Stereo vision based broccoli recognition and attitude estimation method for field harvesting

At present, automatic broccoli harvest in field still faces some issues. It is difficult to segment broccoli in real time under complex field background, and hard to pick tilt-growing broccoli for the end-effector of robot. In this research, an improved YOLOv8n-seg model, named YOLO-Broccoli-Seg was...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhenni He, Fahui Yuan, Yansuo Zhou, Bingbo Cui, Yong He, Yufei Liu
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-09-01
Series:Artificial Intelligence in Agriculture
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2589721725000212
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850151663867789312
author Zhenni He
Fahui Yuan
Yansuo Zhou
Bingbo Cui
Yong He
Yufei Liu
author_facet Zhenni He
Fahui Yuan
Yansuo Zhou
Bingbo Cui
Yong He
Yufei Liu
author_sort Zhenni He
collection DOAJ
description At present, automatic broccoli harvest in field still faces some issues. It is difficult to segment broccoli in real time under complex field background, and hard to pick tilt-growing broccoli for the end-effector of robot. In this research, an improved YOLOv8n-seg model, named YOLO-Broccoli-Seg was proposed for broccoli recognition. Through adding a triplet attention module to YOLOv8-Seg model, the feature fusion capability of the algorithm is improved significantly. The mean average precision mAP50 (Mask), mAP95 (Mask), mAP50 (Bounding Box, Bbox) and mAP95 (Bbox) of YOLO-Broccoli-Seg are 0.973, 0.683, 0.973 and 0.748 respectively. Precision P-value was improved the most, with an increment of 8.7 %. In addition, an attitude estimation method based on three-dimensional point cloud is proposed. When the tilt angle of broccoli is between −30°and 30°, the R2 between the estimated value and the true value is 0.934. It indicated that this method can well represent the growth attitude of broccoli. This research can provide the rich broccoli information and technical basis for the automated broccoli picking.
format Article
id doaj-art-eb9a0f1b0b064a1a87eeed15f0d20cac
institution OA Journals
issn 2589-7217
language English
publishDate 2025-09-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Artificial Intelligence in Agriculture
spelling doaj-art-eb9a0f1b0b064a1a87eeed15f0d20cac2025-08-20T02:26:09ZengKeAi Communications Co., Ltd.Artificial Intelligence in Agriculture2589-72172025-09-0115352653610.1016/j.aiia.2025.02.002Stereo vision based broccoli recognition and attitude estimation method for field harvestingZhenni He0Fahui Yuan1Yansuo Zhou2Bingbo Cui3Yong He4Yufei Liu5College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, ChinaSchool of Mechanical Engineering, Tianjin University, Tianjin 300072, ChinaKey Laboratory of Modern Agricultural Equipment and Technology, Jiangsu University, Ministry of Education, Zhenjiang 212013, ChinaCollege of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China; Corresponding authors.College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China; Corresponding authors.At present, automatic broccoli harvest in field still faces some issues. It is difficult to segment broccoli in real time under complex field background, and hard to pick tilt-growing broccoli for the end-effector of robot. In this research, an improved YOLOv8n-seg model, named YOLO-Broccoli-Seg was proposed for broccoli recognition. Through adding a triplet attention module to YOLOv8-Seg model, the feature fusion capability of the algorithm is improved significantly. The mean average precision mAP50 (Mask), mAP95 (Mask), mAP50 (Bounding Box, Bbox) and mAP95 (Bbox) of YOLO-Broccoli-Seg are 0.973, 0.683, 0.973 and 0.748 respectively. Precision P-value was improved the most, with an increment of 8.7 %. In addition, an attitude estimation method based on three-dimensional point cloud is proposed. When the tilt angle of broccoli is between −30°and 30°, the R2 between the estimated value and the true value is 0.934. It indicated that this method can well represent the growth attitude of broccoli. This research can provide the rich broccoli information and technical basis for the automated broccoli picking.http://www.sciencedirect.com/science/article/pii/S2589721725000212Broccoli recognitionInstance segmentationAttitude estimationYOLOv8n-SegAgricultural automation
spellingShingle Zhenni He
Fahui Yuan
Yansuo Zhou
Bingbo Cui
Yong He
Yufei Liu
Stereo vision based broccoli recognition and attitude estimation method for field harvesting
Artificial Intelligence in Agriculture
Broccoli recognition
Instance segmentation
Attitude estimation
YOLOv8n-Seg
Agricultural automation
title Stereo vision based broccoli recognition and attitude estimation method for field harvesting
title_full Stereo vision based broccoli recognition and attitude estimation method for field harvesting
title_fullStr Stereo vision based broccoli recognition and attitude estimation method for field harvesting
title_full_unstemmed Stereo vision based broccoli recognition and attitude estimation method for field harvesting
title_short Stereo vision based broccoli recognition and attitude estimation method for field harvesting
title_sort stereo vision based broccoli recognition and attitude estimation method for field harvesting
topic Broccoli recognition
Instance segmentation
Attitude estimation
YOLOv8n-Seg
Agricultural automation
url http://www.sciencedirect.com/science/article/pii/S2589721725000212
work_keys_str_mv AT zhennihe stereovisionbasedbroccolirecognitionandattitudeestimationmethodforfieldharvesting
AT fahuiyuan stereovisionbasedbroccolirecognitionandattitudeestimationmethodforfieldharvesting
AT yansuozhou stereovisionbasedbroccolirecognitionandattitudeestimationmethodforfieldharvesting
AT bingbocui stereovisionbasedbroccolirecognitionandattitudeestimationmethodforfieldharvesting
AT yonghe stereovisionbasedbroccolirecognitionandattitudeestimationmethodforfieldharvesting
AT yufeiliu stereovisionbasedbroccolirecognitionandattitudeestimationmethodforfieldharvesting