Rough compressed domain camera pose estimation through object motion

We present an unsupervised method to estimate the camera orientation angle on monocular video scenes in the H.264 compressed domain. The method is based on the presence of moving objects in the scene. We start by estimating the global camera motion based on the motion vectors present in the stream,...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Kas, C., Nicolas, H.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	camera pose estimation Cameras Compressed domain Filtering Layout Motion analysis Motion detection Motion estimation Object detection object distance estimation Streaming media Tracking Video compression
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!