Depth map calculation for a variable number of moving objects using Markov sequential object processes

被引：7

作者：

van Lieshout, M. N. M. ^{[1
,2
]}

机构：

[1] Ctr Wiskunde & Informat, NL-1098 SJ Amsterdam, Netherlands

[2] Eindhoven Univ Technol, NL-1009 AB Amsterdam, Netherlands

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2008年 / 30卷 / 07期

关键词：

depth calculation; Markov chain Monte Carlo; Markov sequential object process; object tracking; regularization; stochastic geometry;

D O I：

10.1109/TPAMI.2008.45

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We advocate the use of Markov sequential object processes for tracking a variable number of moving objects through video frames with a view towards depth calculation. A regression model based on a sequential object process quantifies goodness of fit; regularization terms are incorporated to control within and between frame object interactions. We construct a Markov chain Monte Carlo method for finding the optimal tracks and associated depths and illustrate the approach on a synthetic data set as well as a sports sequence.

引用

页码：1308 / 1312

页数：5

共 26 条

[1]

[Anonymous], 1993, Journal of Applied Statistics, DOI DOI 10.1080/02664769300000065

[2]

[Anonymous], 1999, BAYESIAN ANAL SPATIA

[3]

BADDELEY A, 1992, P 11 INT ASS PATT RE, pB136

[4]

Eubank R.L., 2006, A Kalman Filter Primer

[5]

GEYER CJ, 1994, SCAND J STAT, V21, P359

[6]

GOODMAN IR, 1997, MATH DATA FUSION B, V39

[7] NOVEL-APPROACH TO NONLINEAR NON-GAUSSIAN BAYESIAN STATE ESTIMATION [J].

GORDON, NJ ;

SALMOND, DJ ;

SMITH, AFM .

IEE PROCEEDINGS-F RADAR AND SIGNAL PROCESSING, 1993, 140 (02) :107-113

[8]

Green PJ, 1995, BIOMETRIKA, V82, P711, DOI 10.2307/2337340

[9]

Hough PV., 1962, US Patent, Patent No. 3069654

[10] Sequential Monte Carlo methods for multiple target tracking and data fusion [J].

Hue, C ;

Le Cadre, JP ;

Pérez, P .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2002, 50 (02) :309-325

← 1 2 3 →