A probabilistic framework for 3D visual object representation

We present an object representation framework that encodes probabilistic spatial relations between 3D features and organizes these features in a hierarchy. Features at the bottom of the hierarchy are bound to local 3D descriptors. Higher level features recursively encode probabilistic spatial config...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 31(2009), 10 vom: 16. Okt., Seite 1790-803
1. Verfasser: Detry, Renaud (VerfasserIn)
Weitere Verfasser: Pugeault, Nicolas, Piater, Justus H
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2009
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article Research Support, Non-U.S. Gov't
LEADER 01000naa a22002652 4500
001 NLM190819251
003 DE-627
005 20231223190019.0
007 cr uuu---uuuuu
008 231223s2009 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2009.64  |2 doi 
028 5 2 |a pubmed24n0636.xml 
035 |a (DE-627)NLM190819251 
035 |a (NLM)19696450 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Detry, Renaud  |e verfasserin  |4 aut 
245 1 2 |a A probabilistic framework for 3D visual object representation 
264 1 |c 2009 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 06.10.2009 
500 |a Date Revised 21.08.2009 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a We present an object representation framework that encodes probabilistic spatial relations between 3D features and organizes these features in a hierarchy. Features at the bottom of the hierarchy are bound to local 3D descriptors. Higher level features recursively encode probabilistic spatial configurations of more elementary features. The hierarchy is implemented in a Markov network. Detection is carried out by a belief propagation algorithm, which infers the pose of high-level features from local evidence and reinforces local evidence from globally consistent knowledge, effectively producing a likelihood for the pose of the object in the detection scene. We also present a simple learning algorithm that autonomously builds hierarchies from local object descriptors. We explain how to use our framework to estimate the pose of a known object in an unknown scene. Experiments demonstrate the robustness of hierarchies to input noise, viewpoint changes, and occlusions 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Pugeault, Nicolas  |e verfasserin  |4 aut 
700 1 |a Piater, Justus H  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 31(2009), 10 vom: 16. Okt., Seite 1790-803  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:31  |g year:2009  |g number:10  |g day:16  |g month:10  |g pages:1790-803 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2009.64  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 31  |j 2009  |e 10  |b 16  |c 10  |h 1790-803