@article{oai:ipsj.ixsq.nii.ac.jp:00101632,
 author = {Ukrit, Watchareeruetai and Akisato, Kimura and RobertChengBao and Takahito, Kawanishi and Kunio, Kashino and Ukrit, Watchareeruetai and Akisato, Kimura and Robert, ChengBao and Takahito, Kawanishi and Kunio, Kashino},
 journal = {IPSJ Transactions on Computer Vision and Applications（CVA）},
 month = {Dec},
 note = {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., 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.},
 pages = {186--197},
 title = {Interest Point Detection Based on Stochastically Derived Stability},
 volume = {3},
 year = {2011}
}