Book chapter
Graspable parts recognition in Man-Made 3D shapes
Computer Vision – ACCV 2012: 11th Asian Conference on Computer Vision, Daejeon, Korea, November 5-9, 2012, Revised Selected Papers, Part II, Vol.7725, pp.552-564
Springer Berlin Heidelberg
2013
Abstract
We address the problem of automatic recognition of graspable parts in man-made 3D shapes, which exhibit high intra-class variability that cannot be captured with geometric descriptors alone. We observe that, in the presence of significant geometric and topological variations, the context of a part within a 3D shape provides important cues about its functionality. We propose to model the context as structural relationships between shape parts and use them, in addition to part geometry, as cues for identifying automatically the graspable parts. We design a set of spatial relationships that can be extracted from general shapes. Then, we propose a new similarity measure that captures a part context and enables better recognition of graspable parts. We use this property to design a classifier that learns the semantics of a shape part. We demonstrate that our approach outperforms the state-of-the-art approaches that are purely geometric-based.
Details
- Title
- Graspable parts recognition in Man-Made 3D shapes
- Authors/Creators
- H. Laga (Author/Creator) - University of South Australia
- Contributors
- K.M. Lee (Editor)Y. Matsushita (Editor)J.M. Rehg (Editor)
- Publication Details
- Computer Vision – ACCV 2012: 11th Asian Conference on Computer Vision, Daejeon, Korea, November 5-9, 2012, Revised Selected Papers, Part II, Vol.7725, pp.552-564
- Publisher
- Springer Berlin Heidelberg
- Identifiers
- 991005541304207891
- Copyright
- 2013 Springer-Verlag Berlin Heidelberg
- Murdoch Affiliation
- Murdoch University
- Language
- English
- Resource Type
- Book chapter
- Additional Information
- Series title: Lecture Notes in Computer Science; Vol. 7725 ISSN: 0302-9743.
Metrics
45 Record Views