KalmanFlow 2.0 : Efficient Video Optical Flow Estimation via Context-Aware Kalman Filtering

Recent studies on optical flow typically focus on the estimation of the single flow field in between a pair of images but pay little attention to the multiple consecutive flow fields in a longer video sequence. In this paper, we propose an efficient video optical flow estimation method by exploiting...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 28(2019), 9 vom: 07. Sept., Seite 4233-4246
1. Verfasser: Bao, Wenbo (VerfasserIn)
Weitere Verfasser: Zhang, Xiaoyun, Chen, Li, Gao, Zhiyong
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2019
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article