Clausius Normalized Field-Based Shape-Independent Motion Segmentation

Eunjin KOH; Chanyoung LEE; Dong Gil JEONG

doi:10.1587/transinf.E97.D.1254

Clausius Normalized Field-Based Shape-Independent Motion Segmentation

Eunjin KOH, Chanyoung LEE, Dong Gil JEONG

Full Text Views

0

Share
Cite this

Summary :

We propose a novel motion segmentation method based on a Clausius Normalized Field (CNF), a probabilistic model for treating time-varying imagery, which estimates entropy variations by observing the entropy definitions of Clausius and Boltzmann. As pixels of an image are viewed as a state of lattice-like molecules in a thermodynamic system, estimating entropy variations of pixels is the same as estimating their degrees of disorder. A greater increase in entropy means that a pixel has a higher chance of belonging to moving objects rather than to the background, because of its higher disorder. In addition to these homologous operations, a CNF naturally takes into consideration both spatial and temporal information to avoid local maxima, which substantially improves the accuracy of motion segmentation. Our motion segmentation system using CNF clearly separates moving objects from their backgrounds. It also effectively eliminates noise to a level achieved when refined post-processing steps are applied to the results of general motion segmentations. It requires less computational power than other random fields and generates automatically normalized outputs without additional post-processes.

Publication: IEICE TRANSACTIONS on Information Vol.E97-D No.5 pp.1254-1263

Publication Date: 2014/05/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E97.D.1254

Type of Manuscript: PAPER

Category: Pattern Recognition

Authors

Eunjin KOH
  Agency for Defense Development
Chanyoung LEE
  Agency for Defense Development
Dong Gil JEONG
  Agency for Defense Development

Keyword

motion segmentation, pixel classification, time-varying imagery

Cite this

Copy

Eunjin KOH, Chanyoung LEE, Dong Gil JEONG, "Clausius Normalized Field-Based Shape-Independent Motion Segmentation" in IEICE TRANSACTIONS on Information, vol. E97-D, no. 5, pp. 1254-1263, May 2014, doi: 10.1587/transinf.E97.D.1254.
Abstract: We propose a novel motion segmentation method based on a Clausius Normalized Field (CNF), a probabilistic model for treating time-varying imagery, which estimates entropy variations by observing the entropy definitions of Clausius and Boltzmann. As pixels of an image are viewed as a state of lattice-like molecules in a thermodynamic system, estimating entropy variations of pixels is the same as estimating their degrees of disorder. A greater increase in entropy means that a pixel has a higher chance of belonging to moving objects rather than to the background, because of its higher disorder. In addition to these homologous operations, a CNF naturally takes into consideration both spatial and temporal information to avoid local maxima, which substantially improves the accuracy of motion segmentation. Our motion segmentation system using CNF clearly separates moving objects from their backgrounds. It also effectively eliminates noise to a level achieved when refined post-processing steps are applied to the results of general motion segmentations. It requires less computational power than other random fields and generates automatically normalized outputs without additional post-processes.
URL: https://globals.ieice.org/en_transactions/information/10.1587/transinf.E97.D.1254/_p

Copy

@ARTICLE{e97-d_5_1254,
author={Eunjin KOH, Chanyoung LEE, Dong Gil JEONG, },
journal={IEICE TRANSACTIONS on Information},
title={Clausius Normalized Field-Based Shape-Independent Motion Segmentation},
year={2014},
volume={E97-D},
number={5},
pages={1254-1263},
abstract={We propose a novel motion segmentation method based on a Clausius Normalized Field (CNF), a probabilistic model for treating time-varying imagery, which estimates entropy variations by observing the entropy definitions of Clausius and Boltzmann. As pixels of an image are viewed as a state of lattice-like molecules in a thermodynamic system, estimating entropy variations of pixels is the same as estimating their degrees of disorder. A greater increase in entropy means that a pixel has a higher chance of belonging to moving objects rather than to the background, because of its higher disorder. In addition to these homologous operations, a CNF naturally takes into consideration both spatial and temporal information to avoid local maxima, which substantially improves the accuracy of motion segmentation. Our motion segmentation system using CNF clearly separates moving objects from their backgrounds. It also effectively eliminates noise to a level achieved when refined post-processing steps are applied to the results of general motion segmentations. It requires less computational power than other random fields and generates automatically normalized outputs without additional post-processes.},
keywords={},
doi={10.1587/transinf.E97.D.1254},
ISSN={1745-1361},
month={May},}

Copy

TY - JOUR
TI - Clausius Normalized Field-Based Shape-Independent Motion Segmentation
T2 - IEICE TRANSACTIONS on Information
SP - 1254
EP - 1263
AU - Eunjin KOH
AU - Chanyoung LEE
AU - Dong Gil JEONG
PY - 2014
DO - 10.1587/transinf.E97.D.1254
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E97-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2014
AB - We propose a novel motion segmentation method based on a Clausius Normalized Field (CNF), a probabilistic model for treating time-varying imagery, which estimates entropy variations by observing the entropy definitions of Clausius and Boltzmann. As pixels of an image are viewed as a state of lattice-like molecules in a thermodynamic system, estimating entropy variations of pixels is the same as estimating their degrees of disorder. A greater increase in entropy means that a pixel has a higher chance of belonging to moving objects rather than to the background, because of its higher disorder. In addition to these homologous operations, a CNF naturally takes into consideration both spatial and temporal information to avoid local maxima, which substantially improves the accuracy of motion segmentation. Our motion segmentation system using CNF clearly separates moving objects from their backgrounds. It also effectively eliminates noise to a level achieved when refined post-processing steps are applied to the results of general motion segmentations. It requires less computational power than other random fields and generates automatically normalized outputs without additional post-processes.
ER -