| Presentation | 2018-03-19 3D Indoor Scene Classification using Images Reflecting the Depth Density of Voxel Group Kazuma Hamada, Masaki Aono, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Along with the spread of VR technology, demand for applications using scenes composed of 3D data is increasing and the number of 3D scene has a trend to increase. If there is technology that can recognize the 3D scene, it will be possible to help classify and organize 3D scenes. In this research, we propose a proprietary imaging method reflecting the depth density of 3D scene converted to voxels and describe indoor 3D scene classification applied to deep learning. By reflecting the depth density of the voxel group from the projection plane with the x, y and z axes as the depths respectively, images useful for classifying the 3D scene is generated. In the experiment, benchmark data sets of six categories were created based on the 3D scene published as Princeton University's SUNCG data set and compared with the conventional method typified by the method using such as voxel group and images as input. As a result, our proposed method could obtain classification result with higher accuracy than the conventional method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | 3D / 3D Scene / Scene Classification / Voxel / Imaging / Deep Learning |
| Paper # | BioX2017-68,PRMU2017-204 |
| Date of Issue | 2018-03-11 (BioX, PRMU) |
| Conference Information | |
| Committee | PRMU / BioX |
|---|---|
| Conference Date | 2018/3/18(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) / Kazuhiko Sumi(AGU) |
| Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Hiroshi Takano(Toyama Pref. Univ.) / Hitoshi Imaoka(NEC) |
| Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Hiroshi Takano(Shizuoka Univ.) / Hitoshi Imaoka(Fujitsu Labs.) |
| Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Masatsugu Ichino(Univ. of Electro-Comm.) / Naoyuki Takada(Secom) / Norihiro Okui(KDDI Research) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Biometrics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | 3D Indoor Scene Classification using Images Reflecting the Depth Density of Voxel Group |
| Sub Title (in English) | |
| Keyword(1) | 3D |
| Keyword(2) | 3D Scene |
| Keyword(3) | Scene Classification |
| Keyword(4) | Voxel |
| Keyword(5) | Imaging |
| Keyword(6) | Deep Learning |
| 1st Author's Name | Kazuma Hamada |
| 1st Author's Affiliation | Toyohashi University of Technology(Toyohashi Univ. of Tech.) |
| 2nd Author's Name | Masaki Aono |
| 2nd Author's Affiliation | Toyohashi University of Technology(Toyohashi Univ. of Tech.) |
| Date | 2018-03-19 |
| Paper # | BioX2017-68,PRMU2017-204 |
| Volume (vol) | vol.117 |
| Number (no) | BioX-513,PRMU-514 |
| Page | pp.pp.189-194(BioX), pp.189-194(PRMU), |
| #Pages | 6 |
| Date of Issue | 2018-03-11 (BioX, PRMU) |