Tao, Lili and Matuszewski, Bogdan (2013) Deformable Shape Reconstruction from Monocular Video with Manifold Forests. Lecture Notes in Computer Science, 8047 (1). pp. 28-36. ISSN 0302-9743
Full text not available from this repository.
Official URL: http://dx.doi.org/10.1007/978-3-642-40261-6_3
A common approach to recover structure of 3D deformable scene and camera motion from uncalibrated 2D video sequences is to assume that shapes can be accurately represented in linear subspaces. These methods are simple and have been proven effective for reconstructions of objects with relatively small deformations, but have considerable limitations when the deformations are large or complex. This paper describes a novel approach to reconstruction of deformable objects utilising a manifold decision forest technique. The key contribution of this work is the use of random decision forests for the shape manifold learning. The learned manifold defines constraints imposed on the reconstructed shapes. Due to nonlinear structure of the learned manifold, this approach is more suitable to deal with large and complex object deformations when compared to the linear constraints. © 2013 Springer-Verlag.
|Additional Information:||15th International Conference on Computer Analysis of Images and Patterns, CAIP 2013, 27 August 2013 through 29 August 2013, 9783642402609 (ISBN)|
|Uncontrolled Keywords (separate with ;):||Complex objects; Deformable object; Deformable shapes; Linear constraints; Linear subspace; Monocular video; Nonlinear structure; Small deformations; Decision trees; Forestry; Image analysis; Video signal processing; Deformation; Decision Making; Trees|
|Subjects:||Engineering > Civil engineering|
|Schools:||Faculty of Science and Technology > School of Engineering|
|Deposited By:||Helen Cooper|
|Deposited On:||25 Jul 2014 08:22|
|Last Modified:||09 Aug 2016 15:20|
Downloads per month over past year
Downloads for past 30 days
Repository Staff Only: item control page