A Dynamic Hierarchical Clustering Method for Trajectory-Based Unusual Video Event Detection

被引：87

作者：

Jiang, Fan ^{[1
]}

Wu, Ying ^{[1
]}

Katsaggelos, Aggelos K. ^{[1
]}

机构：

[1] Northwestern Univ, Dept Elect Engn & Comp Sci, Evanston, IL 60208 USA

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 2009年 / 18卷 / 04期

关键词：

Event detection; unsupervised clustering; video surveillance; RECOGNITION;

D O I：

10.1109/TIP.2008.2012070

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The proposed unusual video event detection method is based on unsupervised clustering of object trajectories, which are modeled by hidden Markov models (HMM). The novelty of the method Includes a dynamic hierarchical process Incorporated in the trajectory clustering algorithm to prevent model overfitting and a 2-depth greedy search strategy for efficient clustering.

引用

页码：907 / 913

页数：7

共 19 条

[1] Object trajectory-based activity classification and recognition using hidden Markov models [J].

Bashir, Faisal I. ;

Khokhar, Ashfaq A. ;

Schonfeld, Dan .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2007, 16 (07) :1912-1919

[2]

Chen SS, 1998, INT CONF ACOUST SPEE, P645, DOI 10.1109/ICASSP.1998.675347

[3]

Cuntoor N.P., 2007, P IEEE COMPUTER SOC, P1

[4]

Duong TV, 2005, PROC CVPR IEEE, P838

[5]

Fu ZY, 2005, IEEE IMAGE PROC, P2029

[6] Using adaptive tracking to classify and monitor activities in a site [J].

Grimson, WEL ;

Stauffer, C ;

Romano, R ;

Lee, L .

1998 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, PROCEEDINGS, 1998, :22-29

[7]

HETTICH S, 1999, UCI KDD ARCHIVE

[8] Recognition of visual activities and interactions by stochastic parsing [J].

Ivanov, YA ;

Bobick, AF .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2000, 22 (08) :852-872

[9]

JIANG F, 2007, P IEEE INT C IM PROC, V5, P145

[10] A PROBABILISTIC DISTANCE MEASURE FOR HIDDEN MARKOV-MODELS [J].

JUANG, BH ;

RABINER, LR .

AT&T TECHNICAL JOURNAL, 1985, 64 (02) :391-408

← 1 2 →