Sciweavers

24 search results - page 1 / 5
» Building mosaics from video using MPEG motion vectors
Sort
View
MM
1999
ACM
125views Multimedia» more  MM 1999»
13 years 9 months ago
Building mosaics from video using MPEG motion vectors
In this paper we present a novel way of creating mosaics from an MPEG video sequence. Two original aspects of our work are that (1) we explicitly compute camera motion between fra...
Ryan C. Jones, Daniel DeMenthon, David S. Doermann
CIVR
2007
Springer
231views Image Analysis» more  CIVR 2007»
13 years 11 months ago
Classification of video events using 4-dimensional time-compressed motion features
Among the various types of semantic concepts modeled, events pose the greatest challenge in terms of computational power needed to represent the event and accuracy that can be ach...
Alexander Haubold, Milind R. Naphade
ICIP
1999
IEEE
13 years 9 months ago
Real-Time Image Mosaicing from a Video Sequence
This paper describes a fast and robust image registration method that can be used to create a panoramic image/video from video sequences. To estimate alignment parameters for imag...
Masakatsu Kourogi, Takeshi Kurata, Junichi Hoshino...
CIARP
2003
Springer
13 years 10 months ago
Multi-channel Reconstruction of Video Sequences from Low-Resolution and Compressed Observations
A framework for recovering high-resolution video sequences from sub-sampled and compressed observations is presented. Compression schemes that describe a video sequence through a c...
Luis D. Alvarez, Rafael Molina, Aggelos K. Katsagg...
ICIP
2003
IEEE
14 years 6 months ago
Robust moving video object segmentation in the MPEG compressed domain
In this paper, we proposed a robust moving video object segmentation algorithm using features in the MPEG compressed domain. We first cluster the motion vectors and produce a moti...
Xiao-Dong Yu, Ling-Yu Duan, Qi Tian