Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Probabilistic object models for pose estimation in 2D images|
|Citation:||Pattern Recognition, 2011 / Mester, R., Felsberg, M. (ed./s), vol.6835 LNCS, pp.336-345|
|Series/Report no.:||Lecture Notes in Computer Science|
|Conference Name:||Joint Pattern Recognition Symposium (DAGM) (31 Aug 2011 - 02 Sep 2011 : Frankfurt am Main, Germany)|
|Damien TeneyJustus Piater|
|Abstract:||We present a novel way of performing pose estimation of known objects in 2D images. We follow a probabilistic approach for modeling objects and representing the observations. These object models are suited to various types of observable visual features, and are demonstrated here with edge segments. Even imperfect models, learned from single stereo views of objects, can be used to infer the maximumlikelihood pose of the object in a novel scene, using a Metropolis-Hastings MCMC algorithm, given a single, calibrated 2D view of the scene. The probabilistic approach does not require explicit model-to-scene correspondences, allowing the system to handle objects without individuallyidentifiable features. We demonstrate the suitability of these object models to pose estimation in 2D images through qualitative and quantitative evaluations, as we show that the pose of textureless objects can be recovered in scenes with clutter and occlusion.|
|Description:||LNCS, volume 6835|
|Rights:||© Springer-Verlag Berlin Heidelberg 2011|
|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.