TurboPixels : fast superpixels using geometric flows

We describe a geometric-flow-based algorithm for computing a dense oversegmentation of an image, often referred to as superpixels. It produces segments that, on one hand, respect local image boundaries, while, on the other hand, limiting undersegmentation through a compactness constraint. It is very...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 31(2009), 12 vom: 20. Dez., Seite 2290-7
1. Verfasser: Levinshtein, Alex (VerfasserIn)
Weitere Verfasser: Stere, Adrian, Kutulakos, Kiriakos N, Fleet, David J, Dickinson, Sven J, Siddiqi, Kaleem
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2009
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM192095552
003 DE-627
005 20231223192330.0
007 cr uuu---uuuuu
008 231223s2009 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2009.96  |2 doi 
028 5 2 |a pubmed24n0640.xml 
035 |a (DE-627)NLM192095552 
035 |a (NLM)19834148 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Levinshtein, Alex  |e verfasserin  |4 aut 
245 1 0 |a TurboPixels  |b fast superpixels using geometric flows 
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 01.02.2010 
500 |a Date Revised 16.10.2009 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a We describe a geometric-flow-based algorithm for computing a dense oversegmentation of an image, often referred to as superpixels. It produces segments that, on one hand, respect local image boundaries, while, on the other hand, limiting undersegmentation through a compactness constraint. It is very fast, with complexity that is approximately linear in image size, and can be applied to megapixel sized images with high superpixel densities in a matter of minutes. We show qualitative demonstrations of high-quality results on several complex images. The Berkeley database is used to quantitatively compare its performance to a number of oversegmentation algorithms, showing that it yields less undersegmentation than algorithms that lack a compactness constraint while offering a significant speedup over N-cuts, which does enforce compactness 
650 4 |a Journal Article 
700 1 |a Stere, Adrian  |e verfasserin  |4 aut 
700 1 |a Kutulakos, Kiriakos N  |e verfasserin  |4 aut 
700 1 |a Fleet, David J  |e verfasserin  |4 aut 
700 1 |a Dickinson, Sven J  |e verfasserin  |4 aut 
700 1 |a Siddiqi, Kaleem  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 31(2009), 12 vom: 20. Dez., Seite 2290-7  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:31  |g year:2009  |g number:12  |g day:20  |g month:12  |g pages:2290-7 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2009.96  |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 12  |b 20  |c 12  |h 2290-7