期刊文献+

音视频相结合的广告检测算法 被引量:2

Robust video and audio based commercials detection
在线阅读 下载PDF
导出
摘要 利用广告最后一帧的特点,提出了一种新颖的音视频相结合的广告检测的方法。在镜头分割的基础上,运用基于SVM的FMP(I有产品信息的图像帧)检测与静音段检测相结合的方法检测广告区域最后一帧。根据检测出来的结果确定广告的开始位置和结束位置,从而确定广告区域。实验结果表明,该方法不仅具有较高的准确率和查全率,而且解决了以往广告检测边缘定位不准的问题。 Taking advantage of the feature on EFC (the Ending Frame in the Commercial), a new method of com- mercial detection is proposed in this paper. This method is based on shots, and applies FMPI (Frames Marked with Product Information) detection using SVM and silence detection to find EFC. According to the EFCs, the method predicts the beginning and ending frames in commercials and then gets the commercials' boundary. Experiments show that the proposed method is not only able to obtain high detection accuracy and recall, but also resolves the problem in how to identify the boundary of the commercial block.
出处 《计算机工程与应用》 CSCD 2012年第22期184-188,共5页 Computer Engineering and Applications
基金 高等学校博士学科点专项科研基金(No.20100071120033) 上海市科委课题(No.10dz1201605)
关键词 有产品信息的图像帧(FMPI) 广告最后一帧(EFC) 支持向量机分类器 广告检测 静音段检测 Frames Marked with Product Information (FMPI) Ending Frame in the Commercial (EFC) Support Vector Machine(SVM) classifier commercials detection silence detection
  • 相关文献

参考文献11

  • 1Covell M, Baluja S, Fink M.Advertisement detection and replacement using acoustic and visual repetition[C]// Proceedings of the 8th IEEE International Workshop on Multimedia Signal Processing, Victoria, BC, Canada, 2006: 461-466.
  • 2Duygulu P,Chen M, Hauptmann A.Comparison and com- bination of two novel commercial detection methods[C]// Proc ICME,2004: 1267-1270.
  • 3Sadlier D,Marlow S,O'Connor N, et al.Automatic tv ad- vertisement detection from MPEG bitstream[J].Pattem Recognition Society, 2002,35 (12) : 2-15.
  • 4Gauch J, Shivadas A.Identication of new commercials using repeated Video sequence detection[C]//Proc ICIP, 2005: 1252-1255.
  • 5Hua X-S, Lu L, Zhang H-J.Robust learning-based TV commercial deteetion[C]//Proc ICME,Amsterdam, Nether- lands, 2005: 149-152.
  • 6Cortes C, Vapnik V.Support-vector networks[J].Machine Learning, 1995: 273-297.
  • 7Zabih R, Miller J, Mai K.A feature-based algorithm for detecting and classifying scene breaks[C]//Proc of ACM Multimedia 95, San Francisco, CA, 1995:189-200.
  • 8秦剑鹏,符茂胜,涂铮铮,罗斌.基于颜色直方图变化率的视频镜头检测[J].计算机应用与软件,2011,28(4):17-20. 被引量:12
  • 9Duan L Y,Wang J,Zheng Y, et al.Segmentation, catego- rization, and identifcation of commercials from TV streams using multimodal analysis[C]//Proceedings of ACM Multimedia, 2006: 201-210.
  • 10Manjunath B S, Ma W Y.Texture features for brows- ing and retrieval of image data[J].IEEE Trans on PA- MI, 1996,18(8) :837-842.

二级参考文献8

共引文献11

同被引文献12

  • 1Coskun B,Sankur B, etal.Spatio-temporaltransform-based video hashing. [J]IeeeTrans- actions on Multimedia, 8(6):1190-1208, 2006.
  • 2BhatD and Nayar S. Ordinal measures for imagecorres- pondence. [J]ieee Transactions on PattemAnalysis and Machine Intelligence, 20(4):415-423,1998.
  • 3Mohan R. Video sequence matching. In Int.Conference on Audio, [c]Speech and SignalProcessing, 1998.
  • 4JURADOF, SAENZJ R. Comparison between discrete STFT and wavelets for the analysis of power quality events. [J]Elect. Power Syst. Res. vol. 62, no. 3,pp. 183-190.2002.
  • 5SCHAPIRER, SINGERY. Improved boosting algorithms using confidence-rated predictions. [J]Machine Learning, 37(3), 1999.
  • 6VIOLAP, JONES M. Rapid object detection using a boosted cascade of simple features[C]. Proceedings of Computer Vision and Pattern Recognition, 2001.
  • 7GIONISA, INDYKP, MOTWANIR. Similarity search in high dimensions via hashing[C]. In Proceedings of Inter- national Conference on Very Large Databases, 1999.
  • 8INDYKP, MOTWANIR. Approximate nearest neigh- bor-towards removing the curse of dimensionality[C]. Proceedings of Symposium on Theory of Computing, 1998.
  • 9ZIBERT J, et al. The COST278 Broadcast News Seg- mentation and Speaker Clustering Evaluation - Overview Methodology, [c]Systems, Results. Interspeech 2005.
  • 10Francisco Jurado,José R. Saenz.Comparison between discrete STFT and wavelets for the analysis of power quality events[J].Electric Power Systems Research.2002(3)

引证文献2

二级引证文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部