This paper presents a parts-based method for classifying scenes of 3D objects into a set of pre-determined object classes. Working at the part level, as opposed to the whole object level, enables a more flexible class representation and allows scenes in which the query object is significantly occluded to be classified. In our approach, parts are extracted from training objects and grouped into part classes using a hierarchical clustering algorithm. Each part class is represented as a collection of semi-local shape features and can be used to perform pan class recognition. A mapping from part classes to object classes is derived from the learned part classes and known object classes. At run-time, a 3D query scene is sampled, local shape features are computed, and the object class is determined using the learned pan classes and the pan-to-object mapping. Classifying novel 3D scenes of vehicles into eight classes demonstrate the approach.
Parts-based 3D object classification
2004-01-01
687431 byte
Conference paper
Electronic Resource
English
Parts-Based 3D Object Classification
British Library Conference Proceedings | 2004
|Object Classification by Functional Parts
British Library Conference Proceedings | 2002
|Object Classification Considering Movability Based on Shape Features with Parts Decomposition
British Library Online Contents | 2015
|Foreground Object Detection by Motion-based Grouping of Object Parts
Springer Verlag | 2014
|Foreground Object Detection by Motion-based Grouping of Object Parts
Springer Verlag | 2014
|