Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Generalized exemplar-based full pose estimation from 2D images without correspondences|
|Citation:||Proceedings of the 2012 International Conference on Digital Image Computing Techniques and Applications, 2012 / pp.1-8|
|Conference Name:||International Conference on Digital Image Computing Techniques and Applications (DICTA) (03 Dec 2012 - 05 Dec 2012 : Fremantle, WA)|
|Damien Teney, Justus Piater|
|Abstract:||This paper addresses the problem of full pose estimation of objects in 2D images, using registered 2D examples as training data. We present a general formulation of the problem, which departs from traditional approaches by not focusing on one specific type of image features. The proposed algorithm avoids relying on specific model-to-scene correspondences, allowing using similar-looking and generally unmatchable features. We effectively demonstrate this capability by applying the method to edge segments. Our algorithm uses successive histogrambased and probabilistic evaluations, which ultimately recover a complete description of the probability distribution of the pose of the object, in the 6 degree-of-freedom 3D pose space, thereby accounting for the inherent ambiguities in the 2D input data. Furthermore, we propose, in a rigorous framework, an efficient procedure for fusing multiple sources of evidence, such as multiple registered 2D views of the same scene. The proposed method is evaluated qualitatively and quantitatively on synthetic and real test images. It shows promising results under challenging conditions, including occlusions and heavy clutter, while being capable of handling objects with little texture and detail.|
|Appears in Collections:||Computer Science publications|
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.