Record Details

Aspect graph construction with noisy feature detectors

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Aspect graph construction with noisy feature detectors
 
Creator ROY, SD
CHAUDHURY, S
BANERJEE, S
 
Subject projection aspect graph
object recognition
automatic-generation
vision
model
aspect graph
aspect graph construction algorithm
aspects
classes
feature detection errors
noisy sensor data
 
Description Many three-dimensional (3-D) object recognition strategies use aspect graphs to represent objects in the model base. A crucial factor in the success of these object recognition strategies is the accurate construction of the aspect graph, its ease of creation, and the extent to which it can represent all views of the object for a given setup. Factors such as noise and nonadaptive thresholds may introduce errors in the feature detection process. This paper presents a characterization of errors in aspect graphs, as well as an algorithm for estimating aspect graphs, given noisy sensor data. We present extensive results of our strategies applied on a reasonably complex experimental set, and demonstrate applications to a robust 3-D object recognition problem.
 
Publisher IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
 
Date 2011-07-31T21:21:15Z
2011-12-26T12:53:09Z
2011-12-27T05:40:20Z
2011-07-31T21:21:15Z
2011-12-26T12:53:09Z
2011-12-27T05:40:20Z
2003
 
Type Article
 
Identifier IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 33(2), 340-351
1083-4419
http://dx.doi.org/10.1109/TSMCB.2003.810445
http://dspace.library.iitb.ac.in/xmlui/handle/10054/8241
http://hdl.handle.net/10054/8241
 
Language en