Cotemporal Multi-View Video Segmentation - Archive ouverte HAL Access content directly
Conference Papers Year :

Cotemporal Multi-View Video Segmentation

(1) , (2) , (2) , (3) , (1)


We address the problem of multi-view video segmentation of dynamic scenes in general and outdoor environments with possibly moving cameras. Multi-view methods for dynamic scenes usually rely on geometric calibration to impose spatial shape constraints between viewpoints. In this paper, we show that the calibration constraint can be relaxed while still getting competitive segmentation results using multi-view constraints. We introduce new multi-view cotemporality constraints through motion correlation cues, in addition to common appearance features used by co-segmentation methods to identify co-instances of objects. We also take advantage of learning based segmentation strategies by casting the problem as the selection of monocular proposals that satisfy multi-view constraints. This yields a fully automated method that can segment subjects of interest without any particular pre-processing stage. Results on several challenging outdoor datasets demonstrate the feasibility and robustness of our approach.
Fichier principal
Vignette du fichier
final_umvseg_3dv.pdf (1.83 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01367430 , version 1 (16-09-2016)
hal-01367430 , version 2 (19-09-2016)



Abdelaziz Djelouah, Jean-Sébastien Franco, Edmond Boyer, Patrick Pérez, George Drettakis. Cotemporal Multi-View Video Segmentation. 3DV 2016 -International Conference on 3D Vision, Oct 2016, Stanford, United States. pp.360-369, ⟨10.1109/3DV.2016.45⟩. ⟨hal-01367430v2⟩
617 View
447 Download



Gmail Facebook Twitter LinkedIn More