Skip to Main content Skip to Navigation
Conference papers

Improving the Scope of Deformable Model Shape and Motion Estimation

Cristian Sminchisescu 1 Dimitris Metaxas 2 Sven Dickinson 3
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
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.
Document type :
Conference papers
Complete list of metadata

Cited literature [28 references]  Display  Hide  Download
Contributor : Team Perception Connect in order to contact the contributor
Submitted on : Tuesday, May 3, 2011 - 9:28:21 AM
Last modification on : Monday, December 28, 2020 - 3:44:02 PM
Long-term archiving on: : Friday, November 9, 2012 - 10:21:31 AM


Files produced by the author(s)





Cristian Sminchisescu, Dimitris Metaxas, Sven Dickinson. Improving the Scope of Deformable Model Shape and Motion Estimation. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR '01), Dec 2001, Kauai, United States. pp.485--492, ⟨10.1109/CVPR.2001.990514⟩. ⟨inria-00590157⟩



Record views


Files downloads