Improving the scope of deformable model shape and motion estimation

Cristian Sminchisescu, Dimitri Metaxas, Sven Dickinson

Research output: Contribution to journalConference article

3 Citations (Scopus)

Abstract

Previous approaches to deformable model shape estimation and tracking have assumed a fixed class of shapes representation (e.g., deformable superquadrics), initialized prior to tracking. Since the shape coverage of the model is fixed, such approaches do not directly accommodate incremental representation discovery during tracking. As a result, model shape coverage is decoupled from tracking, thereby limiting both processes in terms of scope and robustness. We present a novel deformable model framework that accommodates the incremental incorporation during tracking of new geometric primitives (lines, in addition to points) that are not explicitly captured in the initial deformable model but that are moving consistently with its image motion. As these new features are detected via consistency checks, they are added to the model, providing incremental soft constraints on the estimation of its rigid parameters. The consistency checks are based on trilinear relationships between geometric primitives. Consequently we not only increase both model scope and, ultimately, its higher-level shape coverage, but improve tracking robustness and accuracy, by directly employing the new features in both forward prediction and reconstruction. Our new formulation is a step towards automating model shape estimation and tracking, since it requires significantly reduced initial model hand-crafting. We demonstrate our approach on two separate image-based tracking domains, each involving complex 3D object shape and motion.

Original languageEnglish (US)
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
StatePublished - Dec 1 2001
Externally publishedYes
Event2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Kauai, HI, United States
Duration: Dec 8 2001Dec 14 2001

Fingerprint

Motion estimation

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

@article{bf9a486926e546379b155a6aa47d5812,
title = "Improving the scope of deformable model shape and motion estimation",
abstract = "Previous approaches to deformable model shape estimation and tracking have assumed a fixed class of shapes representation (e.g., deformable superquadrics), initialized prior to tracking. Since the shape coverage of the model is fixed, such approaches do not directly accommodate incremental representation discovery during tracking. As a result, model shape coverage is decoupled from tracking, thereby limiting both processes in terms of scope and robustness. We present a novel deformable model framework that accommodates the incremental incorporation during tracking of new geometric primitives (lines, in addition to points) that are not explicitly captured in the initial deformable model but that are moving consistently with its image motion. As these new features are detected via consistency checks, they are added to the model, providing incremental soft constraints on the estimation of its rigid parameters. The consistency checks are based on trilinear relationships between geometric primitives. Consequently we not only increase both model scope and, ultimately, its higher-level shape coverage, but improve tracking robustness and accuracy, by directly employing the new features in both forward prediction and reconstruction. Our new formulation is a step towards automating model shape estimation and tracking, since it requires significantly reduced initial model hand-crafting. We demonstrate our approach on two separate image-based tracking domains, each involving complex 3D object shape and motion.",
author = "Cristian Sminchisescu and Dimitri Metaxas and Sven Dickinson",
year = "2001",
month = "12",
day = "1",
language = "English (US)",
volume = "1",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

Improving the scope of deformable model shape and motion estimation. / Sminchisescu, Cristian; Metaxas, Dimitri; Dickinson, Sven.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, 01.12.2001.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Improving the scope of deformable model shape and motion estimation

AU - Sminchisescu, Cristian

AU - Metaxas, Dimitri

AU - Dickinson, Sven

PY - 2001/12/1

Y1 - 2001/12/1

N2 - Previous approaches to deformable model shape estimation and tracking have assumed a fixed class of shapes representation (e.g., deformable superquadrics), initialized prior to tracking. Since the shape coverage of the model is fixed, such approaches do not directly accommodate incremental representation discovery during tracking. As a result, model shape coverage is decoupled from tracking, thereby limiting both processes in terms of scope and robustness. We present a novel deformable model framework that accommodates the incremental incorporation during tracking of new geometric primitives (lines, in addition to points) that are not explicitly captured in the initial deformable model but that are moving consistently with its image motion. As these new features are detected via consistency checks, they are added to the model, providing incremental soft constraints on the estimation of its rigid parameters. The consistency checks are based on trilinear relationships between geometric primitives. Consequently we not only increase both model scope and, ultimately, its higher-level shape coverage, but improve tracking robustness and accuracy, by directly employing the new features in both forward prediction and reconstruction. Our new formulation is a step towards automating model shape estimation and tracking, since it requires significantly reduced initial model hand-crafting. We demonstrate our approach on two separate image-based tracking domains, each involving complex 3D object shape and motion.

AB - Previous approaches to deformable model shape estimation and tracking have assumed a fixed class of shapes representation (e.g., deformable superquadrics), initialized prior to tracking. Since the shape coverage of the model is fixed, such approaches do not directly accommodate incremental representation discovery during tracking. As a result, model shape coverage is decoupled from tracking, thereby limiting both processes in terms of scope and robustness. We present a novel deformable model framework that accommodates the incremental incorporation during tracking of new geometric primitives (lines, in addition to points) that are not explicitly captured in the initial deformable model but that are moving consistently with its image motion. As these new features are detected via consistency checks, they are added to the model, providing incremental soft constraints on the estimation of its rigid parameters. The consistency checks are based on trilinear relationships between geometric primitives. Consequently we not only increase both model scope and, ultimately, its higher-level shape coverage, but improve tracking robustness and accuracy, by directly employing the new features in both forward prediction and reconstruction. Our new formulation is a step towards automating model shape estimation and tracking, since it requires significantly reduced initial model hand-crafting. We demonstrate our approach on two separate image-based tracking domains, each involving complex 3D object shape and motion.

UR - http://www.scopus.com/inward/record.url?scp=0035683328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035683328&partnerID=8YFLogxK

M3 - Conference article

VL - 1

JO - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

JF - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SN - 1063-6919

ER -