Stereo matching with linear superposition of layers

In this paper, we address stereo matching in the presence of a class of non-Lambertian effects, where image formation can be modeled as the additive superposition of layers at different depths. The presence of such effects makes it impossible for traditional stereo vision algorithms to recover depth...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 28(2006), 2 vom: 18. Feb., Seite 290-301
1. Verfasser: Tsin, Yanghai (VerfasserIn)
Weitere Verfasser: Kang, Sing Bing, Szeliski, Richard
Format: Aufsatz
Sprache:English
Veröffentlicht: 2006
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Evaluation Study Journal Article
LEADER 01000naa a22002652 4500
001 NLM160627257
003 DE-627
005 20231223090459.0
007 tu
008 231223s2006 xx ||||| 00| ||eng c
028 5 2 |a pubmed24n0536.xml 
035 |a (DE-627)NLM160627257 
035 |a (NLM)16468624 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Tsin, Yanghai  |e verfasserin  |4 aut 
245 1 0 |a Stereo matching with linear superposition of layers 
264 1 |c 2006 
336 |a Text  |b txt  |2 rdacontent 
337 |a ohne Hilfsmittel zu benutzen  |b n  |2 rdamedia 
338 |a Band  |b nc  |2 rdacarrier 
500 |a Date Completed 07.03.2006 
500 |a Date Revised 10.12.2019 
500 |a published: Print 
500 |a Citation Status MEDLINE 
520 |a In this paper, we address stereo matching in the presence of a class of non-Lambertian effects, where image formation can be modeled as the additive superposition of layers at different depths. The presence of such effects makes it impossible for traditional stereo vision algorithms to recover depths using direct color matching-based methods. We develop several techniques to estimate both depths and colors of the component layers. Depth hypotheses are enumerated in pairs, one from each layer, in a nested plane sweep. For each pair of depth hypotheses, matching is accomplished using spatial-temporal differencing. We then use graph cut optimization to solve for the depths of both layers. This is followed by an iterative color update algorithm which we proved to be convergent. Our algorithm recovers depth and color estimates for both synthetic and real image sequences 
650 4 |a Evaluation Study 
650 4 |a Journal Article 
700 1 |a Kang, Sing Bing  |e verfasserin  |4 aut 
700 1 |a Szeliski, Richard  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 28(2006), 2 vom: 18. Feb., Seite 290-301  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:28  |g year:2006  |g number:2  |g day:18  |g month:02  |g pages:290-301 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 28  |j 2006  |e 2  |b 18  |c 02  |h 290-301