Fast and cheap object recognition by linear combination of views

Abstract : In this paper, we present a real-time algorithm for 3D object detection in images. Our method relies on the Ullman and Basri theory which claims that the same object under different transformations can often be expressed as the linear combinations of a small number of its views. Thus, in our framework the 3D object is modelized by two 2D images associated with spatial relationships described by local invariant feature points. The recognition is based on feature points detection and alignment with the model. Important theoretical optimizations have been introduced in order to speed up the original full alignment scheme and to reduce the model size in memory. The recognition process is based on a very fast recognition loop which quickly eliminates outliers. The proposed approach does not require a segmentation stage, and it is applicable to cluttered scenes. The small size of the model and the rapidity of the detection make this algorithm particularly suitable for real-time applications on mobile devices.
Type de document :
Communication dans un congrès
ACM. Conference on Image and Video Retrieval (CIVR'07), Jul 2007, Amsterdam, Netherlands, Netherlands. 2007
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01541585
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : lundi 19 juin 2017 - 12:04:09
Dernière modification le : jeudi 19 avril 2018 - 14:38:06

Identifiants

  • HAL Id : hal-01541585, version 1

Citation

Jérôme Revaud, Guillaume Lavoué, Yasuo Ariki, Atilla Baskurt. Fast and cheap object recognition by linear combination of views. ACM. Conference on Image and Video Retrieval (CIVR'07), Jul 2007, Amsterdam, Netherlands, Netherlands. 2007. 〈hal-01541585〉

Partager

Métriques

Consultations de la notice

106