification with interest point matching and pattern learning. IEEE Trans. on Multimedia, 2007,9(5):1037?1048. [doi: 10.1109/TMM.2007.898928]
    [16] Zhao WL, Jiang YG, Ngo CW. Keyframe retrieval by keypoints: Can point-to-point matching help? In: Proc. of the Int’l Conf. on Image and Video Retrieval (CIVR 2006). Tempe: Springer-Verlag, 2006. 72?81.
    [17] Zheng YT, Neo SY, Chua TS, Tian Q. Fast near-duplicate keyframe detection in large-scale video corpus for video search. In: Proc. of the Int’l Workshop on Advanced Image Technology (IWAIT 2007). Bangkok, 2007.
    [18] Zheng YT, Neo SY, Chua TS, Tian Q. The use of temporal, semantic and visual partitioning model for efficient near duplicate detection in large scale news corpus. In: Proc. of the Int’l Conf. on Image and Video Retrieval (CIVR2007). Amsterdam: ACM, 2007. 409?416.
    [19] Lin J. Event detection and tracking in news video [Ph.D. Thesis]. Hangzhou: Zhejiang University, 2007 (in Chinese with English abstract).
    [20] Wen J, Wu LD, Zeng P, Luan XD, Xie YX. News video story segmentation method using fusion of audio-visual features. In: Proc. of the SPIE 5th Int’l Symp. on Multispectral Image Processing and Pattern Recognition. Wuhan: SPIE, 2007. 67904G1?67904G6.
    [21] Xie YX, Luan XD, Wu LD, Lao SY. A decompression-based shot detection method. Systems Engineering and Electronics, 2003, 25(8):1028?1031 (in Chinese with English abstract).
    [22] Wen J, Zeng P, Luan XD, Wu LD. Adaptive method to detect anchorperson shot in news video. Computer Engineering, 2008,34(3): 244?246 (in Chinese with English abstract).
    [23] Zhou XZ, Shi YC, Wang T. TV symbol recognition based on weighted Hu invariant moments in HSV colour space. Journal of Nanjing University of Science and Technology, 2005,29(3):363?367 (in Chinese with English abstract).
    [24] http://www.ee.columbia.edu/ln/dvmm/researchProjects/FeatureExtraction/NearDuplicateByParts/INDDetection.html
    [25] Hauptmann A, Yan R, Lin WH. How many highlevel concepts will fill the semantic gap in news video retrieval? In: Proc. of the 6th ACM Int’l Conf. on Image and Video Retrieval (CIVR 2007). Amsterdam: ACM, 2007. 627?634.
    [26] Christel MG. Establishing the utility of non-text search for news video retrieval with real world users. In: Proc. of the 15th Int’l Conf. on Multimedia (MM 2007). Augsburg: ACM, 2007. 707?716.
    附中文参考文献: [1] 李保利,俞士汶.话题识别与跟踪研究.计算机工程与应用,2003,39(17):7?10.
    [2] 贾自艳,何清,张海俊,李嘉佑,史忠植.一种基于动态进化模型的事件探测和追踪算法.计算机研究与发展,2004,41(17): 1273?1280.
    [6] 彭宇新,Ngo CW,董庆杰,郭宗明,肖建国.一种通过视频片段进行视频检索的方法.软件学报,2003,14(8):1409?1417. http://www.jos.org.cn/1000-9825/14/1409.htm
    [7] 林通,张宏江,封举富,石青云.镜头内容分析及其在视频检索中的应用.软件学报,2002,13(8):1577?1585. http://www.jos.org.cn/ 1000-9825/13/1577.pdf
    [19] 凌坚.新闻视频主题识别与跟踪的研究[博士学位论文].杭州:浙江大学,2007.
    [21] 谢毓湘,栾悉道,吴玲达,老松杨.一种基于解压的镜头探测方法.系统工程与电子技术,2003,25(8):1028?1031.
    [22] 文军,曾璞,栾悉道,吴玲达.自适应的新闻视频播音员镜头探测方法.计算机工程,2008,34(3):244?246.
    [23] 周献忠,史迎春,王韬.基于HSV颜色空间加权Hu不变矩的台标识别.南京理工大学学报,2005,29(3):363?367.
    Comments
    Comments
    分享到微博
    Submit
Get Citation

文军,吴玲达,曾璞,栾悉道.新闻视频相似关键帧识别与故事单元关联分析研究.软件学报,2010,21(11):2971-2984

Copy
Share
Article Metrics
  • Abstract:4336
  • PDF: 6571
  • HTML: 0
  • Cited by: 0
History
  • Received:June 16,2008
  • Revised:April 27,2009
Links:Institute of Software, CASChina Computer FederationCASNSFC
You are the first2037973Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address：4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code：100190
Phone：010-62562563 Fax：010-62562533 Email：jos@iscas.ac.cn
Technical Support：Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063