Title :
Camera motion characterization through image feature analysis
Author :
LERTRUSDACHAKUL, Thitiporn ; Aoki, Terumasa ; Yasuda, Hiroshi
Author_Institution :
Res. Center for Adv. Sci. & Technol., Tokyo Univ., Japan
Abstract :
This paper presents an approach to characterize camera motion in video sequences based on image feature analysis. The approach predicts camera motion using spatio-temporal information obtained from tracking the feature points throughout an image sequence. The spatio-temporal information provides the advantage of rich visual characteristic along a larger temporal scale over the traditional approaches, which tend to formulate computational methodologies on a few adjacent frames. In this paper, we propose an algorithm to estimate camera motion by analyzing the motion trajectories of feature points over temporal change. The experimental results support that the proposed algorithm is effective in determining camera motion.
Keywords :
feature extraction; image sequences; motion estimation; video cameras; camera motion characterization; feature point tracking; image feature analysis; image sequence; spatio-temporal information; video sequences; Algorithm design and analysis; Cameras; Image analysis; Image motion analysis; Image sequence analysis; Image sequences; Motion analysis; Motion estimation; Tracking; Video sequences;
Conference_Titel :
Computational Intelligence and Multimedia Applications, 2005. Sixth International Conference on
Print_ISBN :
0-7695-2358-7
DOI :
10.1109/ICCIMA.2005.15