| 大会名称 |
|---|
| 2009年 情報科学技術フォーラム(FIT) |
| 大会コ－ド |
| F |
| 開催年 |
| 2009 |
| 発行日 |
| 2009/8/20 |
| セッション番号 |
| 7L |
| セッション名 |
| ヒューマン情報処理（3） |
| 講演日 |
| 2009/09/04 |
| 講演場所(会議室等) |
| L会場（9号館3F 933教室） |
| 講演番号 |
| J-030 |
| タイトル |
| スキャンパス理論に基づく移動ロボットの手先動作時の関心領域特性と検出特性 |
| 著者名 |
| 藤田 豊己, |
| キーワード |
| スキャンパス, 関心領域, 注視機能 |
| 抄録 |
|
Visual functions are important for robots who engage in cooperative work with other robots. In order to develop an effective visual function for robots, we investigate the features of the human visual scanpath in a scene of robot hand movement. Human regions-of-interest (hROIs) are measured by psychophysical experiments and compared by using a positional similarity index, Sp, on the basis of scanpath theory. The result reveals consistent loci of the hROIs due to dominant topdown active looking in such a scene. This paper also discusses how bottom-up image processing algorithms (IPAs) are able to predict hROIs. We compare algorithmic regions-of-interest (aROIs) which are generated by the IPAs, with the hROIs obtained from images of robot hand movements. We observe that the predictability of the hROIs by IPAs becomes high if the support size of IPA is almost equal to the size of the fovea. The results also suggest that the combination of the IPAs and topdown processing models is more useful for effective prediction. |
| 本文pdf |
| PDF download (323.4KB) |