Estimation and segmentation of displacement field using multiple features

Sanghoon Sull, N. Ahuja

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

We present an approach for estimating and segmenting the displacement field (DF) between two frames. Our method is based on local affine (first-order) approximation of the displacement field which is derived under the assumption of locally rigid motion. Each distinct motion is represented in the image plane by a distinct set of values of affine coefficients. All sets of values supported by the feature locations in two frames are identified by exhaustive coarse-to-fine search. The integrated use of multiple features (points, regions and lines) increases the probability of finding well-supported sets. The sets of coefficients thus obtained are used to describe the DF. Two experimental results with real images are presented to demonstrate the feasibility of our approach.

Original languageEnglish
Article number413889
Pages (from-to)53-57
Number of pages5
JournalProceedings - International Conference on Image Processing, ICIP
Volume3
DOIs
Publication statusPublished - 1994
Externally publishedYes

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Estimation and segmentation of displacement field using multiple features. / Sull, Sanghoon; Ahuja, N.

In: Proceedings - International Conference on Image Processing, ICIP, Vol. 3, 413889, 1994, p. 53-57.

Research output: Contribution to journalArticle

@article{6f4ae1118f1043a4b990fd1cd99f4e6f,
title = "Estimation and segmentation of displacement field using multiple features",
abstract = "We present an approach for estimating and segmenting the displacement field (DF) between two frames. Our method is based on local affine (first-order) approximation of the displacement field which is derived under the assumption of locally rigid motion. Each distinct motion is represented in the image plane by a distinct set of values of affine coefficients. All sets of values supported by the feature locations in two frames are identified by exhaustive coarse-to-fine search. The integrated use of multiple features (points, regions and lines) increases the probability of finding well-supported sets. The sets of coefficients thus obtained are used to describe the DF. Two experimental results with real images are presented to demonstrate the feasibility of our approach.",
author = "Sanghoon Sull and N. Ahuja",
year = "1994",
doi = "10.1109/ICIP.1994.413889",
language = "English",
volume = "3",
pages = "53--57",
journal = "Proceedings - International Conference on Image Processing, ICIP",
issn = "1522-4880",

}

TY - JOUR

T1 - Estimation and segmentation of displacement field using multiple features

AU - Sull, Sanghoon

AU - Ahuja, N.

PY - 1994

Y1 - 1994

N2 - We present an approach for estimating and segmenting the displacement field (DF) between two frames. Our method is based on local affine (first-order) approximation of the displacement field which is derived under the assumption of locally rigid motion. Each distinct motion is represented in the image plane by a distinct set of values of affine coefficients. All sets of values supported by the feature locations in two frames are identified by exhaustive coarse-to-fine search. The integrated use of multiple features (points, regions and lines) increases the probability of finding well-supported sets. The sets of coefficients thus obtained are used to describe the DF. Two experimental results with real images are presented to demonstrate the feasibility of our approach.

AB - We present an approach for estimating and segmenting the displacement field (DF) between two frames. Our method is based on local affine (first-order) approximation of the displacement field which is derived under the assumption of locally rigid motion. Each distinct motion is represented in the image plane by a distinct set of values of affine coefficients. All sets of values supported by the feature locations in two frames are identified by exhaustive coarse-to-fine search. The integrated use of multiple features (points, regions and lines) increases the probability of finding well-supported sets. The sets of coefficients thus obtained are used to describe the DF. Two experimental results with real images are presented to demonstrate the feasibility of our approach.

UR - http://www.scopus.com/inward/record.url?scp=84999218043&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84999218043&partnerID=8YFLogxK

U2 - 10.1109/ICIP.1994.413889

DO - 10.1109/ICIP.1994.413889

M3 - Article

AN - SCOPUS:84999218043

VL - 3

SP - 53

EP - 57

JO - Proceedings - International Conference on Image Processing, ICIP

JF - Proceedings - International Conference on Image Processing, ICIP

SN - 1522-4880

M1 - 413889

ER -