| Presentation | 2017-12-14 Object Recognition System using Deep Learning with Depth Image for Home Service Robots Yuma Yoshimoto, Hakaru Tamukoh, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In an aging society with fewer children, home service robots are expected to be realized. In order to bring a realization of the robots, it is necessary for a generic object recognition system to recognize a wide variety of objects with high accuracy. Therefore, in this research, we employ deep convolutional neural networks for the generic object recognition system. The networks are famous for their own high performance in recognition tasks. To improve the accuracy of the object recognition, utilizing both of the RGB and the depth images is effective. In this paper, we propose a new architecture for the deep convolutional neural networks to train both of the RGB and the depth images. Furthermore, we propose a new training method for proposed architecture. Experimental results show that effectiveness of the proposed architecture and training method. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Home Service Robots / Generic Object Recognition System / Deep Learning / CNN / Depth Image |
| Paper # | SIS2017-55 |
| Date of Issue | 2017-12-07 (SIS) |
| Conference Information | |
| Committee | SIS |
|---|---|
| Conference Date | 2017/12/14(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Tottori Prefectural Center for Lifelong Learning |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | System on Silicon, Short Range Wireless Systems, etc. |
| Chair | Hirokazu Tanaka(Hiroshima City Univ.) |
| Vice Chair | Takayuki Nakachi(NTT) / Noriaki Suetake(Yamaguchi Univ.) |
| Secretary | Takayuki Nakachi(Kanagawa Inst. of Tech.) / Noriaki Suetake(Kyushu Inst. of Tech.) |
| Assistant | Masaaki Fujiyoshi(Tokyo Metropolitan Univ.) / Takanori Koga(NIT, Tokuyama Col.) |
| Paper Information | |
| Registration To | Technical Committee on Smart Info-Media Systems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Object Recognition System using Deep Learning with Depth Image for Home Service Robots |
| Sub Title (in English) | |
| Keyword(1) | Home Service Robots |
| Keyword(2) | Generic Object Recognition System |
| Keyword(3) | Deep Learning |
| Keyword(4) | CNN |
| Keyword(5) | Depth Image |
| 1st Author's Name | Yuma Yoshimoto |
| 1st Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| 2nd Author's Name | Hakaru Tamukoh |
| 2nd Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| Date | 2017-12-14 |
| Paper # | SIS2017-55 |
| Volume (vol) | vol.117 |
| Number (no) | SIS-349 |
| Page | pp.pp.123-128(SIS), |
| #Pages | 6 |
| Date of Issue | 2017-12-07 (SIS) |