抄録
We present a fast and accurate method for reconstructing surfaces of revolution (SoR) on 3D data and its application to structural modeling of a cluttered scene in real-time. To estimate a SoR axis, we derive an approximately linear cost function for fast convergence. Also, we design a framework for reconstructing SoR on dense SLAM. In the experiment results, we show our method is accurate, robust to noise and runs in real-time.
| 元の言語 | 英語 |
|---|---|
| ホスト出版物のタイトル | Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016 |
| 出版者 | Institute of Electrical and Electronics Engineers Inc. |
| ページ | 28-36 |
| ページ数 | 9 |
| ISBN（電子版） | 9781509054077 |
| DOI | |
| 出版物ステータス | 出版済み - 12 15 2016 |
| イベント | 4th International Conference on 3D Vision, 3DV 2016 - Stanford, 米国 継続期間: 10 25 2016 → 10 28 2016 |
出版物シリーズ
| 名前 | Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016 |
|---|
その他
| その他 | 4th International Conference on 3D Vision, 3DV 2016 |
|---|---|
| 国 | 米国 |
| 市 | Stanford |
| 期間 | 10/25/16 → 10/28/16 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Computer Vision and Pattern Recognition
- Signal Processing
これを引用
Real-time surface of revolution reconstruction on dense SLAM. / Yang, Liming; Uchiyama, Hideaki; Normand, Jean Marie; Moreau, Guillaume; Nagahara, Hajime; Taniguchi, Rin Ichiro.
Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 28-36 7785074 (Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016).研究成果: 著書/レポートタイプへの貢献 › 会議での発言
}
TY - GEN
T1 - Real-time surface of revolution reconstruction on dense SLAM
AU - Yang, Liming
AU - Uchiyama, Hideaki
AU - Normand, Jean Marie
AU - Moreau, Guillaume
AU - Nagahara, Hajime
AU - Taniguchi, Rin Ichiro
PY - 2016/12/15
Y1 - 2016/12/15
N2 - We present a fast and accurate method for reconstructing surfaces of revolution (SoR) on 3D data and its application to structural modeling of a cluttered scene in real-time. To estimate a SoR axis, we derive an approximately linear cost function for fast convergence. Also, we design a framework for reconstructing SoR on dense SLAM. In the experiment results, we show our method is accurate, robust to noise and runs in real-time.
AB - We present a fast and accurate method for reconstructing surfaces of revolution (SoR) on 3D data and its application to structural modeling of a cluttered scene in real-time. To estimate a SoR axis, we derive an approximately linear cost function for fast convergence. Also, we design a framework for reconstructing SoR on dense SLAM. In the experiment results, we show our method is accurate, robust to noise and runs in real-time.
UR - http://www.scopus.com/inward/record.url?scp=85011263045&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85011263045&partnerID=8YFLogxK
U2 - 10.1109/3DV.2016.13
DO - 10.1109/3DV.2016.13
M3 - Conference contribution
AN - SCOPUS:85011263045
T3 - Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016
SP - 28
EP - 36
BT - Proceedings - 2016 4th International Conference on 3D Vision, 3DV 2016
PB - Institute of Electrical and Electronics Engineers Inc.
ER -