Presentation | 2016-06-13 Preliminary study on deep manifold embedding for 3D object pose estimation Hiroshi Ninomiya, Yasutomo Kawanishi, Daisuke Deguchi, Ichiro Ide, Hiroshi Murase, Norimasa Kobori, Kunimatsu Hashimoto, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, 3D object pose estimation is being focused. The parametric eigenspace method is known as one of the fundamental methods. It represents the appearance change of an object caused by pose change with a manifold embedded in a low-dimentional subspace. It obtains features by PCA, which maximizes the appearance variation. However, there is not always a correlation between pose change and appearance change. So, there is a problem that the method cannot handle a pose change with a slight appearance change. In this report, we introduce deep manifold embedding which maximizes the pose variation. We construct a manifold from features extracted from Deep Convolutional Neural Networks (DCNNs) trained with pose information. Pose estimation with the proposed method achieved the best accuracy in experiments using a public dataset. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | 3D object / pose estimation / manifold / deep learning |
Paper # | PRMU2016-39,SP2016-5,WIT2016-5 |
Date of Issue | 2016-06-06 (PRMU, SP, WIT) |
Conference Information | |
Committee | PRMU / SP / WIT / ASJ-H |
---|---|
Conference Date | 2016/6/13(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Eisaku Maeda(NTT) / Kazunori Mano(Shibaura Inst. of Tech.) / Kiyohiko Nunokawa(Tokyo International Univ.) |
Vice Chair | Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / Hiroki Mori(Utsunomiya Univ.) / Chikamune Wada(Kyushu Inst. of Tech.) |
Secretary | Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / Hiroki Mori(Kobe Univ.) / Chikamune Wada(Shizuoka Univ.) / (Nagoya Inst. of Tech.) |
Assistant | Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / Taichi Asami(NTT) / Kei Hashimoto(Nagoya Inst. of Tech.) / Tomohiro Amemiya(NTT) / Takeaki Shionome(Tsukuba Univ. of Tech.) / Manabi Miyagi(Tsukuba Univ. of Tech.) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Speech / Technical Committee on Well-being Information Technology / Auditory Research Meeting |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Preliminary study on deep manifold embedding for 3D object pose estimation |
Sub Title (in English) | |
Keyword(1) | 3D object |
Keyword(2) | pose estimation |
Keyword(3) | manifold |
Keyword(4) | deep learning |
1st Author's Name | Hiroshi Ninomiya |
1st Author's Affiliation | Nagoya University(Nagoya Univ.) |
2nd Author's Name | Yasutomo Kawanishi |
2nd Author's Affiliation | Nagoya University(Nagoya Univ.) |
3rd Author's Name | Daisuke Deguchi |
3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
4th Author's Name | Ichiro Ide |
4th Author's Affiliation | Nagoya University(Nagoya Univ.) |
5th Author's Name | Hiroshi Murase |
5th Author's Affiliation | Nagoya University(Nagoya Univ.) |
6th Author's Name | Norimasa Kobori |
6th Author's Affiliation | Toyota Motor Corporation(Toyota) |
7th Author's Name | Kunimatsu Hashimoto |
7th Author's Affiliation | Toyota Motor Corporation(Toyota) |
Date | 2016-06-13 |
Paper # | PRMU2016-39,SP2016-5,WIT2016-5 |
Volume (vol) | vol.116 |
Number (no) | PRMU-89,SP-90,WIT-91 |
Page | pp.pp.25-30(PRMU), pp.25-30(SP), pp.25-30(WIT), |
#Pages | 6 |
Date of Issue | 2016-06-06 (PRMU, SP, WIT) |