融合视音频特征的视频广告表现力识别
|
摘要
视频广告的表现力直接影响着商业品牌的树立和商品的营销,但是视频广告表现力的识别尚不能满足人们的需求。为了自动、量化的让计算机识别广告视频的表现力,本文提出了一种直接利用视音频特征对是视频广告表现力进行识别的算法,该算法融合BoW、GIST、颜色矩特征、颜色直方图和音频特征进行识别,实验结果表明了融合视音频特征可以较好的对视频广告表现力进行识别,并且融合多种特征进行识别的准确率要高于单独使用一种特征。
The power of the video advertisement determined the establishment of commercial brands and the sales of goods directly. However,the recognition of the power of the video advertisement has been far away from satisfaction. In order to recognize the power of the video advertisement via computer automatically and quantitatively,this paper proposed an algorithm which recognized the power of the video advertisement directly by fusing video's visual and audio features. These features contained Bow,GIST,Color moment,Color histogram and audio feature. The experimental results demonstrated the fusion of visual and audio features can recognized the power of the video advertisement well,and also the fusion of features outperformed single feature.
The power of the video advertisement determined the establishment of commercial brands and the sales of goods directly. However,the recognition of the power of the video advertisement has been far away from satisfaction. In order to recognize the power of the video advertisement via computer automatically and quantitatively,this paper proposed an algorithm which recognized the power of the video advertisement directly by fusing video's visual and audio features. These features contained Bow,GIST,Color moment,Color histogram and audio feature. The experimental results demonstrated the fusion of visual and audio features can recognized the power of the video advertisement well,and also the fusion of features outperformed single feature.
引文
[1] X. Ji,J. Han,X. Hu,K. Li,F. Deng,J. Fang,L.Guo,and T. Liu,“Retrieving video shots in semantic brain imaging space using manifold-ranking,” in Image Processing(ICIP),2011 18th IEEE International Conference on,2011:3633-3636.
[2] J. Han,X. Ji,X. Hu,D. Zhu,K. Li,X. Jiang,G.Cui,L. Guo,and T. Liu,“Representing and Retrieving Video Shots in Human-Centric Brain Imaging Space,”IEEE Trans. Image Process.,2013,22(7):2723-2736.
[3]朱方,吴莉,陈飞凌,袁卫忠.智能视频监控终端在物联网中的应用和发展研究.中国电子科学研究院学报,2011,6(6):561-566.
[4] F. Li,P. Perona.“A bayesian hierarchical model for learning natural scene categories,”IEEE Conference on Computer Vision and Pattern Recognition, 2005,2:524-531.
[5] D. G. Lowe.“Object recognition from local scale-invariant features,”The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999,2:1150-1157.
[6] A. Oliva and A. Torralba,“Modeling the shape of the scene:A holistic representation of the spatial envelope,”Int. J. Comput. Vis.,2001,42(3):145-175.
[7] A. Oliva and A. Torralba,“Building the gist of a scene:The role of global image features in recognition,”Prog.Brain Res.,2006,155:23-36.
[8] O. Lartillot and P. Toiviainen,“A matlab toolbox for musical feature extraction from audio,” in Proc. Int’l Conf. on Digital Audio Effects,2007:237-244.
[9] C.-C. Chang and C.-J. Lin,“LIBSVM:a library for support vector machines,” ACM Trans. Intell. Syst.Technol.,2011,2(3):27.
[2] J. Han,X. Ji,X. Hu,D. Zhu,K. Li,X. Jiang,G.Cui,L. Guo,and T. Liu,“Representing and Retrieving Video Shots in Human-Centric Brain Imaging Space,”IEEE Trans. Image Process.,2013,22(7):2723-2736.
[3]朱方,吴莉,陈飞凌,袁卫忠.智能视频监控终端在物联网中的应用和发展研究.中国电子科学研究院学报,2011,6(6):561-566.
[4] F. Li,P. Perona.“A bayesian hierarchical model for learning natural scene categories,”IEEE Conference on Computer Vision and Pattern Recognition, 2005,2:524-531.
[5] D. G. Lowe.“Object recognition from local scale-invariant features,”The Proceedings of the Seventh IEEE International Conference on Computer Vision, 1999,2:1150-1157.
[6] A. Oliva and A. Torralba,“Modeling the shape of the scene:A holistic representation of the spatial envelope,”Int. J. Comput. Vis.,2001,42(3):145-175.
[7] A. Oliva and A. Torralba,“Building the gist of a scene:The role of global image features in recognition,”Prog.Brain Res.,2006,155:23-36.
[8] O. Lartillot and P. Toiviainen,“A matlab toolbox for musical feature extraction from audio,” in Proc. Int’l Conf. on Digital Audio Effects,2007:237-244.
[9] C.-C. Chang and C.-J. Lin,“LIBSVM:a library for support vector machines,” ACM Trans. Intell. Syst.Technol.,2011,2(3):27.