Searching Videos by Their Time-Varying Features
スポンサーリンク
概要
- 論文の詳細を見る
In this paper, we present a video search system based on the time-varying features of objects. In this system, video shots are modeled at three levels, object level, frame level, and shot level. The model captures the visual features of individual objects at the object level, visual-spatio-temporal (VST) relationships between objects at the frame level, and time-varying visual features and time-varying VST relationships at the shot level. We call the combination of the time-varying visual features and the time-varying VST relationships a content trajectory, which is used to represent and index a video shot. A novel query interface, that allows users to describe queries, by sketch and feature specification, is presented. Our experimental results proves the effectiveness of modeling and querying video shots using the content trajectory approach.
- 社団法人電子情報通信学会の論文
- 2002-07-11
著者
-
Aghbari Zaher
Graduate School Of Information Science And Electrical Engineering Department Of Intelligent Systems
-
Aghbari Zaher
Graduate School Of Information Science And Electrical Engineering Department Of Intelligent System K
-
Makinouchi A
Graduate School Of Information Science And Electrical Engineering Department Of Intelligent Systems
-
Makinouchi Akifumi
Graduate School Of Information Science And E.e. Kyushu University
-
MAKINOUOHI Akifumi
Graduate School of Information Science and Electrical Engineering, Department of Intelligent Systems
-
AGHBARI Zaher
Graduate School of Information Science and E.E., Kyushu University
関連論文
- Towards Range Queries with Partial Dimensions in OLAP Applications (夏のデータベースワークショップDBWS2004)
- Towards QPD: Queries with Partial Dimensions (夏のデータベースワークショップ(DBWS2004))
- Batch-Incremental Nearest Neighbor Search Algorithm and Its Performance Evaluation(Databases)
- Searching Videos by Their Time-Varying Features (データベースシステム研究報告 夏のデータベースワークショップ DBWS2002)
- Semantic Approach to Image Database Classification and Retrieval (夏のワークショップDBWS2003)
- Image Retrieval by Edge Features Using Higher Order Autocorrelation in a SOM Environment(Image Processing, Image Pattern Recognition)
- Searching Videos by Their Time-Varying Features
- Semantic Approach to Image Database Classification and Retrieval
- A Dimensionality Reduction Method for Efficient Search of High-Dimensional Databases
- New Indexing method for Content-Based Video Retrieval and Clustering
- 永続分散共有メモリ機能を提供するデータベースサーバ : 「わかし」のメモリコヒーレンス機構