| Presentation | 2018-03-18 Feature extraction of object shape from motion parallax using convolutional neural network ChengJun Shao, Makoto Murakami, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The convolution neural networks (CNN) have good feature extraction capability. In this paper, we propose a method which can extract 3D features of object shape from a sequence of RGB images captured with a single camera through two different convolutional neural networks such as a spatial feature extraction CNN and a spatiotemporal feature extraction CNN. We extract spatial features by trained spatial feature extraction CNN, and input them to spatiotemporal feature extraction CNN and extract features of object shape. As a result of experiment using simple building blocks, we extracted motion trajectory and direction. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | convolutional neural network / motion parallax / feature extraction |
| Paper # | BioX2017-41,PRMU2017-177 |
| 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) | Feature extraction of object shape from motion parallax using convolutional neural network |
| Sub Title (in English) | |
| Keyword(1) | convolutional neural network |
| Keyword(2) | motion parallax |
| Keyword(3) | feature extraction |
| 1st Author's Name | ChengJun Shao |
| 1st Author's Affiliation | Toyo University(Toyo Univ.) |
| 2nd Author's Name | Makoto Murakami |
| 2nd Author's Affiliation | Toyo University(Toyo Univ.) |
| Date | 2018-03-18 |
| Paper # | BioX2017-41,PRMU2017-177 |
| Volume (vol) | vol.117 |
| Number (no) | BioX-513,PRMU-514 |
| Page | pp.pp.31-36(BioX), pp.31-36(PRMU), |
| #Pages | 6 |
| Date of Issue | 2018-03-11 (BioX, PRMU) |