Interest Point Detection Based on Stochastically Derived Stability

スポンサーリンク

概要

• 論文の詳細を見る

• 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.

• 一般社団法人 情報処理学会の論文

著者

• Kashino Kunio

  Ntt Communication Science Laboratories Ntt Corporation

• Watchareeruetai Ukrit

  NTT Communication Science Laboratories, NTT Corporation

• Kimura Akisato

  NTT Communication Science Laboratories, NTT Corporation

• Bao Robert

  NTT Communication Science Laboratories, NTT Corporation

• Kawanishi Takahito

  NTT Communication Science Laboratories, NTT Corporation

関連論文

• Similar Music Retrieval Using Polyphonic Binary Feature Vectors and Its Acceleration
• Interest Point Detection Based on Stochastically Derived Stability
• SemiCCA: Efficient Semi-supervised Learning of Canonical Correlations
• Designing Various Multivariate Analysis at Will via Generalized Pairwise Expression
• SemiCCA: Efficient Semi-supervised Learning of Canonical Correlations
• Interest Point Detection Based on Stochastically Derived Stability
• Quick audio retrieval based on histogram feature sequences
• Designing Various Multivariate Analysis at Will via Generalized Pairwise Expression
• Computational Models of Human Visual Attention and Their Implementations: A Survey
• Computational Models of Human Visual Attention and Their Implementations : A Survey

スポンサーリンク