Towards multi-view object class detection

Alexander Thomas (1) , Vittorio Ferrari (2) , Bastian Leibe (3) , Tinne Tuytelaars (4) , Bernt Schiele (5) , Luc van Gool (3)

1 KU Leuven - Catholic University of Leuven = Katholieke Universiteit Leuven
2 LEAR - Learning and recognition in vision
3 ETH Zürich - Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology [Zürich]
4 ESAT - Department of Electrical Engineering [Leuven]
5 Department of Computer Science

We present a novel system for generic object class detection. In contrast to most existing systems which focus on a single viewpoint or aspect, our approach can detect object instances from arbitrary viewpoints. This is achieved by combining the Implicit Shape Model for object class detection proposed by Leibe and Schiele with the multi-view specific object recognition system of Ferrari et al. After learning single-view codebooks, these are interconnected by so-called activation links, obtained through multi-view region tracks across different training views of individual object instances. During recognition, these integrated codebooks work together to determine the location and pose of the object. Experimental results demonstrate the viability of the approach and compare it to a bank of independent single-view detectors.

Mots clés: object detection; multiple views; local features

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Alexander Thomas, Vittorio Ferrari, Bastian Leibe, Tinne Tuytelaars, Bernt Schiele, et al.. Towards multi-view object class detection. IEEE Conference on Computer Vision & Pattern Recognition (CPRV '06), Jun 2006, New York, United States. pp.1589, ⟨10.1109/CVPR.2006.311⟩. ⟨inria-00548577⟩