Are we ready to segment consumer stereo videos? The amount of this data type is rapidly increasing and encompasses rich information of appearance, motion and depth cues. However, the segmentation of such data is still largely unexplored. First, we propose therefore a new benchmark: videos, annotations and metrics to measure progress on this emerging challenge. Second, we evaluate several state of the art segmentation methods and propose a novel ensemble method based on recent spectral theory. This combines existing image and video segmentation techniques in an efficient scheme. Finally, we propose and integrate into this model a novel regressor, learnt to optimize the stereo segmentation performance directly via a differentiable proxy. The regressor makes our segmentation ensemble adaptive to each stereo video and outperforms the segmentations of the ensemble as well as a most recent RGB-D segmentation technique.

Towards segmenting consumer stereo videos: benchmark, baselines and ensembles / Chiu, W-C; Galasso, F; Fritz, M. - 10115:(2017), pp. 378-395. (Intervento presentato al convegno Asian Conference on Computer Vision, ACCV 2016 tenutosi a Taipei; Taiwan) [10.1007/978-3-319-54193-8_24].

Towards segmenting consumer stereo videos: benchmark, baselines and ensembles

Galasso F;
2017

Abstract

Are we ready to segment consumer stereo videos? The amount of this data type is rapidly increasing and encompasses rich information of appearance, motion and depth cues. However, the segmentation of such data is still largely unexplored. First, we propose therefore a new benchmark: videos, annotations and metrics to measure progress on this emerging challenge. Second, we evaluate several state of the art segmentation methods and propose a novel ensemble method based on recent spectral theory. This combines existing image and video segmentation techniques in an efficient scheme. Finally, we propose and integrate into this model a novel regressor, learnt to optimize the stereo segmentation performance directly via a differentiable proxy. The regressor makes our segmentation ensemble adaptive to each stereo video and outperforms the segmentations of the ensemble as well as a most recent RGB-D segmentation technique.
2017
Asian Conference on Computer Vision, ACCV 2016
computer vision; machine Learning; video segmentation
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
Towards segmenting consumer stereo videos: benchmark, baselines and ensembles / Chiu, W-C; Galasso, F; Fritz, M. - 10115:(2017), pp. 378-395. (Intervento presentato al convegno Asian Conference on Computer Vision, ACCV 2016 tenutosi a Taipei; Taiwan) [10.1007/978-3-319-54193-8_24].
File allegati a questo prodotto
File Dimensione Formato  
Chiu_Segmenting_2017.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 2.63 MB
Formato Adobe PDF
2.63 MB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1317756
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact