Non-Rigid Object Detection with LocalInterleaved Sequential Alignment (LISA)

This paper shows that the successively evaluated features used in a sliding window detection process to decide about object presence/absence also contain knowledge about object deformation. We exploit these detection features to estimate the object deformation. Estimated deformation is then immediat...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 36(2014), 4 vom: 01. Apr., Seite 731-43
1. Verfasser: Zimmermann, Karel (VerfasserIn)
Weitere Verfasser: Hurych, David, Svoboda, Tomáš
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2014
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 NLM252590724
003 DE-627
005 20231224164432.0
007 cr uuu---uuuuu
008 231224s2014 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2013.171  |2 doi 
028 5 2 |a pubmed24n0842.xml 
035 |a (DE-627)NLM252590724 
035 |a (NLM)26353196 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Zimmermann, Karel  |e verfasserin  |4 aut 
245 1 0 |a Non-Rigid Object Detection with LocalInterleaved Sequential Alignment (LISA) 
264 1 |c 2014 
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 27.11.2015 
500 |a Date Revised 10.09.2015 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a This paper shows that the successively evaluated features used in a sliding window detection process to decide about object presence/absence also contain knowledge about object deformation. We exploit these detection features to estimate the object deformation. Estimated deformation is then immediately applied to not yet evaluated features to align them with the observed image data. In our approach, the alignment estimators are jointly learned with the detector. The joint process allows for the learning of each detection stage from less deformed training samples than in the previous stage. For the alignment estimation we propose regressors that approximate non-linear regression functions and compute the alignment parameters extremely fast 
650 4 |a Journal Article 
650 4 |a Research Support, Non-U.S. Gov't 
700 1 |a Hurych, David  |e verfasserin  |4 aut 
700 1 |a Svoboda, Tomáš  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 36(2014), 4 vom: 01. Apr., Seite 731-43  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:36  |g year:2014  |g number:4  |g day:01  |g month:04  |g pages:731-43 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2013.171  |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 36  |j 2014  |e 4  |b 01  |c 04  |h 731-43