- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- 【Updated on June 30, 2025】Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Parallel Clustering Method for Realtime Image Processing
-
- MINO Yoshiteru
- Central Research Laboratories Corporate Research Division Matsushita Electric Industrial Co., Ltd.
-
- WAKATANI Akiyoshi
- Central Research Laboratories Corporate Research Division Matsushita Electric Industrial Co., Ltd.
-
- KADOTA Hiroshi
- Central Research Laboratories Corporate Research Division Matsushita Electric Industrial Co., Ltd.
Bibliographic Information
- Other Title
-
- 実時間処理のための並列画像クラスタリング
Search this article
Description
This paper describes a high-speed pararell clustering method, which is suitable for a pre-processing of the motion picture compression and coding. In the parallel clustering process, prural pixels are sampled in one frame of image. They are gathered according to their characteristics ; color, brightness etc., to organaize clusters or to modify cluster-parameters, in pararell manner. This operation is repeated until the frame is optimally segmented by a set of clusters. Furthermore, by implementing this algorithm on a dedicated parallel architecture, the process speed increases by several hundred times, and a realtime clustering of motion picture will be available.
Journal
-
- IEICE technical report. Computer systems
-
IEICE technical report. Computer systems 95 (125), 55-60, 1995-06-23
The Institute of Electronics, Information and Communication Engineers
- Tweet
Details 詳細情報について
-
- CRID
- 1573105977222112128
-
- NII Article ID
- 110003180086
-
- NII Book ID
- AN10013141
-
- Text Lang
- ja
-
- Data Source
-
- CiNii Articles