Brownian Images: a generic background model

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Brownian Images : a generic background model. / Pedersen, Kim Steenstrup; Lillholm, Martin.

Proceedings of the ECCV'04 Workshop on Statistical Learning in Computer Vision. 2004.

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Pedersen, KS & Lillholm, M 2004, Brownian Images: a generic background model. i Proceedings of the ECCV'04 Workshop on Statistical Learning in Computer Vision. Statistical Learning in Computer Vision. ECCV Workshop, Prague, Tjekkiet, 29/11/2010.

APA

Pedersen, K. S., & Lillholm, M. (2004). Brownian Images: a generic background model. I Proceedings of the ECCV'04 Workshop on Statistical Learning in Computer Vision

Vancouver

Pedersen KS, Lillholm M. Brownian Images: a generic background model. I Proceedings of the ECCV'04 Workshop on Statistical Learning in Computer Vision. 2004

Author

Pedersen, Kim Steenstrup ; Lillholm, Martin. / Brownian Images : a generic background model. Proceedings of the ECCV'04 Workshop on Statistical Learning in Computer Vision. 2004.

Bibtex

@inproceedings{868bacc06ad211dd8d9f000ea68e967b,
title = "Brownian Images: a generic background model",
abstract = "The local structure of a suitably differentiable function can be described through it's truncated Taylor series. Gaussian scale space theory is a sensible framework for calculating image derivatives or the coefficients of the Taylor series up to any order using the corresponding derivatives of the Gaussian kernel. Zero-crossings of invariant combinations of such regularised derivatives have successfully been used as feature detectors.Recent work shows that feature detection can be stated as a simple problem of classification into the feature types of interest (edges, blobs, etc.). The information used in the classication is the mapping of Taylor series coefficients, i.e. image derivatives, into jet space. The conjecture is that features form classes or clusters in jet space. We introduce the classification framework and present feature detection results based on empirical edge and blob models. These models are augmented with a theoretical parametric model of a background feature type, namely the Brownian image model. The background feature type is not to be considered as the class of all non-modelled feature types, but as a new feature type in itself.The quality of the Brownian image background model is further investigated. The background model leads to classification of images into areas which are plausible featureless background areas. From an intuitive point of view the image structure is more complex in areas classified as features as opposed to the simpler background region. We verify this using a reconstruction scheme with spatially uniform constraints and a simple Gaussian assumption of prior pixel distributions. We are, however, also able to show that reconstructions using a Brownian prior results in a significant gain in reconstruction quality for the Brownian like background areas.",
author = "Pedersen, {Kim Steenstrup} and Martin Lillholm",
year = "2004",
language = "English",
booktitle = "Proceedings of the ECCV'04 Workshop on Statistical Learning in Computer Vision",

}

RIS

TY - GEN

T1 - Brownian Images

T2 - a generic background model

AU - Pedersen, Kim Steenstrup

AU - Lillholm, Martin

PY - 2004

Y1 - 2004

N2 - The local structure of a suitably differentiable function can be described through it's truncated Taylor series. Gaussian scale space theory is a sensible framework for calculating image derivatives or the coefficients of the Taylor series up to any order using the corresponding derivatives of the Gaussian kernel. Zero-crossings of invariant combinations of such regularised derivatives have successfully been used as feature detectors.Recent work shows that feature detection can be stated as a simple problem of classification into the feature types of interest (edges, blobs, etc.). The information used in the classication is the mapping of Taylor series coefficients, i.e. image derivatives, into jet space. The conjecture is that features form classes or clusters in jet space. We introduce the classification framework and present feature detection results based on empirical edge and blob models. These models are augmented with a theoretical parametric model of a background feature type, namely the Brownian image model. The background feature type is not to be considered as the class of all non-modelled feature types, but as a new feature type in itself.The quality of the Brownian image background model is further investigated. The background model leads to classification of images into areas which are plausible featureless background areas. From an intuitive point of view the image structure is more complex in areas classified as features as opposed to the simpler background region. We verify this using a reconstruction scheme with spatially uniform constraints and a simple Gaussian assumption of prior pixel distributions. We are, however, also able to show that reconstructions using a Brownian prior results in a significant gain in reconstruction quality for the Brownian like background areas.

AB - The local structure of a suitably differentiable function can be described through it's truncated Taylor series. Gaussian scale space theory is a sensible framework for calculating image derivatives or the coefficients of the Taylor series up to any order using the corresponding derivatives of the Gaussian kernel. Zero-crossings of invariant combinations of such regularised derivatives have successfully been used as feature detectors.Recent work shows that feature detection can be stated as a simple problem of classification into the feature types of interest (edges, blobs, etc.). The information used in the classication is the mapping of Taylor series coefficients, i.e. image derivatives, into jet space. The conjecture is that features form classes or clusters in jet space. We introduce the classification framework and present feature detection results based on empirical edge and blob models. These models are augmented with a theoretical parametric model of a background feature type, namely the Brownian image model. The background feature type is not to be considered as the class of all non-modelled feature types, but as a new feature type in itself.The quality of the Brownian image background model is further investigated. The background model leads to classification of images into areas which are plausible featureless background areas. From an intuitive point of view the image structure is more complex in areas classified as features as opposed to the simpler background region. We verify this using a reconstruction scheme with spatially uniform constraints and a simple Gaussian assumption of prior pixel distributions. We are, however, also able to show that reconstructions using a Brownian prior results in a significant gain in reconstruction quality for the Brownian like background areas.

M3 - Article in proceedings

BT - Proceedings of the ECCV'04 Workshop on Statistical Learning in Computer Vision

ER -

ID: 5521155