Video Object Segmentation Via Dense Trajectories

In this paper, we propose a novel approach to segment moving object in video by utilizing improved point trajectories . First, point trajectories are densely sampled from video and tracked through optical flow, which provides information of long-term temporal interactions among objects in the video...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on multimedia 2015-12, Vol.17 (12), p.2225-2234
Hauptverfasser:	Chen, Lin, Shen, Jianbing, Wang, Wenguan, Ni, Bingbing
Format:	Artikel
Sprache:	eng
Schlagworte:	Clustering algorithms Dense trajectories energy optimization global motion information Motion segmentation Object segmentation point trajectory clustering Tracking Trajectory video object segmentation Video sequences
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!