Title :
Multi-frame simultaneous motion estimation and segmentation
Author :
Feghali, Rosario
Author_Institution :
CRC Canada, Ottawa, Ont., Canada
Abstract :
This study proposes a new approach to jointly perform motion estimation and segmentation in the spatiotemporal domain. An energy functional that embeds the constraints of both the motion estimation and segmentation problems is minimized through the Euler-Lagrange equations yielding a set of descent equations executed via spatiotemporal level-sets representation. The resulting motion field is smooth yet boundary preserving and the motion segmentation map reflects the motion field enhancement.
Keywords :
differential equations; functional equations; image enhancement; image representation; image segmentation; motion estimation; set theory; spatiotemporal phenomena; video signal processing; Euler-Lagrange equations; boundary preserving motion field; descent equations; energy functional; level-sets representation; motion estimation; motion field enhancement; motion segmentation map; multi-frame segmentation; smooth motion field; spatiotemporal domain; Brightness; Computer vision; Convergence; Image segmentation; Integral equations; Motion estimation; Motion segmentation; Pixel; Spatiotemporal phenomena; Yield estimation;
Conference_Titel :
Consumer Electronics, 2005. ICCE. 2005 Digest of Technical Papers. International Conference on
Print_ISBN :
0-7803-8838-0
DOI :
10.1109/ICCE.2005.1429805