A lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehicles

Developing algorithms to identify fruit cutting locations is important for the functionality of harvesting robots. However, existing studies often rely on multi-stage detection processes. This complicates system design and hinders real-time performance. To address these challenges, this study propos...

Full description

Saved in:
Bibliographic Details
Main Authors: Duc Tai Nguyen, Phuoc Bao Long Do, Doan Dang Khoa Nguyen, Wei-Chih Lin
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Smart Agricultural Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772375525002849
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850111131611299840
author Duc Tai Nguyen
Phuoc Bao Long Do
Doan Dang Khoa Nguyen
Wei-Chih Lin
author_facet Duc Tai Nguyen
Phuoc Bao Long Do
Doan Dang Khoa Nguyen
Wei-Chih Lin
author_sort Duc Tai Nguyen
collection DOAJ
description Developing algorithms to identify fruit cutting locations is important for the functionality of harvesting robots. However, existing studies often rely on multi-stage detection processes. This complicates system design and hinders real-time performance. To address these challenges, this study proposes a novel detection model for banana-harvesting robots. The model simultaneously detects banana bunches and stalks in orchard environments. It is built upon the YOLOv8n (You Only Look Once version 8 nano) baseline and includes enhancements to improve accuracy while preserving a lightweight architecture. Specifically, the standard convolution layers are upgraded with a lightweight group-shuffle convolution module, reducing complexity while preserving efficiency. Additionally, a novel C2f-fast efficient channel attention module is proposed in the backbone, significantly enhancing the model's feature extraction capabilities. Furthermore, the bidirectional feature pyramid network is introduced in the original neck network, improving feature aggregation and adaptability to varying environmental conditions. Experimental results demonstrate that the proposed model achieves performance, with precision, recall, and mAP50 metrics of 96.3 %, 90 %, and 94.5 %, respectively, exceeding the baseline model by 0.5 %, 2.6 %, and 1 %. Moreover, the parameters and size of the proposed model are optimized to 1.7 M and 3.7 MB, reflecting reductions of 43.3 % and 40.3 %, respectively, in comparison to the baseline. Notably, the proposed model outperforms the previous detection models, offering high accuracy while optimizing computational efficiency. These advancements make the proposed model highly suitable for deployment on embedded systems in agricultural robots.
format Article
id doaj-art-d278e8347350403ab74a3bde65866269
institution OA Journals
issn 2772-3755
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Smart Agricultural Technology
spelling doaj-art-d278e8347350403ab74a3bde658662692025-08-20T02:37:41ZengElsevierSmart Agricultural Technology2772-37552025-08-011110105110.1016/j.atech.2025.101051A lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehiclesDuc Tai Nguyen0Phuoc Bao Long Do1Doan Dang Khoa Nguyen2Wei-Chih Lin3Department of Mechanical and Electro-Mechanical Engineering, National Sun Yat-sen University, Kaohsiung City, TaiwanDepartment of Mechanical and Electro-Mechanical Engineering, National Sun Yat-sen University, Kaohsiung City, TaiwanDepartment of Mechanical and Electro-Mechanical Engineering, National Sun Yat-sen University, Kaohsiung City, TaiwanCorresponding author.; Department of Mechanical and Electro-Mechanical Engineering, National Sun Yat-sen University, Kaohsiung City, TaiwanDeveloping algorithms to identify fruit cutting locations is important for the functionality of harvesting robots. However, existing studies often rely on multi-stage detection processes. This complicates system design and hinders real-time performance. To address these challenges, this study proposes a novel detection model for banana-harvesting robots. The model simultaneously detects banana bunches and stalks in orchard environments. It is built upon the YOLOv8n (You Only Look Once version 8 nano) baseline and includes enhancements to improve accuracy while preserving a lightweight architecture. Specifically, the standard convolution layers are upgraded with a lightweight group-shuffle convolution module, reducing complexity while preserving efficiency. Additionally, a novel C2f-fast efficient channel attention module is proposed in the backbone, significantly enhancing the model's feature extraction capabilities. Furthermore, the bidirectional feature pyramid network is introduced in the original neck network, improving feature aggregation and adaptability to varying environmental conditions. Experimental results demonstrate that the proposed model achieves performance, with precision, recall, and mAP50 metrics of 96.3 %, 90 %, and 94.5 %, respectively, exceeding the baseline model by 0.5 %, 2.6 %, and 1 %. Moreover, the parameters and size of the proposed model are optimized to 1.7 M and 3.7 MB, reflecting reductions of 43.3 % and 40.3 %, respectively, in comparison to the baseline. Notably, the proposed model outperforms the previous detection models, offering high accuracy while optimizing computational efficiency. These advancements make the proposed model highly suitable for deployment on embedded systems in agricultural robots.http://www.sciencedirect.com/science/article/pii/S2772375525002849Deep learningDetection optimizationBanana detectionLightweight architectureBanana harvesting vehicles
spellingShingle Duc Tai Nguyen
Phuoc Bao Long Do
Doan Dang Khoa Nguyen
Wei-Chih Lin
A lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehicles
Smart Agricultural Technology
Deep learning
Detection optimization
Banana detection
Lightweight architecture
Banana harvesting vehicles
title A lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehicles
title_full A lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehicles
title_fullStr A lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehicles
title_full_unstemmed A lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehicles
title_short A lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehicles
title_sort lightweight and optimized deep learning model for detecting banana bunches and stalks in autonomous harvesting vehicles
topic Deep learning
Detection optimization
Banana detection
Lightweight architecture
Banana harvesting vehicles
url http://www.sciencedirect.com/science/article/pii/S2772375525002849
work_keys_str_mv AT ductainguyen alightweightandoptimizeddeeplearningmodelfordetectingbananabunchesandstalksinautonomousharvestingvehicles
AT phuocbaolongdo alightweightandoptimizeddeeplearningmodelfordetectingbananabunchesandstalksinautonomousharvestingvehicles
AT doandangkhoanguyen alightweightandoptimizeddeeplearningmodelfordetectingbananabunchesandstalksinautonomousharvestingvehicles
AT weichihlin alightweightandoptimizeddeeplearningmodelfordetectingbananabunchesandstalksinautonomousharvestingvehicles
AT ductainguyen lightweightandoptimizeddeeplearningmodelfordetectingbananabunchesandstalksinautonomousharvestingvehicles
AT phuocbaolongdo lightweightandoptimizeddeeplearningmodelfordetectingbananabunchesandstalksinautonomousharvestingvehicles
AT doandangkhoanguyen lightweightandoptimizeddeeplearningmodelfordetectingbananabunchesandstalksinautonomousharvestingvehicles
AT weichihlin lightweightandoptimizeddeeplearningmodelfordetectingbananabunchesandstalksinautonomousharvestingvehicles