A method of soccer ball tracking from several viewpoints using a machine learning algorithm
-
- TAKAHASHI Masaki
- NHK Science and Technology Research Laboratories
-
- NAKAMURA Toshiyuki
- NHK Broadcast Engineering Department
-
- MISHINA Tomoyuki
- NHK Science and Technology Research Laboratories
Bibliographic Information
- Other Title
-
- 機械学習を利用した複数視点映像からのサッカーボール追跡(スポーツ映像解析,および一般)
- 機械学習を利用した複数視点映像からのサッカーボール追跡
- キカイ ガクシュウ オ リヨウ シタ フクスウ シテン エイゾウ カラ ノ サッカーボール ツイセキ
Search this article
Abstract
Tracking a ball in football video sequences is a difficult problem due to unpredictable motions and the small area of the ball in image coordinates. We propose a novel ball tracking method in football videos by using a machine learning algorithm. Tracking results from several viewpoints are collected and the method accurately estimates final ball position in real 3D coordinates. Experimental results showed that the method can robustly track a ball in real-time.
Journal
-
- ITE Technical Report
-
ITE Technical Report 38.51 (0), 5-8, 2014
The Institute of Image Information and Television Engineers
- Tweet
Details 詳細情報について
-
- CRID
- 1390001204530027264
-
- NII Article ID
- 110009885416
-
- NII Book ID
- AN1059086X
-
- ISSN
- 24241970
- 13426893
-
- NDL BIB ID
- 026021825
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- NDL
- CiNii Articles
-
- Abstract License Flag
- Disallowed