Abstract | ||
---|---|---|
In this paper we propose a novel fast fuzzy classifier able to find regular and low distorted near regular tex- ture taking into account the constraints of video stabi- lization applications. Digital video stabilization allows to acquire video sequences without disturbing jerkiness, removing unwanted camera movements. In presence of regular or near regular texture, video stabilization ap- proaches typically fail. These kind of patterns, due to their periodicity, create multiple matching that degrade motion estimation performances. The proposed classi- fier has been used as a filtering module in a block based video stabilization approach. Experiments on real se- quences with (and without) regular texture confirm the effectiveness of the proposed approach. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ICPR.2008.4761562 | ICPR |
Keywords | Field | DocType |
filtering theory,fuzzy set theory,image matching,image sequences,motion estimation,video signal processing,block based video stabilization,digital video stabilization,fast fuzzy classifier,filtering module,low distorted near regular texture taking,motion estimation,multiple matching,regular texture removal,video sequences | Computer vision,Block-matching algorithm,Jerkiness,Pattern recognition,Computer science,Image stabilization,Filter (signal processing),Video tracking,Artificial intelligence,Motion estimation,Video denoising,Texture filtering | Conference |
ISSN | Citations | PageRank |
1051-4651 | 5 | 0.51 |
References | Authors | |
8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sebastiano Battiato | 1 | 659 | 78.73 |
Giovanni Puglisi | 2 | 383 | 31.62 |
Arcangelo Bruna | 3 | 54 | 9.64 |