Saliency-guided video deinterlacing
Type de document :
Communication dans un congrès avec actes
Titre :
Saliency-guided video deinterlacing
Auteur(s) :
Trocan, Maria [Auteur]
Institut Supérieur d'Electronique de Paris [ISEP]
Coudoux, François-Xavier [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Institut Supérieur d'Electronique de Paris [ISEP]
Coudoux, François-Xavier [Auteur]
COMmunications NUMériques - IEMN [COMNUM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Éditeur(s) ou directeur(s) scientifique(s) :
Manuel Núñez
Ngoc Thanh Nguyen
David Camacho
Bogdan Trawiński
Ngoc Thanh Nguyen
David Camacho
Bogdan Trawiński
Titre de la manifestation scientifique :
7th International Conference on Computational Collective Intelligence Technologies and Applications, ICCCI 2015
Ville :
Madrid
Pays :
Espagne
Date de début de la manifestation scientifique :
2015-09-21
Titre de l’ouvrage :
Computational Collective Intelligence
Éditeur :
Springer Cham
Date de publication :
2015-10-24
Mot(s)-clé(s) en anglais :
Video Sequence
Motion Vector
Motion Estimation
Salient Region
Visual Saliency
Motion Vector
Motion Estimation
Salient Region
Visual Saliency
Discipline(s) HAL :
Informatique [cs]
Sciences de l'ingénieur [physics]
Sciences de l'ingénieur [physics]
Résumé en anglais : [en]
Video deinterlacing is a technique wherein the interlaced video format is converted into progressive scan format for nowadays display devices. In this paper a spatial saliency-guided motion compensated deinterlacing method ...
Lire la suite >Video deinterlacing is a technique wherein the interlaced video format is converted into progressive scan format for nowadays display devices. In this paper a spatial saliency-guided motion compensated deinterlacing method is proposed: our algorithm classifies the field according to its texture and viewer’s region of interest and adapts the motion estimation and compensation, as well as the saliency-guided interpolation in order to ensure high quality frame reconstruction. The experimental results show significant improvement of the proposed method over classical motion compensated and adaptive deinterlacing techniques.Lire moins >
Lire la suite >Video deinterlacing is a technique wherein the interlaced video format is converted into progressive scan format for nowadays display devices. In this paper a spatial saliency-guided motion compensated deinterlacing method is proposed: our algorithm classifies the field according to its texture and viewer’s region of interest and adapts the motion estimation and compensation, as well as the saliency-guided interpolation in order to ensure high quality frame reconstruction. The experimental results show significant improvement of the proposed method over classical motion compensated and adaptive deinterlacing techniques.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Commentaire :
Special Session WebSys I - Collective Intelligence in Web Systems - Web Systems AnalysisLect. Notes Comput. Sci. 9330 (2015) 24-33
Source :