Presentation 2022-11-24
Locating the Fruit to Be Harvested and Estimating their Cut Positions from RGBD Images Acquired by a Camera Moved along a Fixed Path Using a Mask-RCNN Based Method
Wentao Zhao, Jun Ohya, Chanjin Seo, Takuya Otani, Taiga Tanaka, Koki Masaya, Atsuo Takanishi, Shuntaro Aotake, Masatoshi Funabashi,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes a Mask R-CNN[1] based method for locating fruits (tomatoes and yellow bell peppers, etc.) and estimating the cutting positions from RGBD images acquired by a camera moved along a fixed path. After getting mask results of all fruits and pedicels (cutting positions), the proposed method judges the matching relationship between the located fruit and pedicel according to the distance between fruit and pedicel. Experimental results show the proposed method effectively detects the cutting position of each fruit. The method is also robust in complex environments. In addition, it turns out that the fixed path strategy is valid for avoiding obstacles and reaching the pedicel and cutting position accurately. A high harvesting success rate was achieved in a Gazebo based simulated environment.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Harvest RobotPoint Cloud ProcessingMask R-CNNLocating Cutting positionFixed Harvesting path
Paper # CS2022-55,IE2022-43
Date of Issue 2022-11-17 (CS, IE)

Conference Information
Committee CS / IE / IPSJ-AVM / ITE-BCT
Conference Date 2022/11/24(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Nagoya Institute of Technology
Topics (in Japanese) (See Japanese page)
Topics (in English) Image coding, Communications and streaming technologies, etc.
Chair Daisuke Umehara(Kyoto Inst. of Tech.) / Kazuya Kodama(NII) / Hiroyuki Kasai(Waseda University)
Vice Chair Seiji Kozaki(Mitsubishi Electric) / Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(Univ. of Tokyo)
Secretary Seiji Kozaki(Chiba Inst. of Tech.) / Hiroyuki Bandoh(NTT) / Toshihiko Yamazaki(KDDI Research) / (Nagoya Inst. of Tech.) / (KDDI Research, Inc.)
Assistant Hikaru Kawasaki(NICT) / Yuta Ida(Yamaguchi Univ.) / Shunsuke Iwamura(NHK) / Shinobu Kudo(NTT)

Paper Information
Registration To Technical Committee on Communication Systems / Technical Committee on Image Engineering / Special Interest Group on Audio Visual and Multimedia Information Processing / Technical Group on Broadcasting Technology
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Locating the Fruit to Be Harvested and Estimating their Cut Positions from RGBD Images Acquired by a Camera Moved along a Fixed Path Using a Mask-RCNN Based Method
Sub Title (in English) *
Keyword(1) Harvest RobotPoint Cloud ProcessingMask R-CNNLocating Cutting positionFixed Harvesting path
1st Author's Name Wentao Zhao
1st Author's Affiliation Waseda University(Waseda Univ.)
2nd Author's Name Jun Ohya
2nd Author's Affiliation Waseda University(Waseda Univ.)
3rd Author's Name Chanjin Seo
3rd Author's Affiliation Waseda University(Waseda Univ.)
4th Author's Name Takuya Otani
4th Author's Affiliation Waseda University(Waseda Univ.)
5th Author's Name Taiga Tanaka
5th Author's Affiliation Waseda University(Waseda Univ.)
6th Author's Name Koki Masaya
6th Author's Affiliation Waseda University(Waseda Univ.)
7th Author's Name Atsuo Takanishi
7th Author's Affiliation Waseda University(Waseda Univ.)
8th Author's Name Shuntaro Aotake
8th Author's Affiliation Sony Computer Science Laboratories(SONY CSL)
9th Author's Name Masatoshi Funabashi
9th Author's Affiliation Sony Computer Science Laboratories(SONY CSL)
Date 2022-11-24
Paper # CS2022-55,IE2022-43
Volume (vol) vol.122
Number (no) CS-269,IE-270
Page pp.pp.39-44(CS), pp.39-44(IE),
#Pages 6
Date of Issue 2022-11-17 (CS, IE)