Record Details

3D object recognition using Bayesian geometric hashing and pose clustering

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title 3D object recognition using Bayesian geometric hashing and pose clustering
 
Creator SEHGAL, A
DESAI, UB
 
Subject geometric hashing
pose clustering
object recognition
 
Description Geometric hashing (GH) and partial pose clustering are well-known algorithms for pattern recognition. However, the performance of both these algorithms degrades rapidly with an increase in scene clutter and the measurement uncertainty in the detected features. The primary contribution of this paper is the formulation of a framework that unifies the GH and the partial pose clustering paradigms for pattern recognition in cluttered scenes. The proposed scheme has a better discrimination capability as compared to the GA algorithm, thus improving recognition accuracy. The scheme is incorporated in a Bayesian MLE framework to make it robust to the presence of sensor noise. It is able to handle partial occlusions, is robust to measurement uncertainty in the data features and to the presence of spurious scene features (scene clutter). An efficient hash table representation of 3D features extracted from range images is also proposed. Simulations with real and synthetic 2D/3D objects show that the scheme performs better than the GH algorithm in scenes with a large amount of clutter. (C) 2002 on behalf of Pattern Recognition Society.
 
Publisher PERGAMON-ELSEVIER SCIENCE LTD
 
Date 2011-08-22T09:08:02Z
2011-12-26T12:56:17Z
2011-12-27T05:44:44Z
2011-08-22T09:08:02Z
2011-12-26T12:56:17Z
2011-12-27T05:44:44Z
2003
 
Type Article
 
Identifier PATTERN RECOGNITION, 36(3), 765-780
0031-3203
http://dx.doi.org/10.1016/S0031-3203(02)00102-4
http://dspace.library.iitb.ac.in/xmlui/handle/10054/10386
http://hdl.handle.net/10054/10386
 
Language en