Hypothesis Verification in Model Based Object Recognition with a Gaussian Error Model

Frédéric Jurie 1
1 image
LASMEA - Laboratoire des sciences et matériaux pour l'électronique et d'automatique
Abstract : The use of hypothesis verification is recurrent in the model based recognition literature. Small sets of features forming salient groups are paired with model features. Poses can be hypothesised from this small set of feature-to-feature correspondences. The verification of the pose consists in measuring how much model features transformed by the computed pose coincide with image features. When data involved in the initial pairing are noisy the pose is inaccurate and the verification is a difficult problem. In this paper we propose a robust hypothesis verification algorithm, assuming data error is Gaussian. Previous approaches using gaussian error model start from an initial set of correspondences and try to extend it feature by feature. This solution is not optimal. In this paper, the opposite strategy is adopted. Assuming the right pose belongs to a known volume of the pose space (including the initial pose) we take into account all of the correspondences compatible with this volume and refine iteratively this set of correspondences. This is our main contribution. We present experimental results obtained with 2D recognition proving that the proposed algorithm is fast and robust.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00548334
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 8:43:27 AM
Last modification on : Tuesday, June 5, 2018 - 6:00:02 PM

Links full text

Identifiers

Citation

Frédéric Jurie. Hypothesis Verification in Model Based Object Recognition with a Gaussian Error Model. European Conference on Computer Vision (ECCV '98), Jun 1998, Freiburg, Germany. pp.642--656, ⟨10.1007/BFb0054770⟩. ⟨inria-00548334⟩

Share

Metrics

Record views

113