講演抄録/キーワード |
講演名 |
2022-11-24 15:20
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(Waseda Univ.)・Shuntaro Aotake・Masatoshi Funabashi(SONY CSL) CS2022-55 IE2022-43 |
抄録 |
(和) |
(まだ登録されていません) |
(英) |
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. |
キーワード |
(和) |
/ / / / / / / |
(英) |
Harvest Robot / Point Cloud Processing / Mask R-CNN / Locating Cutting position / Fixed Harvesting path / / / |
文献情報 |
信学技報, vol. 122, no. 270, IE2022-43, pp. 39-44, 2022年11月. |
資料番号 |
IE2022-43 |
発行日 |
2022-11-17 (CS, IE) |
ISSN |
Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
CS2022-55 IE2022-43 |