| 研究課題/領域番号 |
19K20335
|
|---|
| 研究種目 |
若手研究
|
| 配分区分 | 基金 |
|---|
| 審査区分 |
小区分61030:知能情報学関連
|
|---|
| 研究機関 | 国立研究開発法人産業技術総合研究所 (2021-2022)
筑波大学 (2019-2020) |
|---|
研究代表者 |
Gatto Bernardo 国立研究開発法人産業技術総合研究所, 情報・人間工学領域, 産総研特別研究員 (10826267)
|
|---|
| 研究期間 (年度) |
2019-04-01 – 2023-03-31
|
| 研究課題ステータス |
中途終了 (2022年度)
|
| 配分額 *注記 |
4,160千円 (直接経費: 3,200千円、間接経費: 960千円)
2022年度: 1,300千円 (直接経費: 1,000千円、間接経費: 300千円)
2021年度: 1,170千円 (直接経費: 900千円、間接経費: 270千円)
2020年度: 650千円 (直接経費: 500千円、間接経費: 150千円)
2019年度: 1,040千円 (直接経費: 800千円、間接経費: 240千円)
|
|---|
| キーワード | elderly surveillance / subspace representation / image recognition / deep learning |
|---|
| 研究開始時の研究の概要 |
We will investigate the fusion of visual and acoustic data to support the safe life of the elderly living alone. We will employ information from visual and acoustic sensors (e.g., cameras and microphones) and recognize events, such as domestic activities or abnormal events. In this research, we develop the following technologies: (1) fast neural networks for extraction of visual characteristics from videos, (2) neural networks for acoustic data analysis and, (3) data fusion for event recognition.
|
| 研究実績の概要 |
Motivated by applications of subspace analysis, two new groups of methods were presented in this project: (1) Shallow networks for image classification; and (2) Subspaces for tensor representation and classification. New representations are proposed to preserve the spatial structure and maintain a fast processing time. A new method to keep the temporal structure was also given.
These solutions were evaluated over problems involving person detection, action, and gesture representation. We focused on the fusion of visual and acoustic data to support the safe life of the elderly living alone.
|
