Interest Point Detection Based on Stochastically Derived Stability

We propose a novel framework called StochasticSIFT for detecting interest points (IPs) in video sequences. The proposed framework incorporates a stochastic model considering the temporal dynamics of videos into the SIFT detector to improve robustness against fluctuations inherent to video signals. I...

Full description

Saved in:
Bibliographic Details
Published inIPSJ Transactions on Computer Vision and Applications Vol. 3; pp. 186 - 197
Main Authors Watchareeruetai, Ukrit, Kimura, Akisato, Bao, Robert Cheng, Kawanishi, Takahito, Kashino, Kunio
Format Journal Article
LanguageEnglish
Published Information Processing Society of Japan 2011
Subjects
Detectors
Fluctuation
Probability theory
Randomness
Robustness
Stability
Stochasticity
Video signals
Online AccessGet full text

Cover

More Information
Summary:We propose a novel framework called StochasticSIFT for detecting interest points (IPs) in video sequences. The proposed framework incorporates a stochastic model considering the temporal dynamics of videos into the SIFT detector to improve robustness against fluctuations inherent to video signals. Instead of detecting IPs and then removing unstable or inconsistent IP candidates, we introduce IP stability derived from a stochastic model of inherent fluctuations to detect more stable IPs. The experimental results show that the proposed IP detector outperforms the SIFT detector in terms of repeatability and matching rates.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ObjectType-Article-1
ObjectType-Feature-2
ISSN:1882-6695
1882-6695
DOI:10.2197/ipsjtcva.3.186