Presentation | 2020-12-18 Estimating 3D regions for grasping an object Atsuki Tsukamoto, Kiyoshi Kogure, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper proposes a method for estimating 3D regions for object grasping. The method takes as its inputs two RGB images, each from one of two stereo cameras, and translates them into object grasping region images, from which it estimates 3D object grasping regions based on stereo matching. The translation is conducted using fully convolutional networks. The method has been evaluated experimentally with four kinds of fully convolutional network models, that is, two kinds of single task models and two kinds of multi-task models, each with object region estimation task as its auxiliary task. The experimental results show that the proposed method can estimate 3D regions for object grasping for all of these four kinds of models. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | object grasping / fully convolutional network / multi-task learning |
Paper # | PRMU2020-65 |
Date of Issue | 2020-12-10 (PRMU) |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2020/12/17(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Transfer learning and few shot learning |
Chair | Yoichi Sato(Univ. of Tokyo) |
Vice Chair | Akisato Kimura(NTT) / Masakazu Iwamura(Osaka Pref. Univ.) |
Secretary | Akisato Kimura(Mobility Technologies) / Masakazu Iwamura(Chubu Univ.) |
Assistant | Takashi Shibata(NTT) / Masashi Nishiyama(Tottori Univ.) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Estimating 3D regions for grasping an object |
Sub Title (in English) | |
Keyword(1) | object grasping |
Keyword(2) | fully convolutional network |
Keyword(3) | multi-task learning |
1st Author's Name | Atsuki Tsukamoto |
1st Author's Affiliation | Kanazawa Institute of Technology(KIT) |
2nd Author's Name | Kiyoshi Kogure |
2nd Author's Affiliation | Kanazawa Institute of Technology(KIT) |
Date | 2020-12-18 |
Paper # | PRMU2020-65 |
Volume (vol) | vol.120 |
Number (no) | PRMU-300 |
Page | pp.pp.156-160(PRMU), |
#Pages | 5 |
Date of Issue | 2020-12-10 (PRMU) |