Learning to recognize 3D objects using sparse depth and intensity information

McCane, Brendan, Caelli, Terry and De Vel, Olivier 1997, Learning to recognize 3D objects using sparse depth and intensity information, International Journal of Pattern Recognition and Artificial Intelligence, vol. 11, no. 6, pp. 909-931, doi: 10.1142/s021800149700041x.

Title Learning to recognize 3D objects using sparse depth and intensity information
Author(s) McCane, Brendan
Caelli, TerryORCID iD for Caelli, Terry orcid.org/0000-0001-9281-2556
De Vel, Olivier
Journal name International Journal of Pattern Recognition and Artificial Intelligence
Volume number 11
Issue number 6
Start page 909
End page 931
Total pages 23
Publication date 1997-01-01
ISSN 0218-0014
Keyword(s) Science & Technology
Computer Science, Artificial Intelligence
Computer Science
object recognition
machine learning
sparse depth
conditional rule generation
fuzzy clustering
Summary In this paper we further explore the use of machine learning (ML) for the recognition of 3D objects in isolation or embedded in scenes. Of particular interest is the use of a recent ML technique (specifically CRG — Conditional Rule Generation) which generates descriptions of objects in terms of object parts and part-relational attribute bounds. We show how this technique can be combined with intensity-based model and scene–views to locate objects and their pose. The major contributions of this paper are: the extension of the CRG classifier to incorporate fuzzy decisions (FCRG), the application of the FCRG classifier to the problem of learning 3D objects from 2D intensity images, the study of the usefulness of sparse depth data in regards to recognition performance, and the implementation of a complete object recognition system that does not rely on perfect or synthetic data. We report a recognition rate of 80% for unseen single object scenes in a database of 18 non-trivial objects.
Language eng
DOI 10.1142/s021800149700041x
Indigenous content off
Field of Research 0801 Artificial Intelligence and Image Processing
1702 Cognitive Sciences
HERDC Research category C1 Refereed article in a scholarly journal
Persistent URL http://hdl.handle.net/10536/DRO/DU:30138524

Connect to link resolver
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 6 times in TR Web of Science
Scopus Citation Count Cited 8 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 27 Abstract Views  -  Detailed Statistics
Created: Mon, 08 Jun 2020, 15:31:36 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.