Dynamic texture detection based on motion analysis

Sándor Fazekas, Tomer Amiaz, D. Chetverikov, Nahum Kiryati

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

Motion estimation is usually based on the brightness constancy assumption. This assumption holds well for rigid objects with a Lambertian surface, but it is less appropriate for fluid and gaseous materials. For these materials an alternative assumption is required. This work examines three possible alternatives: gradient constancy, color constancy and brightness conservation (under this assumption the brightness of an object can diffuse to its neighborhood). Brightness conservation and color constancy are found to be adequate models. We propose a method for detecting regions of dynamic texture in image sequences. Accurate segmentation into regions of static and dynamic texture is achieved using a level set scheme. The level set function separates each image into regions that obey brightness constancy and regions that obey the alternative assumption. We show that the method can be simplified to obtain a less robust but fast algorithm, capable of real-time performance. Experimental results demonstrate accurate segmentation by the full level set scheme, as well as by the simplified method. The experiments included challenging image sequences, in which color or geometry cues by themselves would be insufficient.

Original languageEnglish
Pages (from-to)48-63
Number of pages16
JournalInternational Journal of Computer Vision
Volume82
Issue number1
DOIs
Publication statusPublished - Apr 2009

Fingerprint

Luminance
Textures
Color
Conservation
Motion estimation
Motion analysis
Fluids
Geometry
Experiments

Keywords

  • Brightness conservation
  • Dynamic texture
  • Level set
  • Motion analysis
  • Optical flow
  • Real-time processing

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition

Cite this

Dynamic texture detection based on motion analysis. / Fazekas, Sándor; Amiaz, Tomer; Chetverikov, D.; Kiryati, Nahum.

In: International Journal of Computer Vision, Vol. 82, No. 1, 04.2009, p. 48-63.

Research output: Contribution to journalArticle

Fazekas, Sándor ; Amiaz, Tomer ; Chetverikov, D. ; Kiryati, Nahum. / Dynamic texture detection based on motion analysis. In: International Journal of Computer Vision. 2009 ; Vol. 82, No. 1. pp. 48-63.
@article{ff4e05bfa5cf4d5fa3f0ea11ffb497f6,
title = "Dynamic texture detection based on motion analysis",
abstract = "Motion estimation is usually based on the brightness constancy assumption. This assumption holds well for rigid objects with a Lambertian surface, but it is less appropriate for fluid and gaseous materials. For these materials an alternative assumption is required. This work examines three possible alternatives: gradient constancy, color constancy and brightness conservation (under this assumption the brightness of an object can diffuse to its neighborhood). Brightness conservation and color constancy are found to be adequate models. We propose a method for detecting regions of dynamic texture in image sequences. Accurate segmentation into regions of static and dynamic texture is achieved using a level set scheme. The level set function separates each image into regions that obey brightness constancy and regions that obey the alternative assumption. We show that the method can be simplified to obtain a less robust but fast algorithm, capable of real-time performance. Experimental results demonstrate accurate segmentation by the full level set scheme, as well as by the simplified method. The experiments included challenging image sequences, in which color or geometry cues by themselves would be insufficient.",
keywords = "Brightness conservation, Dynamic texture, Level set, Motion analysis, Optical flow, Real-time processing",
author = "S{\'a}ndor Fazekas and Tomer Amiaz and D. Chetverikov and Nahum Kiryati",
year = "2009",
month = "4",
doi = "10.1007/s11263-008-0184-y",
language = "English",
volume = "82",
pages = "48--63",
journal = "International Journal of Computer Vision",
issn = "0920-5691",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Dynamic texture detection based on motion analysis

AU - Fazekas, Sándor

AU - Amiaz, Tomer

AU - Chetverikov, D.

AU - Kiryati, Nahum

PY - 2009/4

Y1 - 2009/4

N2 - Motion estimation is usually based on the brightness constancy assumption. This assumption holds well for rigid objects with a Lambertian surface, but it is less appropriate for fluid and gaseous materials. For these materials an alternative assumption is required. This work examines three possible alternatives: gradient constancy, color constancy and brightness conservation (under this assumption the brightness of an object can diffuse to its neighborhood). Brightness conservation and color constancy are found to be adequate models. We propose a method for detecting regions of dynamic texture in image sequences. Accurate segmentation into regions of static and dynamic texture is achieved using a level set scheme. The level set function separates each image into regions that obey brightness constancy and regions that obey the alternative assumption. We show that the method can be simplified to obtain a less robust but fast algorithm, capable of real-time performance. Experimental results demonstrate accurate segmentation by the full level set scheme, as well as by the simplified method. The experiments included challenging image sequences, in which color or geometry cues by themselves would be insufficient.

AB - Motion estimation is usually based on the brightness constancy assumption. This assumption holds well for rigid objects with a Lambertian surface, but it is less appropriate for fluid and gaseous materials. For these materials an alternative assumption is required. This work examines three possible alternatives: gradient constancy, color constancy and brightness conservation (under this assumption the brightness of an object can diffuse to its neighborhood). Brightness conservation and color constancy are found to be adequate models. We propose a method for detecting regions of dynamic texture in image sequences. Accurate segmentation into regions of static and dynamic texture is achieved using a level set scheme. The level set function separates each image into regions that obey brightness constancy and regions that obey the alternative assumption. We show that the method can be simplified to obtain a less robust but fast algorithm, capable of real-time performance. Experimental results demonstrate accurate segmentation by the full level set scheme, as well as by the simplified method. The experiments included challenging image sequences, in which color or geometry cues by themselves would be insufficient.

KW - Brightness conservation

KW - Dynamic texture

KW - Level set

KW - Motion analysis

KW - Optical flow

KW - Real-time processing

UR - http://www.scopus.com/inward/record.url?scp=59149095246&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=59149095246&partnerID=8YFLogxK

U2 - 10.1007/s11263-008-0184-y

DO - 10.1007/s11263-008-0184-y

M3 - Article

AN - SCOPUS:59149095246

VL - 82

SP - 48

EP - 63

JO - International Journal of Computer Vision

JF - International Journal of Computer Vision

SN - 0920-5691

IS - 1

ER -