DocumentCode :
579850
Title :
Through-the-Lens Multi-camera Synchronisation and Frame-Drop Detection for 3D Reconstruction
Author :
Imre, Evren ; Guillemaut, Jean-Yves ; Hilton, Adrian
Author_Institution :
CVSSP, Univ. of Surrey, Guildford, UK
fYear :
2012
fDate :
13-15 Oct. 2012
Firstpage :
395
Lastpage :
402
Abstract :
Synchronisation is an essential requirement for multiview 3D reconstruction of dynamic scenes. However, the use of HD cameras and large set-ups put a considerable stress on hardware and cause frame drops, which is usually detected by manually verifying very large amounts of data. This paper improves [9], and extends it with frame-drop detection capability. In order to spot frame-drop events, the algorithm fits a broken line to the frame index correspondences for each camera pair, and then fuses the pair wise drop hypotheses into a consistent, absolute frame-drop estimate. The success and the practical utility of the the improved pipeline is demonstrated through a number of experiments, including 3D reconstruction and free-viewpoint video rendering tasks.
Keywords :
estimation theory; high definition video; image reconstruction; object detection; rendering (computer graphics); synchronisation; video cameras; video signal processing; HD cameras; camera pair; dynamic scenes; frame drops; frame index correspondences; frame-drop detection capability; frame-drop estimate; frame-drop events; free-viewpoint video rendering tasks; multiview 3D reconstruction; pair wise drop hypotheses; practical utility; through-the-lens multicamera synchronisation; Cameras; High definition video; Indexes; Pipelines; Synchronization; Three dimensional displays; Trajectory; camera network synchronisation; frame-drop detection; through-the-lens synchronisation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT), 2012 Second International Conference on
Conference_Location :
Zurich
Print_ISBN :
978-1-4673-4470-8
Type :
conf
DOI :
10.1109/3DIMPVT.2012.31
Filename :
6375020
Link To Document :
بازگشت