视频检索中图像信息量度量

doi:10.11959/j.issn.1000-436x.2016033

通信学报 ›› 2016, Vol. 37 ›› Issue (2): 81-88.doi: 10.11959/j.issn.1000-436x.2016033

视频检索中图像信息量度量

袁庆升^1,²,张冬明^3,⁴,靳国庆^3,⁴,刘菲^3,⁴,包秀国^1,²

¹ 中国科学院信息工程研究所，北京 100193
² 国家计算机网络应急技术处理协调中心，北京 100029
³ 中国科学院智能信息处理重点实验室，北京 100190
⁴ 中国科学院计算技术研究所，北京 100190

出版日期:2016-02-26 发布日期:2016-02-26
基金资助:
国家自然科学基金资助项目;国家自然科学基金资助项目;国家自然科学基金资助项目;国家高科技研究发展计划（“863”计划）基金资助项目

Image information measurement for video retrieval

Qing-sheng YUAN^1,²,Dong-ming ZHANG^3,⁴,Guo-qing JIN^3,⁴,Fei LIU^3,⁴,Xiu-guo BAO^1,²

¹ Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100193,China
² National Computer Network Emergency Response Technical Team/Coordination Center of China,Beijing 100029, China
³ Key Lab of Intelligent Information Processing, Chinese Academy of Sciences, Beijing 100190, China
⁴ Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190,China

Online:2016-02-26 Published:2016-02-26
Supported by:
The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National Natural Science Foundation of China;The National High Technology Research and Development Program of China (863 Program)

摘要/Abstract

摘要：

综合考虑信息量度量的速度、性能要求，提出了相适应的显著图、多特征融合模型；基于区域划分融入空间关系，提出了分块信息熵的图像信息量度量方法（SEII）；构建了信息量度量的标注数据集，并设计了性能验证方法。实验结果表明该度量方法符合人眼视觉的评价结果。度量方法在实际视频检索系统中进行对比应用测试，测试表明mAP提高4.4%，检索速度提高1.5倍。

关键词: 视频检索, 关键帧选择, 图像信息量, 显著区域, 多特征融合

Abstract:

To meet the speed and performance requirements, Sub-region entropy based image information measurement (SEII)method was proposed, which integrates the salie region detection, region division and features fusion. And, performance evaluation method was designed and many experiments were carried out, proving SEII coordinates with human vision evaluation.Also,SEII is evaluated in a real video retrieval system,which shows increase about 4.4% of mAP with 1.5 times speedup.

Key words: video retrieval, key frame selection, image information, salient region, features fusion

袁庆升,张冬明,靳国庆,刘菲,包秀国. 视频检索中图像信息量度量[J]. 通信学报, 2016, 37(2): 81-88.

Qing-sheng YUAN,Dong-ming ZHANG,Guo-qing JIN,Fei LIU,Xiu-guo BAO. Image information measurement for video retrieval[J]. Journal on Communications, 2016, 37(2): 81-88.

图/表 11

图1

图2

图3

图4

图5

表1

图6

表2

表3

图7

图8

参考文献 24

[1]	SHAHRARAY B , GIBBON D C . Automatic generation of pictorial transcripts of video programs[C]// Proc SPIE. c1995: 512-518.
[2]	WOLF W . Key frame selection by motion analysis[C]// Acoustics, Speech, and Signal Processing, International Conference. c1996: 1228-1231.
[3]	章毓晋 . 基于内容的视觉信息检索[M]. 北京: 科学出版社, 2003. ZANG Y J , Content based video information retrieval[M]. Beijing: Science Press, 2003.
[4]	SAAD M A , BOVIK A C , CHARRIER C . Blind image quality assessment: a natural scene statistics approach in the DCT domain[J]. IEEE Transactions on Image Processing, 2012, 21(8):3339-3352.
[5]	KOCH C , ULLMAN S . Shifts in selective visual attention: towards the underlying neural circuitry[C]// Matters of Intelligence. c1987:115-141.
[6]	ITTI L , KOCH C , NIEBUR E . A model of saliency-based visual attention for rapid scene analysis[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1998, 20(11):1254-1259.
[7]	MA Y F , ZHANG H J . Contrast-based image attention analysis by using fuzzy growing[C]// The eleventh ACM international conference on Multimedia. c2003: 374-381.
[8]	ZHAI Y , SHAH M . Visual attention detection in video sequences using spatiotemporal cues[C]// 14th annual ACM international conference on Multimedia. c2006: 815-824.
[9]	CHENG M M , ZHANG G X , MITRA N J , et al. Global contrast based salient region detection[C]// Computer Vision and Pattern Recognition(CVPR). c2011:409-416.
[10]	HOU X , HAREL J , KOCH C . Image signature: highlighting sparse salient regions[J]. IEEE Transactions on, Pattern Analysis and Ma chine Intelligence, 2012, 34(1): 194-201.
[11]	MAI L , NIU Y , LIU F . Saliency aggregation: a data-driven approach[C]// IEEE Conference. Computer Vision and Pattern Recognition(CVPR). c2013: 1131-1138.
[12]	BHATTACHARYYA B A . On a measure of divergence between two statistical populations defined by probability distributions[J]. Bulletin of the Calcutta Mathematical Society, 1943, 35: 99-110.
[13]	PENG J , QING X L . Keyframe-based video summary using visual attention clues[J]. IEEE MultiMedia, 2010, 17(2): 64-73.
[14]	LAI J L , YI Y . Key frame extraction based on visual attention model[J]. Journal of Visual Communication and Image Representation, 2012, 23(1): 114-125.
[15]	HUA X S , ZHANG H J . An attention-based decision fusion scheme for multimedia information retrieval[C]// Advances in Multimedia Information Processing-PCM 2004. Springer Berlin Heidelberg, c2005: 1001-1010.
[16]	MA Y F , HUA X S , LU L , et al. A generic framework of user attention model and its application in video summarization[J] EE Transactions on Multimedia, 2005, 7(5): 907-919.
[17]	HU Y , XIE X , MA W Y , et al. Salient region detection using weighted feature maps based on the human visual attention model[C]// Advances in Multimedia Information Processing-PCM 2004. Springer Berlin Heidelberg, c2005: 993-1000.
[18]	ARMANFARD Z , BAHMANI H , NASRABADI A M . A novel feature fusion technique in saliency-based visual attention[C]// Advances in Computational Tools for Engineering Applications, c2009: 230-233.
[19]	LAI J L , YI Y . Key frame extraction based on visual attention model[J] Journal of Visual Communication and Image Representation, 2012, 23(1): 114-125.
[20]	EJAZ N , MEHMOOD I , WOOK B S . Efficient visual attention based framework for extracting key frames from videos[J] Signal Processing: Image Communication, 2013, 28(1): 34-44.
[21]	SMOLA A J , SCH?LKOPF B . A tutorial on support vector regression[J]. Statistics and Computing, 2004, 14(3): 199-222.
[22]	PARK J S , CHEN M S , YU P S . Using a hash-based method with transaction trimming for mining association rules[J]. IEEE Transactions on Knowledge and Data Engineering, 1997, 9(5): 813-825.
[23]	MITTAL A , MOORTHY A K , BOVIK A C . No-reference image quality assessment in the spatial domain[J]. IEEE Transact ns on Image Processing, 2012, 21(12): 1695-4708.
[24]	SHEIKH H R , BOVIK A C . Image information and visual quality[J]. IEEE Transactions on Image Processing, 2006, 15(2): 430-444.

级别	绝对尺度	相对尺度	得分
1	很好	该组最好	80～100
2	较好	高于该组的平均水平	60～79
3	一般	该组平均水平	40～59
4	较差	低于该组平均水平	20～39
5	很差	该组中最差	0～19

编号	训练图片数量	测试图片数量	SROCC评价值
1	372	100	0.807/0.797
2	377	95	0.895/0.887
3	377	95	0.859/0.862
4	382	90	0.901/0.900
5	382	90	0.856/0.832
6	382	90	0.863/0.815
7	382	90	0.862/0.816
8	377	95	0.901/0.903
9	377	95	0.887/0.853
10	372	100	0.821/0.831
	10次结果的均值		0.865/0.850
	10次结果的标准差		0.032/0.038

编号	节目名称	编号	节目名称
A	体育“高尔夫”	G	纪录片“我是普京”
B	人物访谈“刘欢”	H	综艺“快乐大本营”
C	人物访谈“刘嘉玲”	I	综艺“今夜有戏”
D	新闻节目“VOA奥运新闻”	J	综艺“中国达人秀”
E	新闻节目“北京您早”	K	动画“猫和老鼠”
F	新闻节目“Student CNN”	—	—

视频检索中图像信息量度量

Image information measurement for video retrieval

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 24

相关文章 1

Metrics

推荐阅读 0