Sciweavers

Share
CVPR
2010
IEEE

Multi-View Object Class Detection With a 3D Geometric Model

9 years 2 months ago
Multi-View Object Class Detection With a 3D Geometric Model
This paper presents a new approach for multi-view object class detection. Appearance and geometry are treated as separate learning tasks with different training data. Our approach uses a part model which discriminatively learns the object appearance with spatial pyramids from a database of real images, and encodes the 3D geometry of the object class with a generative representation built from a database of synthetic models. The geometric information is linked to the 2D training data and allows to perform an approximate 3D pose estimation for generic object classes. The pose estimation provides an efficient method to evaluate the likelihood of groups of 2D part detections with respect to a full 3D geometry model in order to disambiguate and prune 2D detections and to handle occlusions. In contrast to other methods, neither tedious manual part annotation of training images nor explicit appearance matching between synthetic and real training data is required, which results in high geome...
Joerg Liebelt, Cordelia Schmid
Added 02 May 2010
Updated 14 May 2010
Type Conference
Year 2010
Where CVPR
Authors Joerg Liebelt, Cordelia Schmid
Comments (0)
books