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

M.N.M. Lieshout, van

doi:10.1109/TPAMI.2008.45

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

M.N.M. Lieshout, van

Research output: Contribution to journal › Article › Academic › peer-review

8 Citations (Scopus)

Abstract

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.

Original language	English
Pages (from-to)	1308-1312
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	30
Issue number	7
DOIs	https://doi.org/10.1109/TPAMI.2008.45
Publication status	Published - 2008

Access to Document

10.1109/TPAMI.2008.45

Cite this

@article{60de622351a54f7083771a36e5fa2f35,

title = "Depth map calculation for a variable number of moving objects using Markov sequential object processes",

abstract = "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.",

author = "\{Lieshout, van\}, M.N.M.",

year = "2008",

doi = "10.1109/TPAMI.2008.45",

language = "English",

volume = "30",

pages = "1308--1312",

journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence",

issn = "0162-8828",

publisher = "IEEE Computer Society",

number = "7",

}

TY - JOUR

T1 - Depth map calculation for a variable number of moving objects using Markov sequential object processes

AU - Lieshout, van, M.N.M.

PY - 2008

Y1 - 2008

N2 - 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.

AB - 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.

U2 - 10.1109/TPAMI.2008.45

DO - 10.1109/TPAMI.2008.45

M3 - Article

C2 - 18550912

SN - 0162-8828

VL - 30

SP - 1308

EP - 1312

JO - IEEE Transactions on Pattern Analysis and Machine Intelligence

JF - IEEE Transactions on Pattern Analysis and Machine Intelligence

IS - 7

ER -

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

Abstract

Access to Document

Fingerprint

Cite this