HCRF和网络文本的精彩事件自动检测定位

doi:10.3969/j.issn.1001-2400.2015.04.014

Abstract

Abstract:

Based on the powerful function of the hidden conditional random fields (HCRF) model in the expression and identification of semantic events and combining the webcast text information, a new framework for wonderful events automatic detection is put forward. Firstly, by analyzing and processing the webcast text, keyword combinations corresponding to each exciting event are obtained. Secondly, by classifying the webcast text to be detected, the happening time labels of each wonderful event are obtained. Thirdly, an HCRF model for semantic shot annotation is built to realize the semantic annotation of multiple types of semantic shots simultaneously, and the semantic shot sequence of the video clip is obtained. Finally, combining the multi-modal semantic clues, an HCRF model for the wonderful events detection and localization is effectively built in the case of small-scale training samples. Based on the mapping relationship among video low-level features, the multi-modal semantic clues and the wonderful semantic events, the inherent patterns of the wonderful events are excavated deeply in the multiple dimensions of the semantic structure, and then the wonderful events automatic detection, localization and segmentation are precisely achieved. Experiments show the effectiveness of this model.

Key words: video semantic analysis, event detection, webcast text, hidden conditional random field (HCRF), semantic shots annotation

CLC Number:

TP391

TONG Ming;WANG Shuo;DING Liwei;WANG Gang. Wonderful events automatic detection and location of the HCRF and webcast text[J].J4, 2015, 42(4): 81-87.

References

［1］ Kolekar M H. Bayesian Belief Network Based Broadcast Sports Video Indexing ［J］. Multimedia Tools and Applications, 2011, 54(1): 27-54.
［2］ Cheng H Y, Weng C C, Chen Y Y. Vehicle Detection in Aerial Surveillance Using Dynamic Bayesian Networks ［J］. IEEE Transactions on Image Processing, 2012, 21(4): 2152-2159.
［3］ Huang C L, Shih H C, Chao C Y. Semantic Analysis of Soccer Video Using Dynamic Bayesian Network ［J］. IEEE Transactions on Multimedia, 2006, 8(4): 749-760.
［4］ Murty M N, Devi V S. Hidden Markov Models ［M］. London: Springer, 2011: 103-122.
［5］张玉珍, 丁思捷, 王建宇, 等. 基于HMM的融合多模态的事件检测［J］. 系统仿真学报, 2012, 24(8): 1638-1642.
Zhang Yuzhen, Ding Sijie, Wang Jianyu, et al. Event Detection by Fusing Multimodal Objects Using HMM ［J］. Journal of System Simulation, 2012, 24(8): 1638-1642.
［6］李英, 田春娜, 颜建强, 等. 一种图像中的文字区域检测新方法［J］. 西安电子科技大学学报, 2013, 40(6): 187-192.
Li Ying, Tian Chunna, Yan Jianqiang, et al. New Technique for Text Region Location in Images ［J］. Journal of Xidian University, 2013, 40(6): 187-192.
［7］ Vilas N, Havin R. Entropy Features Trained Support Vector Machine Based Logo Detection Method for Replay Detection and Extraction from Sports Videos ［J］. International Journal of Graphics and Multimedia, 2013, 4(1): 20-30.
［8］ Delaye A, Liu C L. Contextual Text／Non-text Stroke Classification in Online Handwritten Notes with Conditional Random Fields ［J］. Pattern Recognition, 2014, 47(3): 959-968.
［9］ Shyu M L, Xie Z X, Chen M, et al. Video Semantic Event／Concept Detection Using a Subspace-based Multimedia Data Mining Framework ［J］. IEEE Transactions on Multimedia, 2008, 10(2): 252-259.
［10］ Tjondronegoro D W, Chen Y P P. Knowledge-discounted Event Detection in Sports Video ［J］. IEEE Transactions on Systems, Man and Cybernetics, Part A: Systems and Humans, 2010, 40(5): 1009-1024.
［11］ Xu C S, Wang J J, Lu H Q, et al. A Novel Framework for Semantic Annotation and Personalized Retrieval of Sports Video ［J］. IEEE Transactions on Multimedia, 2008, 10(3): 421-436.
［12］ Zhao Y, Juang B H. Stranded Gaussian Mixture Hidden Markov Models for Robust Speech Recognition ［C］//Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2012: 4301-4304.
［13］ Bargi A, Xu R Y D, Piccardi M. An Online HDP-HMM for Joint Action Segmentation and Classification in Motion Capture Data ［C］//IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway: IEEE, 2012: 1-7.
［14］ Van Urgen G J, Saatci Y, Teh Y W, et al. Beam Sampling for the Infinite Hidden Markov Model ［C］//Proceedings of the 25th International Conference on Machine Learning. New York: ACM, 2008: 1088-1095.
［15］同鸣, 丁力伟, 姬成龙. 融合HCRF和AAM的足球视频精彩事件检测［J］. 计算机研究与发展, 2014, 51(1): 225-236.
Tong Ming, Ding Liwei, Ji Chenglong. Fusion of HCRF and AAM Highlight Events Detection in Soccer Videos ［J］. Journal of Computer Research and Development, 2014, 51(1): 225-236.
［16］ Wang J J, Xu C S, Chng E, et al. Automatic Generation of Personalized Music Sports Video ［C］//Proceedings of the 13th ACM International Conference on Multimedia. New York: ACM, 2005: 735-744.
［17］ Xu C S, Wang J J, Wan K, et al. Live Sports Event Detection Based on Broadcast Video and Web-casting Text ［C］//Proceedings of the 14th Annual ACM International Conference on Multimedia. New York: ACM, 2006: 221-230.

[1]	WANG Xiumei;DING Lijie;GAO Xinbo. Linear embedding Hashing method in preserving similarity [J]. J4, 2016, 43(1): 94-98.
[2]	DU Shimin;XIA Yinshui;CHU Zhufei;YANG Runping. Voltage island-driven multilevel floorplanning optimization algorithm [J]. J4, 2015, 42(6): 184-190.
[3]	QIN Bing;TIAN Jun;ZHA Yufei;ZHANG Lichao;HUANG Hongtu. Real-time visual object tracking based on binary descriptors [J]. J4, 2015, 42(5): 168-174.
[4]	ZHANG Minqing;ZHANG Yan;LI Delong;LUO Peng. Blind steganalysis algorithm based new calibration for JPEG images [J]. J4, 2015, 42(5): 133-138.
[5]	ZHANG Li;ZHAO Liangxu;WANG Shouguang;WANG Chengying. Optimal linear constraint transformation method for α-nets [J]. J4, 2015, 42(5): 183-187+212.
[6]	WEI Xiaoran;GENG Guohua;ZHANG Yuhe. Connectivity compression of triangle meshes based on geometric parameter predict [J]. J4, 2015, 42(5): 194-199.
[7]	GE Lin;JI Xinsheng;JIANG Tao. Situation prediction of network information content security incidents using E-IGA-RBF [J]. J4, 2015, 42(4): 107-113.
[8]	NIU Ke;LI Jun;LIU Jia;YANG Xiaoyuan. Strategic adaptive steganography based on the game theory model [J]. J4, 2015, 42(4): 165-170.
[9]	LI Na;GENG Guohua;GONG Xingyu;WANG Xiaofeng. Recolor method for the fading terracotta warrior using the texture image [J]. J4, 2015, 42(4): 127-132+170.
[10]	MA Yanping;JI Guangrong;ZOU Hailin;XIE Hongtao. Data-oriented multi-index Hashing [J]. J4, 2015, 42(4): 159-164.
[11]	FENG Xiaoyi;LAI Yangming;WANG Wenxing;CUI Shaoxing;PENG Jinye;JIANG Xiaoyu. Facial expression recognition based on the binary code of edges [J]. J4, 2015, 42(3): 186-191.
[12]	ZHAO Shanshan;ZHANG Linrang;ZHOU Yu;LIU Nan . Active false-target discrimination method based on the difference in spatial scattering characteristic [J]. J4, 2015, 42(2): 20-27.
[13]	FANG Biao;HUANG Gaoming;GAO Jun;ZUO Wei. Compressive sensing of linear frequency modulated echo signals in fractional Fourier domains [J]. J4, 2015, 42(1): 200-206.
[14]	JIANG Jianguo;ZHAO Yuan;MENG Hongwei;LI Bo. SVM decision-tree multi-classification strategy via electromagnetism-like mechanism [J]. J4, 2014, 41(6): 83-88.
[15]	GONG Yanchao;WAN Shuai;YANG Kaifang;CHEN Hao;LI Bo. Real-time 3D bare-hand gesture recognition using binocular vision videos [J]. J4, 2014, 41(4): 130-136.

Wonderful events automatic detection and location of the HCRF and webcast text

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 0