抄録
In this paper, we describe the Toshiba event detection system for TRECVID surveillance event detection task [1]. Our system consists of four components: (1) a flexible and robust change detection based on non-parametric background modeling, (2) a human detection that extends and outperforms HOG (Histogram of Oriented Gradient) human detection, (3) a human tracking with simple linear estimation and color histogram matching, and (4) an event detection for three TRECVID required events (E05, E19, and E20) based on change detection and human tracking. Our current system has just adopted a simple version of each component and requires further refinement.
| 本文言語 | English |
|---|---|
| 出版ステータス | Published - 2008 |
| 外部発表 | はい |
| イベント | TREC Video Retrieval Evaluation, TRECVID 2008 - Gaithersburg, MD, United States 継続期間: 2008 11月 17 → 2008 11月 18 |
Conference
| Conference | TREC Video Retrieval Evaluation, TRECVID 2008 |
|---|---|
| 国/地域 | United States |
| City | Gaithersburg, MD |
| Period | 08/11/17 → 08/11/18 |
ASJC Scopus subject areas
- コンピュータ グラフィックスおよびコンピュータ支援設計
- コンピュータ ビジョンおよびパターン認識
- 人間とコンピュータの相互作用
- ソフトウェア