Sciweavers

371 search results - page 60 / 75
» 3D-modeling by ortho-image generation from image sequences
Sort
View
ICASSP
2008
IEEE
15 years 6 months ago
Optical flow robust estimation in a hybrid multi-resolution MRF framework
We propose in this paper a robust multi-resolution technique to estimate dense velocity field from image sequences. It couples a Gaussian pyramidal down-sampling decomposition to...
Cyril Cassisa, Véronique Prinet, Liang Shao...
EVOW
2010
Springer
15 years 1 months ago
Refinement Techniques for Animated Evolutionary Photomosaics Using Limited Tile Collections
An animated evolutionary photomosaic is produced from a sequence of still or static photomosaics to evolve a near match to a given target image. A static photomosaic is composed of...
Shahrul Badariah Mat Sah, Victor Ciesielski, Daryl...
TOG
2002
208views more  TOG 2002»
14 years 11 months ago
Video matting of complex scenes
This paper describes a new framework for video matting, the process of pulling a high-quality alpha matte and foreground from a video sequence. The framework builds upon technique...
Yung-Yu Chuang, Aseem Agarwala, Brian Curless, Dav...
CISS
2011
IEEE
14 years 3 months ago
Hardware accelerated visual attention algorithm
— We present a hardware-accelerated implementation of a bottom-up visual attention algorithm. This algorithm generates a multi-scale saliency map from differences in image intens...
Polina Akselrod, Faye Zhao, Ifigeneia Derekli, Cl&...
AVSS
2006
IEEE
15 years 5 months ago
3D Human Motion Analysis in Monocular Video Techniques and Challenges
Extracting meaningful 3D human motion information from video sequences is of interest for applications like intelligent humancomputer interfaces, biometrics, video browsing and ind...
Cristian Sminchisescu