| 電子情報通信学会 研究会発表申込システム 講演論文 詳細 |
技報閲覧サービス [ログイン] 技報アーカイブ |
| トップに戻る | 前のページに戻る | [Japanese] / [English] |
| 講演抄録／キーワード | ||
| 講演名 | 2007-10-26 13:15 Accurate, Real-time 3D Reconstruction of Human Postures from Orthogonal Images Based on Neural Networks Dong-Wan Kang（Waseda Univ.）・Zhongze Chan（Univ. of South China）・○Jun Ohya（Waseda Univ.）  PRMU2007-113 |
|
| 抄録 | （和） | This paper deals with a real-time method for reconstructing 3D posture parameters of the human from orthogonal images by using artificial neural network techniques with higher accuracies than conventional computer vision based methods. To sample the data used for training the neural network, a human wearing the sensing devices of a motion capture system is synchronously observed by orthogonal cameras so that at each frame the motion capture data as well as the positions of the located feature points of the human areas in the camera images are obtained at the same time. During the training phase, the positions of the located feature points and the motion capture data are respectively used for the input and output vectors of the neural network. During the reconstruction phase, the positions of the located feature points at each frame of the video sequence to be reconstructed are inputted into the trained neural network so that the inputted data at each frame are converted to the motion capture data. The proposed method is implemented on a personal computer and runs in real-time (30 frames/sec). Experimental results confirm both the feasibility and the effectiveness of the proposed method for estimating 3D human postures. |
| （英） | This paper deals with a real-time method for reconstructing 3D posture parameters of the human from orthogonal images by using artificial neural network techniques with higher accuracies than conventional computer vision based methods. To sample the data used for training the neural network, a human wearing the sensing devices of a motion capture system is synchronously observed by orthogonal cameras so that at each frame the motion capture data as well as the positions of the located feature points of the human areas in the camera images are obtained at the same time. During the training phase, the positions of the located feature points and the motion capture data are respectively used for the input and output vectors of the neural network. During the reconstruction phase, the positions of the located feature points at each frame of the video sequence to be reconstructed are inputted into the trained neural network so that the inputted data at each frame are converted to the motion capture data. The proposed method is implemented on a personal computer and runs in real-time (30 frames/sec). Experimental results confirm both the feasibility and the effectiveness of the proposed method for estimating 3D human postures. | |
| キーワード | （和） | 3D Reconstruction / Human Posture / Images / Neural Network / / / / |
| （英） | 3D Reconstruction / Human Posture / Images / Neural Network / / / / | |
| 文献情報 | 信学技報, vol. 107, no. 281, PRMU2007-113, pp. 123-128, 2007年10月. | |
| 資料番号 | PRMU2007-113 | |
| 発行日 | 2007-10-18 (PRMU) | |
| ISSN | Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 | |
| 著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します．(許諾番号：10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) | |
| PDFダウンロード | PRMU2007-113 |
|
| 研究会情報 | |
| 研究会 | PRMU |
| 開催期間 | 2007-10-25 - 2007-10-26 |
| 開催地（和） | ホテル松島大観荘 |
| 開催地（英） | Hotel Matsushima Daikansou |
| テーマ（和） | 第二回日韓パターン認識ワークショップ(KJPR) |
| テーマ（英） | |
| 講演論文情報の詳細 | |
| 申込み研究会 | PRMU |
| 会議コード | 2007-10-PRMU |
| 本文の言語 | 英語 |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | Accurate, Real-time 3D Reconstruction of Human Postures from Orthogonal Images Based on Neural Networks |
| サブタイトル（英） | |
| キーワード(1)（和/英） | 3D Reconstruction / 3D Reconstruction |
| キーワード(2)（和/英） | Human Posture / Human Posture |
| キーワード(3)（和/英） | Images / Images |
| キーワード(4)（和/英） | Neural Network / Neural Network |
| キーワード(5)（和/英） | / |
| キーワード(6)（和/英） | / |
| キーワード(7)（和/英） | / |
| キーワード(8)（和/英） | / |
| 第1著者 氏名（和/英/ヨミ） | Dong-Wan Kang / Dong-Wan Kang / |
| 第1著者 所属（和/英） | 早稲田大学 (略称： 早大) Waseda University (略称： Waseda Univ.) |
| 第2著者 氏名（和/英/ヨミ） | Zhongze Chan / Zhongze Chan / |
| 第2著者 所属（和/英） | 南華大学 (略称： 南華大) University of South China (略称： Univ. of South China) |
| 第3著者 氏名（和/英/ヨミ） | Jun Ohya / Jun Ohya / |
| 第3著者 所属（和/英） | 早稲田大学 (略称： 早大) Waseda University (略称： Waseda Univ.) |
| 講演者 | 第3著者 |
| 発表日時 | 2007-10-26 13:15:00 |
| 発表時間 | 25分 |
| 申込先研究会 | PRMU |
| 資料番号 | PRMU2007-113 |
| 巻番号（vol） | vol.107 |
| 号番号（no） | no.281 |
| ページ範囲 | pp.123-128 |
| ページ数 | 6 |
| 発行日 | 2007-10-18 (PRMU) |
[研究会発表申込システムのトップページに戻る]