Tracking-by-Detection of 3D Human Shapes: From Surfaces to Volumes

3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences....

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 40; číslo 8; s. 1994 - 2008
Hlavní autoři:	Huang, Chun-Hao Paul, Allain, Benjamin, Boyer, Edmond, Franco, Jean-Sebastien, Tombari, Federico, Navab, Nassir, Ilic, Slobodan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.08.2018 The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Témata:	3D tracking-by-detection centroidal Voronoi tessellation Computer Science Computer Vision and Pattern Recognition Data models Deformable models Deformation discriminative associations Iterative closest point algorithm Iterative methods random forest Robustness Shape Shape memory Shape recognition Shape tracking Stability analysis State of the art Surface reconstruction Tessellation Three-dimensional displays Tracking Tracking errors Visual observation 3D tracking-by-detection centroidal Voronoi tessellation random forest Shape tracking discriminative associations
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	3D Human shape tracking consists in fitting a template model to temporal sequences of visual observations. It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences. Most current approaches follow the Iterative-Closest-Point (ICP) paradigm, where the association step is carried out by searching for the nearest neighbors. It fails when large deformations occur and errors in the association tend to propagate over time. In this paper, we propose a discriminative alternative for the association, that leverages random forests to infer correspondences in one shot. Regardless the choice of shape parameterizations, being surface or volumetric meshes, we convert 3D shapes to volumetric distance fields and thereby design features to train the forest. We investigate two ways to draw volumetric samples: voxels of regular grids and cells from Centroidal Voronoi Tessellation (CVT). While the former consumes considerable memory and in turn limits us to learn only subject-specific correspondences, the latter yields much less memory footprint by compactly tessellating the interior space of a shape with optimal discretization. This facilitates the use of larger cross-subject training databases, generalizes to different human subjects and hence results in less overfitting and better detection. The discriminative correspondences are successfully integrated to both surface and volumetric deformation frameworks that recover human shape poses, which we refer to as 'tracking-by-detection of 3D human shapes.' It allows for large deformations and prevents tracking errors from being accumulated. When combined with ICP for refinement, it proves to yield better accuracy in registration and more stability when tracking over time. Evaluations on existing datasets demonstrate the benefits with respect to the state-of-the-art.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	0162-8828 1939-3539 2160-9292 1939-3539
DOI:	10.1109/TPAMI.2017.2740308