WEKO3
-
RootNode
アイテム
Interest Point Detection Based on Stochastically Derived Stability
https://ipsj.ixsq.nii.ac.jp/records/101632
https://ipsj.ixsq.nii.ac.jp/records/1016321dac6007-5895-4f4b-a039-1b68b36c1ce4
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-TCVA0300022.pdf (2.8 MB)
|
Copyright (c) 2011 by the Information Processing Society of Japan
|
|
| オープンアクセス | ||
| Item type | Trans(1) | |||||||
|---|---|---|---|---|---|---|---|---|
| 公開日 | 2011-12-28 | |||||||
| タイトル | ||||||||
| タイトル | Interest Point Detection Based on Stochastically Derived Stability | |||||||
| タイトル | ||||||||
| 言語 | en | |||||||
| タイトル | Interest Point Detection Based on Stochastically Derived Stability | |||||||
| 言語 | ||||||||
| 言語 | eng | |||||||
| キーワード | ||||||||
| 主題Scheme | Other | |||||||
| 主題 | Special Issue on MIRU2010 - Research Paper | |||||||
| 資源タイプ | ||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||
| 資源タイプ | journal article | |||||||
| 著者所属 | ||||||||
| NTT Communication Science Laboratories, NTT Corporation／International College, King Mongkut's Institute of Technology Ladkrabang | ||||||||
| 著者所属 | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属 | ||||||||
| NTT Communication Science Laboratories, NTT Corporation／University of British Columbia | ||||||||
| 著者所属 | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属 | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| NTT Communication Science Laboratories, NTT Corporation / International College, King Mongkut's Institute of Technology Ladkrabang | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| NTT Communication Science Laboratories, NTT Corporation / University of British Columbia | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者所属(英) | ||||||||
| en | ||||||||
| NTT Communication Science Laboratories, NTT Corporation | ||||||||
| 著者名 |
Ukrit, Watchareeruetai
Akisato, Kimura
RobertChengBao
Takahito, Kawanishi
Kunio, Kashino
× Ukrit, Watchareeruetai Akisato, Kimura RobertChengBao Takahito, Kawanishi Kunio, Kashino
|
|||||||
| 著者名(英) |
Ukrit, Watchareeruetai
Akisato, Kimura
Robert, ChengBao
Takahito, Kawanishi
Kunio, Kashino
× Ukrit, Watchareeruetai Akisato, Kimura Robert, ChengBao Takahito, Kawanishi Kunio, Kashino
|
|||||||
| 論文抄録 | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | 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. | |||||||
| 論文抄録(英) | ||||||||
| 内容記述タイプ | Other | |||||||
| 内容記述 | 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. | |||||||
| 書誌レコードID | ||||||||
| 収録物識別子タイプ | NCID | |||||||
| 収録物識別子 | AA12394973 | |||||||
| 書誌情報 |
IPSJ Transactions on Computer Vision and Applications（CVA） 巻 3, p. 186-197, 発行日 2011-12-28 |
|||||||
| ISSN | ||||||||
| 収録物識別子タイプ | ISSN | |||||||
| 収録物識別子 | 1882-6695 | |||||||
| 出版者 | ||||||||
| 言語 | ja | |||||||
| 出版者 | 情報処理学会 | |||||||
