Please use this identifier to cite or link to this item: http://dx.doi.org/10.18419/opus-2475
Authors: Leibe, Bastian
Hetzel, Günter
Levi, Paul
Title: Local feature histograms for object recognition from range images
Issue Date: 2001
metadata.ubs.publikation.typ: Arbeitspapier
Series/Report no.: Technischer Bericht / Universität Stuttgart, Fakultät Informatik, Elektrotechnik und Informationstechnik;2001,6
URI: http://nbn-resolving.de/urn:nbn:de:bsz:93-opus-8986
http://elib.uni-stuttgart.de/handle/11682/2492
http://dx.doi.org/10.18419/opus-2475
Abstract: In this paper, we explore the use of local feature histograms for view-based recognition of free-form objects from range images. Our approach uses a set of local features that are easy to calculate and robust to partial occlusions. By combining them in a multidimensional histogram, we can obtain highly discriminative classifiers without having to solve a segmentation problem. The system achieves above 91% recognition accuracy on a database of almost 2000 full-sphere views of 30 free-form objects, with only minimal space requirements. In addition, since it only requires the calculation of very simple features, it is extremely fast and can achieve real-time recognition performance.
Appears in Collections:05 Fakultät Informatik, Elektrotechnik und Informationstechnik

Files in This Item:
File Description SizeFormat 
TR-2001-06.pdf611,56 kBAdobe PDFView/Open


Items in OPUS are protected by copyright, with all rights reserved, unless otherwise indicated.