基于多特征融合的视频检索算法

doi:10.16180/j.cnki.issn1007-7820.2019.05.009

电子科技 ›› 2019, Vol. 32 ›› Issue (5): 44-49.doi: 10.16180/j.cnki.issn1007-7820.2019.05.009

基于多特征融合的视频检索算法

侯严明,李菲菲,陈虬

上海理工大学光电信息与计算机工程学院,上海 200093

收稿日期:2018-05-17 出版日期:2019-05-15 发布日期:2019-05-06
作者简介:侯严明(1993-),男,硕士研究生。研究方向:计算机视觉与模式识别。|李菲菲(1970-),女,博士,教授。研究方向:多媒体信息处理、图像处理与模式识别、信息检索等。|陈虬(1972-),男,博士,教授。研究方向:图像处理与模式识别、计算机视觉、信息检索等。
基金资助:
上海市高校特聘教授东方学者岗位计划(ES2015XX)

Video Retrieval Algorithm Based on Multiple Feature Fusion

HOU Yanming,LI Feifei,CHEN Qiu

School of Optical Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China

Received:2018-05-17 Online:2019-05-15 Published:2019-05-06
Supported by:
The Program for Professor of Special Appointment Eastern Scholar at Shanghai Institutions of Higher Learning(ES2015XX)

摘要/Abstract

摘要：

随着视频等多媒体数据呈指数式迅猛增长,高效快速的视频检索算法引起越来越多的重视。传统的图像特征如颜色直方图以及尺度不变特征变换等对视频拷贝检测中检索速度以及检测精度等问题无法达到很好的效果,因此文中提出一种多特征融合的视频检索方法。该方法利用前后两帧的时空特征进行基于滑动窗口的时间对齐算法,以达到减少检索的范围和提高检索速度的目的。该算法对关键帧进行灰度序列特征、颜色相关图特征以及SIFT局部特征提取,然后融合全局特征和局部特征两者的优势,从而提高检测精度。实验结果表明,该方法可达到较好的视频检索精度。

关键词: 视频检索, 滑动窗口, 多特征融合, 颜色自相相图, 时空特征, 关键帧

Abstract:

Due to the exponential growth of video data on the World Wide Web, efficient and fast video retrieval algorithm has attracted a lot of attentions. Because the traditional video image features, such as color histogram and scale invariant feature transform could not obtain promising results on the retrieval speed and detection precision in video copy detection, a video retrieval algorithm using multiple feature fusion was proposed in this paper. Using the temporal and spatial characteristics of the two frames before and after, the time alignment algorithm based on sliding window was applied to reduce the retrieval range and improve retrieval speed. In order to improve the detection precision, this algorithm performed the global feature, the color correlation graph, and the local feature extraction of the SIFT, and then combined the advantages of both global and local features. Experimental results showed that the proposed method could achieve better performance.

Key words: video retrieval, sliding window, multiple feature fusion, color correlogram, temporal and spatial characteristics, key frame

中图分类号:

TP391.41

侯严明,李菲菲,陈虬. 基于多特征融合的视频检索算法[J]. 电子科技, 2019, 32(5): 44-49.

HOU Yanming,LI Feifei,CHEN Qiu. Video Retrieval Algorithm Based on Multiple Feature Fusion[J]. Electronic Science and Technology, 2019, 32(5): 44-49.

图/表 10

图1

图2

图3

图4

表1

图5

图6

图7

图8

表2

参考文献 17

[1]	Kashino K, Kurozumi T, Murase H . A quick search method for audio and video signals based on histogram pruning[J]. IEEE Transactions on Multimedia, 2003,5(3):348-357. doi: 10.1109/TMM.2003.813281
[2]	Ozkan S, Esen E, Akar G B. Enhanced spatio-temporal video copy detection by combining trajectory and spatial consistency[C]. Paris:IEEE International Conference on Image Processing, 2014.
[3]	Ren D, Zhuo L, Long H, et al. MPEG-2 video copy detection method based on sparse representation of spatial and temporal features[C]. Taipei:IEEE Second International Conference on Multimedia Big Data, 2016.
[4]	黄少年, 赵跃龙, 邱建雄 . 一种基于镜头的视频场景检测方法[J]. 计算机工程与应用, 2006,42(19):170-173.
	Huang Shaonian, Zhao Yuelong, Qiu Jianxiong . A method of video scence detection based on shots[J]. Computer Engineering and Applications, 2006,42(19):170-173.
[5]	Lin H D, Qiang Y U . Design and Implementation of an network video surveillance system based on H264[J]. Journal of Xihua University, 2014,171(6):1029-1045.
[6]	Shiue Y C, Lo S H, Tian Y C , et al. The study of salient object and BoF with SIFT for image retrieval[M]. Bangkok:Frontier Computing, 2018.
[7]	Wu X, Hauptmann A G, Ngo C W. Practical elimination of near-duplicates from web video search [C].Augsburg: ACM International Conference on Multimedia, 2007.
[8]	Chou C L, Chen H T, Lee S Y . Pattern-based near-duplicate video retrieval and localization on web-scale videos[J]. IEEE Transactions on Multimedia, 2015,17(3):382-395. doi: 10.1109/TMM.2015.2391674
[9]	王盼盼, 李玉惠 . 基于特征融合和L-M算法的车辆重识别方法[J]. 电子科技, 2018,31(4):12-15.
	Wang Panpan, Li Yuhui . Vehicle re-identification method based on feature fusion and L-M algorithm[J]. Electronic Science and Technology, 2018,31(4):12-15.
[10]	韩永刚, 赵巍凯 . 基于单目视觉的行人检测研究[J]. 电子科技, 2014,27(8):22-25.
	Han Yonggang, Zhao Weikai . Algorithm for pedestrian detection based on monocular vision[J]. Electronic Science and Technology, 2014,27(8):22-25.
[11]	陈进, 陈思, 王一帆 , 等. 基于ARM的联合收割机远程视频监视系统[J]. 电子科技, 2016,29(2):85-88.
	Chen Jin, Chen Si, Wang Yifan , et al. ARM9-based remote video monitoring system for combine harvester[J], Electronic Science and Technology, 2016,29(2):85-88.
[12]	李阳 . 局部时空特征及部件的视频人体动作识别方法研究[D]. 重庆:重庆大学, 2015.
	Li Yang . Research based on local spatiotemporal features and parts for human action recognition from videos[D]. Chongqing:Chongqing University, 2015.
[13]	李龙 . 视频中人体行为识别的研究[D]. 南京:南京邮电大学, 2016.
	Li Long . A study on human action recognition in video[D]. Nanjing:Nanjing University of Posts and Telecommunications, 2016.
[14]	Gu X, Zhang D, Zhang Y, et al. A video copy detection algorithm combining local feature's robustness and global feature's speed[C]. Vancouver:IEEE International Conference on Acoustics, Speech and Signal Processing, 2013.
[15]	Jiang Y G, Jiang Y, Wang J. VCDB:A Large-scale database for partial copy detection in videos[M]. Amsterdam: Springer International Publishing, 2014.
[16]	Mohamed S T . Shots temporal prediction rules for high-dimensional data of semantic video retrieval[J]. American Journal of Applied Sciences, 2018,15(1):60-69. doi: 10.3844/ajassp.2018.60.69
[17]	张护望, 林浒, 王诗宇 , 等. 一种基于改进SIFT算法的轨道板图像匹配方法[J]. 组合机床与自动化加工技术, 2018(3):1-3.
	Zhang Huwang, Lin hu, Wang Shiyu , et al. Method of rail board image matching based on improved SIFT algorithm[J]. Modular Machine Tool & Automatic Manufacturing Technique, 2018(3):1-3.

图像块	三通道关系
1	C_r>C_g>C_b
2	C_r>C_b>C_g
3	C_g>C_b>C_r
4	C_g>C_r>C_b
5	C_b>C_g>C_r
6	C_b>C_r>C_g
7	C_r>C_g=C_b
8	C_g>C_r=C_b
9	C_b>C_g=C_r
0	其他

方法	MAP/%	时间/s
PPT^[8]	0.958	3 500
SIG_CH	0.892	-
CCV	0.757	22.45
CCV+OM	0.934	33.96
CCV+OM+ORB	0.943	73.45
CCV+OM+SIFT	0.952	64.13

基于多特征融合的视频检索算法

Video Retrieval Algorithm Based on Multiple Feature Fusion

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 17

相关文章 6

Metrics

本文评价

推荐阅读 7

[1]	王庆文,胡海洋. 基于时序行为检测的工作流识别[J]. 电子科技, 2021, 34(8): 14-18.
[2]	邹俊晨,齐金鹏,李娜,刘佳伦,朱厚杰. 一种快速的突变点在线检测算法设计与实现[J]. 电子科技, 2020, 33(8): 10-16.
[3]	张天奇,张顺康. 基于主成分分析的实时全网络异常检测方法[J]. 电子科技, 2019, 32(12): 17-21.
[4]	褚天,潘金满,杜磊. 基于自适应滑动窗口的RFID漏读数据清洗算法[J]. , 2016, 29(4): 24-.
[5]	江楠,徐秦. 数据流聚类算法在数据处理中的应用[J]. , 2015, 28(1): 155-.
[6]	孔英会, 刘淑荣, 张少明, 范启跃. 基于语义的视频检索关键技术综述[J]. , 2012, 25(8): 150-.