Title :
3DTV View Generation Using Uncalibrated Cameras
Author :
Jarusirisawad, Songkran ; Saito, Hideo
Author_Institution :
Dept. of Inf. & Comput. Sci., Keio Univ., Yokohama
Abstract :
This paper proposes a method for synthesizing free viewpoint video which is captured by uncalibrated multiple cameras. Each cameras are allowed to be zoomed and rotated freely during capture. Neither intrinsic nor extrinsic parameters of our cameras are known. Projective grid space (PGS), which is the 3D space defined by the epipolar geometry of two basis cameras, is employed for calibrating dynamic multiple cameras, because geometrical relations among cameras in PGS are obtained from 2D-2D corresponding points between views. We utilize keypoint recognition for finding corresponding points in natural scene for registering cameras to PGS. Moving object is segmented via graph cut optimization. Finally, free viewpoint video is synthesized based on the reconstructed visual hull. In the experimental results, free viewpoint video which is captured by uncalibrated cameras is successfully synthesized using the proposed method.
Keywords :
graph theory; image reconstruction; image registration; image segmentation; optimisation; video cameras; 3DTV view generation; epipolar geometry; free viewpoint video synthesis; graph cut optimization; image reconstruction; image registration; keypoint recognition; moving object segmentation; natural scene; projective grid space; uncalibrated camera; visual hull reconstruction; Calibration; Cameras; Computer science; Geometry; Humans; Image generation; Image reconstruction; Image segmentation; Layout; Shape; Calibration; Image registration; Image synthesis;
Conference_Titel :
3DTV Conference: The True Vision - Capture, Transmission and Display of 3D Video, 2008
Conference_Location :
Istanbul
Print_ISBN :
978-1-4244-1760-5
Electronic_ISBN :
978-1-4244-1755-1
DOI :
10.1109/3DTV.2008.4547807
