[1]闫乐林,温向明,郑伟,等.基于未确知测度的视频情感内容识别[J].东南大学学报(自然科学版),2011,41(3):473-477.[doi:10.3969/j.issn.1001-0505.2011.03.008]
 Yan Lelin,Wen Xiangming,Zheng Wei,et al.Video affective content recognition based on unascertained measure[J].Journal of Southeast University (Natural Science Edition),2011,41(3):473-477.[doi:10.3969/j.issn.1001-0505.2011.03.008]
点击复制

基于未确知测度的视频情感内容识别()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
41
期数:
2011年第3期
页码:
473-477
栏目:
计算机科学与工程
出版日期:
2011-05-20

文章信息/Info

Title:
Video affective content recognition based on unascertained measure
作者:
闫乐林温向明郑伟张良
(北京邮电大学信息与通信工程学院, 北京 100876)
Author(s):
Yan LelinWen XiangmingZheng WeiZhang Liang
(School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China)
关键词:
视频检索未确知测度情感类型低层视频特征
Keywords:
video retrieval unascertained measure emotion type low-level video feature
分类号:
TP391.4
DOI:
10.3969/j.issn.1001-0505.2011.03.008
摘要:
为有效识别视频情感的内容, 基于未确知数学理论, 建立了视频低层特征和高层认知情感之间的联系, 提出了一种基于未确知测度的新算法.首先,选取能反映情感变化的场景亮度、镜头切变率和色调效能作为视频情感低层特征,介绍了每种情感特征的数据提取方法, 并由此构建了视频情感特征向量. 其次, 构造了视频场景的未确知对象空间和指标空间, 并给出了量化用的场景亮度、镜头切变率和色调效能未确知测度函数, 建立了未确知测度矩阵. 最后, 采用信息熵确定3个情感特征的权值, 用置信度识别准则对视频场景的情感类型进行判定. 实验结果验证了该方法的可行性和有效性.
Abstract:
Based on unascertained measure, a novel algorithm for affective content recognition of the video is proposed by establishing the relationship between low-level video features and high-level cognitive emotion about video scene. First, the scene brightness, shot cut rate and color efficacy in a video scene are selected as the low-level video features for their special characteristics that can be used to better distinguish different types of human emotion. Meanwhile, the methods of data extraction from each emotion feature are presented, and the video emotion feature vector is created accordingly. Secondly, after constructing the unascertained object space and the index space, three unascertained measure functions are respectively formed to quantify the video scene brightness, shot cut rate and color efficacy, and then the unascertained measure emotion matrix is built . Finally, the information entropy is applied to determine the weight of each emotion feature, and the emotion type of the video scene is obtained according to credible degree criteria. The experimental results verify the feasibility and effectiveness of the proposed algorithm.

参考文献/References:

[1] Zhang Shiliang,Tian Qi,Jiang Shuqiang,et al.Affective MTV analysis based on arousal and valence features[C]//Proceedings of the 2008 IEEE International Conference on Multimedia and Expo.Hannover,Germany,2008:1369-1372.
[2] Sun Kai,Yu Junqing.Video affective content representation and recognition using video affective tree and hidden Markov models [C]//Proceedings of the 2007 International Conference on Affective Computing and Intelligent Interaction.Lisbon,Portugal,2007:594-605.
[3] 刘开第,吴和琴,王念鹏,等.未确知数学[M].武汉:华中理工大学出版社,1997.
[4] 林新棋.基于模糊理论的电影情感内容识别[D].北京:北京邮电大学信息与通信工程学院,2009.
[5] 戴小文,蔡志平,钟桂英.基于小波变换及熵的视频镜头分割检测方法[J].西南交通大学学报,2008,43(3):314-318.
  Dai Xiaowen,Cai Zhiping,Zhong Guiying.Video shot detection method based on wavelet transform and wavelet entropy [J].Journal of Southwest Jiaotong University,2008,43(3):314-318.(in Chinese)
[6] 王学军,丁红涛,陈贺新.一种基于镜头聚类的视频场景分割方法[J].中国图象图形学报,2007,12(12):2127-2131.
  Wang Xuejun,Ding Hongtao,Chen Hexin.A shot clustering based approach for scene segmentation [J].Journal of Image and Graphics,2007,12(12):2127-2131.(in Chinese)
[7] Lin Xinqi,Wen Xiangming,Lu Zhaoming,et al.Video affective content recognition based on film grammars and fuzzy evaluation[C]//Proceedings of the 2008 International Conference on Multimedia and Information Technology.Three Gorges,China,2008:264-267.
[8] 刘开第,曹庆奎,庞彦军.基于未确知集合的故障诊断方法[J].自动化学报,2004,30(5):747-756.
  Liu Kaidi,Cao Qingkui,Pang Yanjun.Method of fault diagnosis based on unascertained set[J].Acta Automatica Sinica,2004,30(5):747-756.(in Chinese)
[9] 雅格洛姆A M,雅格洛姆N M.概率与信息[M].吴茂森,译.上海:上海科学技术出版社,1964:29-88.
[10] Xu Min,Chia Liang-Tien,Jin Jesse.Affective content analysis in comedy and horror videos by audio emotional event detection[C]//Proceedings of the 2005 IEEE International Conference on Multimedia and Expo.Amsterdam,The Netherlands,2005:622-625.
[11] Wang Hee Lin,Cheong Loong-Fah.Affective understanding in film [J].IEEE Transactions on Circuits and Systems for Video Technology,2006,16(6):689-704.
[12] Lefèvre Sébastien,Vincent Nicole.Efficient and robust shot change detection [J].Journal of Real-Time Image Processing,2007,2(1):23-34.

备注/Memo

备注/Memo:
作者简介:闫乐林(1975—),男,博士生,讲师;温向明(联系人),男,博士,教授,博士生导师,xiangmw@bupt.edu.cn.
基金项目:国家自然科学基金资助项目(60872050).
引文格式: 闫乐林,温向明,郑伟,等.基于未确知测度的视频情感内容识别[J].东南大学学报:自然科学版,2011,41(3):473-477.[doi:10.3969/j.issn.1001-0505.2011.03.008]
更新日期/Last Update: 2011-05-20