Sciweavers

Share
CVPR
2007
IEEE

Flexible Object Models for Category-Level 3D Object Recognition

10 years 7 months ago
Flexible Object Models for Category-Level 3D Object Recognition
Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we propose a novel framework for visual object recognition where object classes are represented by assemblies of partial surface models (PSMs) obeying loose local geometric constraints. The PSMs themselves are formed of dense, locally rigid assemblies of image features. Since our model only enforces local geometric consistency, both at the level of model parts and at the level of individual features within the parts, it is robust to viewpoint changes and intra-class variability. The proposed approach has been implemented, and it outperforms the state-of-the-art algorithms for object detection and localization recently compared in [14] on the Pascal 2005 VOC Challenge Cars Test 1 data.
Akash Kushal, Cordelia Schmid, Jean Ponce
Added 12 Oct 2009
Updated 12 Oct 2009
Type Conference
Year 2007
Where CVPR
Authors Akash Kushal, Cordelia Schmid, Jean Ponce
Comments (0)
books