File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Scalable data parallel implementations of object recognition on connection machine CM-5

TitleScalable data parallel implementations of object recognition on connection machine CM-5
Authors
Issue Date1994
PublisherI E E E, Computer Society. The Journal's web site is located at http://csdl2.computer.org/persagen/DLPublication.jsp?pubtype=p&acronym=HICSS
Citation
Proceedings Of The Hawaii International Conference On System Sciences, 1994, v. 2, p. 130-139 How to Cite?
AbstractObject recognition involves identifying known objects in a given scene. It plays a key role in image understanding, a Grand Challenge problem. Geometric hashing has been recently proposed as a technique for model based object recognition in occluded scenes. In this paper, we present scalable data parallel algorithms for geometric hashing on Connection Machine CM-5. Given a scene consisting of S feature points, the parallel algorithm for one probe of the recognition-phase takes O(S/P log S) time on a fat tree based architecture. We perform implementations of the proposed algorithms on CM-5, after a careful study of its computation and communication characteristics. Earlier parallel implementations of the geometric hashing algorithm have been carried out on the Connection Machine CM-2 using O(Mn3) processors, where M is the number of models in the database and n is the number of features in each model. In these implementations, the number of processors is independent of the size of the scene but depends on the size of model database which is usually very large. The algorithms presented in this paper significantly improve on the number of processors employed while at the same time achieve much superior time performance. Earlier implementations claim 700 to 1300 msec for one probe of the recognition phase, assuming 200 feature points in the scene on an 8 K processor CM-2. Our implementations run on a P processor Connection Machine CM-5, such that 1≤P≤S. Our results show that a probe of the recognition phase for a scene consisting of 1024 feature points takes less than 10 msec on a 256 processor CM-5. The implementations developed in this paper require number of processors independent of the size of the model database and are also scalable with the machine size.
Persistent Identifierhttp://hdl.handle.net/10722/151801
ISSN

 

DC FieldValueLanguage
dc.contributor.authorKhokhar, Ashfaqen_US
dc.contributor.authorPrasanna, Viktoren_US
dc.contributor.authorWang, ChoLien_US
dc.date.accessioned2012-06-26T06:29:44Z-
dc.date.available2012-06-26T06:29:44Z-
dc.date.issued1994en_US
dc.identifier.citationProceedings Of The Hawaii International Conference On System Sciences, 1994, v. 2, p. 130-139en_US
dc.identifier.issn1060-3425en_US
dc.identifier.urihttp://hdl.handle.net/10722/151801-
dc.description.abstractObject recognition involves identifying known objects in a given scene. It plays a key role in image understanding, a Grand Challenge problem. Geometric hashing has been recently proposed as a technique for model based object recognition in occluded scenes. In this paper, we present scalable data parallel algorithms for geometric hashing on Connection Machine CM-5. Given a scene consisting of S feature points, the parallel algorithm for one probe of the recognition-phase takes O(S/P log S) time on a fat tree based architecture. We perform implementations of the proposed algorithms on CM-5, after a careful study of its computation and communication characteristics. Earlier parallel implementations of the geometric hashing algorithm have been carried out on the Connection Machine CM-2 using O(Mn3) processors, where M is the number of models in the database and n is the number of features in each model. In these implementations, the number of processors is independent of the size of the scene but depends on the size of model database which is usually very large. The algorithms presented in this paper significantly improve on the number of processors employed while at the same time achieve much superior time performance. Earlier implementations claim 700 to 1300 msec for one probe of the recognition phase, assuming 200 feature points in the scene on an 8 K processor CM-2. Our implementations run on a P processor Connection Machine CM-5, such that 1≤P≤S. Our results show that a probe of the recognition phase for a scene consisting of 1024 feature points takes less than 10 msec on a 256 processor CM-5. The implementations developed in this paper require number of processors independent of the size of the model database and are also scalable with the machine size.en_US
dc.languageengen_US
dc.publisherI E E E, Computer Society. The Journal's web site is located at http://csdl2.computer.org/persagen/DLPublication.jsp?pubtype=p&acronym=HICSSen_US
dc.relation.ispartofProceedings of the Hawaii International Conference on System Sciencesen_US
dc.titleScalable data parallel implementations of object recognition on connection machine CM-5en_US
dc.typeConference_Paperen_US
dc.identifier.emailWang, ChoLi:clwang@cs.hku.hken_US
dc.identifier.authorityWang, ChoLi=rp00183en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.scopuseid_2-s2.0-0028014773en_US
dc.identifier.volume2en_US
dc.identifier.spage130en_US
dc.identifier.epage139en_US
dc.publisher.placeUnited Statesen_US
dc.identifier.scopusauthoridKhokhar, Ashfaq=7004753270en_US
dc.identifier.scopusauthoridPrasanna, Viktor=7005057102en_US
dc.identifier.scopusauthoridWang, ChoLi=7501646188en_US

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats