We explore the performance of a number of popular feature detectors and descriptors in matching 3D object features across viewpoints and lighting conditions. To this end we design a method, based on intersecting epipolar constraints, for providing ground truth correspondence automatically. We collect a database of 100 objects viewed from 144 calibrated viewpoints under three different lighting conditions. We find that the combination of Hessian-affine feature finder and SIFT features is most robust to viewpoint change. Harris-affine combined with SIFT and Hessian-affine combined with shape context descriptors were best respectively for lighting changes and scale changes. We also find that no detector-descriptor combination performs well with viewpoint changes of more than 25-30/spl deg/.
Evaluation of features detectors and descriptors based on 3D objects
Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 ; 1 ; 800-807 Vol. 1
01.01.2005
730437 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Evaluation of Features Detectors and Descriptors Based on 3D objects
British Library Conference Proceedings | 2005
|Evaluation of Features Detectors and Descriptors based on 3D Objects
British Library Online Contents | 2007
|Automatically scoring LADAR detectors using target descriptors
Tema Archiv | 2001
|Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking
British Library Online Contents | 2011
|Classification of Underwater Objects using Fourier Descriptors
British Library Conference Proceedings | 1999
|