Online Nonparametric Bayesian Activity Mining and Analysis From Surveillance Video

被引：38

作者：

Bastani, Vahid ^{[1
]}

Marcenaro, Lucio ^{[1
]}

Regazzoni, Carlo S. ^{[1
]}

机构：

[1] Univ Genoa, Dept Elect Elect & Telecommun Engn & Naval Archit, I-16145 Genoa, Italy

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 2016年 / 25卷 / 05期

关键词：

Incremental trajectory clustering; online activity analysis; abnormality detection; state dynamics learning; nonparametric Bayesian; Gaussian process; Dirichlet process mixture;

D O I：

10.1109/TIP.2016.2540813

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A method for online incremental mining of activity patterns from the surveillance video stream is presented in this paper. The framework consists of a learning block in which Dirichlet process mixture model is employed for the incremental clustering of trajectories. Stochastic trajectory pattern models are formed using the Gaussian process regression of the corresponding flow functions. Moreover, a sequential Monte Carlo method based on Rao-Blackwellized particle filter is proposed for tracking and online classification as well as the detection of abnormality during the observation of an object. Experimental results on real surveillance video data are provided to show the performance of the proposed algorithm in different tasks of trajectory clustering, classification, and abnormality detection.

引用

页码：2089 / 2102

页数：14

共 40 条

[1] Multifeature Object Trajectory Clustering for Video Analysis [J].

Anjum, Nadeem ;

Cavallaro, Andrea .

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2008, 18 (11) :1555-1564

[2]

[Anonymous], COMPUT NOW

[3]

[Anonymous], P 93 ANN M TRANSP RE

[4]

[Anonymous], 2013, Adv. Neural Inf. Process. Syst.

[5]

[Anonymous], 2014, 17 INT C INF FUS

[6] A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking [J].

Arulampalam, MS ;

Maskell, S ;

Gordon, N ;

Clapp, T .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2002, 50 (02) :174-188

[7]

Bastani V., 2014, P 2014 IEEE INT WORK, P1

[8]

Bastani V, 2015, IEEE IMAGE PROC, P3690, DOI 10.1109/ICIP.2015.7351493

[9] Probabilistic Topic Models [J].

Blei, David ;

Carin, Lawrence ;

Dunson, David .

IEEE SIGNAL PROCESSING MAGAZINE, 2010, 27 (06) :55-65

[10] Variational Inference for Dirichlet Process Mixtures [J].

Blei, David M. ;

Jordan, Michael I. .

BAYESIAN ANALYSIS, 2006, 1 (01) :121-143

← 1 2 3 4 →