DocumentCode :
1446542
Title :
Robust affine structure matching for 3D object recognition
Author :
Cass, Todd A.
Author_Institution :
Xerox Palo Alto Res. Center, CA, USA
Volume :
20
Issue :
11
fYear :
1998
fDate :
11/1/1998 12:00:00 AM
Firstpage :
1265
Lastpage :
1274
Abstract :
We consider model-based object localization based on local geometric feature matching between the model and the image data. The method is based on geometric constraint analysis, working in transformation space. We present a formal method which guarantees finding all feasible matchings in polynomial time. From there we develop more computationally feasible algorithms based on conservative approximations of the formal method. Additionally, our formalism relates object localization, affine model indexing, and structure from multiple views to one another
Keywords :
computational geometry; object recognition; 3D object recognition; affine model indexing; formal method; geometric constraint analysis; local geometric feature matching; model-based object localization; robust affine structure matching; Computational geometry; Computational modeling; Image segmentation; Indexing; Layout; Measurement uncertainty; Object recognition; Polynomials; Robustness; Solid modeling;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/34.730560
Filename :
730560
Link To Document :
بازگشت