| Presentation | 2005-02-25 Camera Arrangement for Object Recognition using Multiple-Viewpoint Images Osanori MATSUGANO, Tomokazu TAKAHASHI, Ichiro IDE, Yoshito MEKADA, Hiroshi MURASE, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In this paper, we propose a method to recognize objects and estimate their pose using multiple-viewpoint images, and also a method to estimate the optimal camera arrangement to recognize the objects accurately. In multiple-viewpoint object recognition, camera arrangement is important, since it affects the recognition accuracy directly. In general, the optimal camera arrangement to recognize one object set is determined by examining the recognition accuracy for all possible camera arrangements, at the expense of a great amount of time. In order to avoid this procedure, this paper proposes a method to estimate the optimal camera arrangement to recognize given objects accurately, refering to the geometric feature of the manihold in the eigenspace, projected by training object images. We evaluated the method through an experiment, applied to four object sets in order to compare the pose estimation ability with the result from the proposed multiple-viewpoint object recognition method, which showed that the proposed method can estimate the optimal camera arrangement for multiple-viewpoint object recognition. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Multiple-viewpoint / Camera arrangement / Parametric eigenspace / Manihold |
| Paper # | NLC2004-119,PRMU2004-201 |
| Date of Issue |
| Conference Information | |
| Committee | NLC |
|---|---|
| Conference Date | 2005/2/18(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Natural Language Understanding and Models of Communication (NLC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Camera Arrangement for Object Recognition using Multiple-Viewpoint Images |
| Sub Title (in English) | |
| Keyword(1) | Multiple-viewpoint |
| Keyword(2) | Camera arrangement |
| Keyword(3) | Parametric eigenspace |
| Keyword(4) | Manihold |
| 1st Author's Name | Osanori MATSUGANO |
| 1st Author's Affiliation | Graduate School of Infomation Science, Nagoya University() |
| 2nd Author's Name | Tomokazu TAKAHASHI |
| 2nd Author's Affiliation | Graduate School of Infomation Science, Nagoya University |
| 3rd Author's Name | Ichiro IDE |
| 3rd Author's Affiliation | Graduate School of Infomation Science, Nagoya University |
| 4th Author's Name | Yoshito MEKADA |
| 4th Author's Affiliation | Life System Science and Technology, Chukyo University |
| 5th Author's Name | Hiroshi MURASE |
| 5th Author's Affiliation | Graduate School of Infomation Science, Nagoya University |
| Date | 2005-02-25 |
| Paper # | NLC2004-119,PRMU2004-201 |
| Volume (vol) | vol.104 |
| Number (no) | 668 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |