Development of a Grape Cut Point Detection System Using Multi-Cameras for a Grape-Harvesting Robot

Harvesting grapes requires a large amount of manual labor. To reduce the labor force for the harvesting job, in this study, we developed a robot harvester for the vine grapes. In this paper, we proposed an algorithm that using multi-cameras, as well as artificial intelligence (AI) object detection m...

Full description

Saved in:
Bibliographic Details
Main Authors: Liangliang Yang, Tomoki Noguchi, Yohei Hoshino
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/24/8035
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846102767610888192
author Liangliang Yang
Tomoki Noguchi
Yohei Hoshino
author_facet Liangliang Yang
Tomoki Noguchi
Yohei Hoshino
author_sort Liangliang Yang
collection DOAJ
description Harvesting grapes requires a large amount of manual labor. To reduce the labor force for the harvesting job, in this study, we developed a robot harvester for the vine grapes. In this paper, we proposed an algorithm that using multi-cameras, as well as artificial intelligence (AI) object detection methods, to detect the thin stem and decide the cut point. The camera system was constructed by two cameras that include multi-lenses. One camera is mounted at the base of the robot and named the “base camera”; the other camera is mounted at the robot hand and named the “hand camera” to recognize grapes and estimate the stem position. At the first step, the grapes are detected by using a You Only Look Once (YOLO) method, while the stems of the grapes are detected at the second step using a pixel-level semantic segmentation method. Field experiments were conducted at an outdoor grapes field. The experiment results show that the proposed algorithm and the camera system can successfully detect out the cut point, and the correct detection rate is around 98% and 93% in the indoor and outdoor conditions, respectively. The detection system was integrated to a grape-harvesting robot in the experiment, and the experiment results show the system can successfully harvest the grapes in the outdoor conditions.
format Article
id doaj-art-238981ffa292414485daa67ef99db6cd
institution Kabale University
issn 1424-8220
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-238981ffa292414485daa67ef99db6cd2024-12-27T14:52:47ZengMDPI AGSensors1424-82202024-12-012424803510.3390/s24248035Development of a Grape Cut Point Detection System Using Multi-Cameras for a Grape-Harvesting RobotLiangliang Yang0Tomoki Noguchi1Yohei Hoshino2Laboratory of Bio-Mechatronics, Faculty of Engineering, Kitami Institute of Technology, Koentyo 165, Kitami Shi 090-8507, Hokkaido, JapanLaboratory of Bio-Mechatronics, Faculty of Engineering, Kitami Institute of Technology, Koentyo 165, Kitami Shi 090-8507, Hokkaido, JapanLaboratory of Bio-Mechatronics, Faculty of Engineering, Kitami Institute of Technology, Koentyo 165, Kitami Shi 090-8507, Hokkaido, JapanHarvesting grapes requires a large amount of manual labor. To reduce the labor force for the harvesting job, in this study, we developed a robot harvester for the vine grapes. In this paper, we proposed an algorithm that using multi-cameras, as well as artificial intelligence (AI) object detection methods, to detect the thin stem and decide the cut point. The camera system was constructed by two cameras that include multi-lenses. One camera is mounted at the base of the robot and named the “base camera”; the other camera is mounted at the robot hand and named the “hand camera” to recognize grapes and estimate the stem position. At the first step, the grapes are detected by using a You Only Look Once (YOLO) method, while the stems of the grapes are detected at the second step using a pixel-level semantic segmentation method. Field experiments were conducted at an outdoor grapes field. The experiment results show that the proposed algorithm and the camera system can successfully detect out the cut point, and the correct detection rate is around 98% and 93% in the indoor and outdoor conditions, respectively. The detection system was integrated to a grape-harvesting robot in the experiment, and the experiment results show the system can successfully harvest the grapes in the outdoor conditions.https://www.mdpi.com/1424-8220/24/24/8035grape-harvesting robotmulti-camera systemyou only look once (YOLO) based grapes detectionstem detection using semantic segmentation
spellingShingle Liangliang Yang
Tomoki Noguchi
Yohei Hoshino
Development of a Grape Cut Point Detection System Using Multi-Cameras for a Grape-Harvesting Robot
Sensors
grape-harvesting robot
multi-camera system
you only look once (YOLO) based grapes detection
stem detection using semantic segmentation
title Development of a Grape Cut Point Detection System Using Multi-Cameras for a Grape-Harvesting Robot
title_full Development of a Grape Cut Point Detection System Using Multi-Cameras for a Grape-Harvesting Robot
title_fullStr Development of a Grape Cut Point Detection System Using Multi-Cameras for a Grape-Harvesting Robot
title_full_unstemmed Development of a Grape Cut Point Detection System Using Multi-Cameras for a Grape-Harvesting Robot
title_short Development of a Grape Cut Point Detection System Using Multi-Cameras for a Grape-Harvesting Robot
title_sort development of a grape cut point detection system using multi cameras for a grape harvesting robot
topic grape-harvesting robot
multi-camera system
you only look once (YOLO) based grapes detection
stem detection using semantic segmentation
url https://www.mdpi.com/1424-8220/24/24/8035
work_keys_str_mv AT liangliangyang developmentofagrapecutpointdetectionsystemusingmulticamerasforagrapeharvestingrobot
AT tomokinoguchi developmentofagrapecutpointdetectionsystemusingmulticamerasforagrapeharvestingrobot
AT yoheihoshino developmentofagrapecutpointdetectionsystemusingmulticamerasforagrapeharvestingrobot