| 講演抄録/キーワード |
| 講演名 |
2007-10-26 14:45
PCA-Based Personal Favorite Scene Selection from Broadcast Soccer Video ○Masao Izumi(Osaka Prefecture Univ.) PRMU2007-123 |
| 抄録 |
(和) |
We propose a novel method for selecting personal favorite scenes using
Principle Component Analysis (PCA) based approach from broadcast
soccer videos.
Firstly we extract physical parameters, image space frequency and time
space frequency.
We use these physical parameters as feature vectors, make an eigenspace
of these vectors extracted from image slices of broadcast soccer videos,
and select the image slices that the distance from prior selected image
slices as a personal favorite scene in the eigenspace is small.
Personal favorite scenes are characterized as the feature vectors which
are selected from physical parameters extracted from videos. |
| (英) |
We propose a novel method for selecting personal favorite scenes using
Principle Component Analysis (PCA) based approach from broadcast
soccer videos.
Firstly we extract physical parameters, image space frequency and time
space frequency.
We use these physical parameters as feature vectors, make an eigenspace
of these vectors extracted from image slices of broadcast soccer videos,
and select the image slices that the distance from prior selected image
slices as a personal favorite scene in the eigenspace is small.
Personal favorite scenes are characterized as the feature vectors which
are selected from physical parameters extracted from videos. |
| キーワード |
(和) |
principle component analysis / scene selection / broadcast soccer video / / / / / |
| (英) |
principle component analysis / scene selection / broadcast soccer video / / / / / |
| 文献情報 |
信学技報, vol. 107, no. 281, PRMU2007-123, pp. 187-190, 2007年10月. |
| 資料番号 |
PRMU2007-123 |
| 発行日 |
2007-10-18 (PRMU) |
| ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
| PDFダウンロード |
PRMU2007-123 |