Matching objects across the textured-smooth continuum
conference contribution
posted on 2012-01-01, 00:00authored byOgnjen Arandjelovic
The problem of 3D object recognition is of immense practical importance, with the last decade witnessing a number of breakthroughs in the state of the art. Most of the previous work has focused on the matching of textured objects using local appearance descriptors extracted around salient image points. The recently proposed bag of boundaries method was the first to address directly the problem of matching smooth objects using boundary features. However, no previous work has attempted to achieve a holistic treatment of the problem by jointly using textural and shape features which is what we describe herein. Due to the complementarity of the two modalities, we fuse the corresponding matching scores and learn their relative weighting in a data specific manner by optimizing discriminative performance on synthetically distorted data. For the textural description of an object we adopt a representation in the form of a histogram of SIFT based visual words. Similarly the apparent shape of an object is represented by a histogram of discretized features capturing local shape. On a large public database of a diverse set of objects, the proposed method is shown to outperform significantly both purely textural and purely shape based approaches for matching across viewpoint variation.
History
Event
Australasian Conference on Robotics and Automation (2012: Wellington, New Zealand)
Pagination
1 - 8
Publisher
Australian Robotics and Automation Association
Location
Wellington, New Zealand
Place of publication
Sydney, N.S.W.
Start date
2012-12-03
End date
2012-12-05
ISSN
1448-2053
ISBN-13
9780980740431
Language
eng
Publication classification
E1 Full written paper - refereed
Copyright notice
2012, Australian Robotics and Automation Association
Title of proceedings
ACRA 2012 : Proceedings of Australasian Conference on Robotics and Automation