| Presentation | 2019-05-30 Estimating areas in images for grasping an object by a three-fingered robot hand Atsuki Tsukamoto, Ryosuke Kubota, Kiyoshi Kogure, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper proposes a method for estimation areas for grasping an object by a three-fingered robot hand. The method takes as its input a grayscale image that includes a target object and generates an image or images that indicate suitable areas by using fully convolutional networks. The method has been evaluated experimentally with six kinds of network models, that is, three kinds of basic models and their corresponding models augmented by introducing the task of predicting the target object region. The experimental results show that the method can estimate suitable areas with all of these six models and that the best performance is obtained by using the augmented network models for three binary classification tasks. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | object grasping / fully convolutional network / multitask learning |
| Paper # | PRMU2019-4 |
| Date of Issue | 2019-05-23 (PRMU) |
| Conference Information | |
| Committee | PRMU / IPSJ-CVIM |
|---|---|
| Conference Date | 2019/5/30(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinichi Sato(NII) |
| Vice Chair | Yoshihisa Ijiri(Omron) / Toru Tamaki(Hiroshima Univ.) |
| Secretary | Yoshihisa Ijiri(NEC) / Toru Tamaki(Osaka Univ.) |
| Assistant | Go Irie(NTT) / Yoshitaka Ushiku(Univ. of Tokyo) |
| Paper Information | |
| Registration To | Technical Committee on Pattern Recognition and Media Understanding / Special Interest Group on Computer Vision and Image Media |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Estimating areas in images for grasping an object by a three-fingered robot hand |
| Sub Title (in English) | |
| Keyword(1) | object grasping |
| Keyword(2) | fully convolutional network |
| Keyword(3) | multitask learning |
| 1st Author's Name | Atsuki Tsukamoto |
| 1st Author's Affiliation | Kanazawa Institute of Technology(KIT) |
| 2nd Author's Name | Ryosuke Kubota |
| 2nd Author's Affiliation | Kanazawa Institute of Technology(KIT) |
| 3rd Author's Name | Kiyoshi Kogure |
| 3rd Author's Affiliation | Kanazawa Institute of Technology(KIT) |
| Date | 2019-05-30 |
| Paper # | PRMU2019-4 |
| Volume (vol) | vol.119 |
| Number (no) | PRMU-64 |
| Page | pp.pp.19-24(PRMU), |
| #Pages | 6 |
| Date of Issue | 2019-05-23 (PRMU) |