Title :
Creating virtual scenes using active contours and global motion estimation
Author :
Giaccone, P.R. ; Greenhill, D. ; Jones, G.A.
Author_Institution :
Sch. of Comput. Sci. & Electron. Syst., Kingston Univ., UK
Abstract :
This paper demonstrates how active contour segmentation and optical flow estimation techniques can be combined to create a seamless mosaic of frames from a video sequence. This virtual scene forms the basis of a number of post-production effects such as creating new image trajectories for the shot, or special effects which include new foreground elements. The optical flow method produces highly accurate global motion estimates by drawing upon an appropriate 3D geometrical model of camera motion. The active contour technique has been extended to include user selected edge data to guide crudely specified initial contours to their final location. The resultant rotoscoping tool dramatically improves the performance of traditional tools by using edge chain matching to relocate the active contour in subsequent frames
Keywords :
edge detection; image matching; image segmentation; image sequences; motion estimation; solid modelling; video signal processing; virtual reality; 3D geometrical model; active contour segmentation; edge chain matching; motion estimation; optical flow; rotoscoping; special effects; video sequence; virtual scenes; Active contours; Cameras; Electrical capacitance tomography; Image motion analysis; Image segmentation; Image sequences; Layout; Motion estimation; Optical films; Production;
Conference_Titel :
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location :
Brisbane, Qld.
Print_ISBN :
0-8186-8512-3
DOI :
10.1109/ICPR.1998.711992