SWMD-YOLO: A Lightweight Model for Tomato Detection in Greenhouse Environments

The accurate detection of occluded tomatoes in complex greenhouse environments remains challenging due to the limited feature representation ability and high computational costs of existing models. This study proposes SWMD-YOLO, a lightweight multi-scale detection network optimized for greenhouse sc...

Full description

Saved in:
Bibliographic Details
Main Authors: Quan Wang, Ye Hua, Qiongdan Lou, Xi Kan
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Agronomy
Subjects:
Online Access:https://www.mdpi.com/2073-4395/15/7/1593
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849304151643652096
author Quan Wang
Ye Hua
Qiongdan Lou
Xi Kan
author_facet Quan Wang
Ye Hua
Qiongdan Lou
Xi Kan
author_sort Quan Wang
collection DOAJ
description The accurate detection of occluded tomatoes in complex greenhouse environments remains challenging due to the limited feature representation ability and high computational costs of existing models. This study proposes SWMD-YOLO, a lightweight multi-scale detection network optimized for greenhouse scenarios. The model integrates switchable atrous convolution (SAConv) and wavelet transform convolution (WTConv) for the dynamic adjustment of receptive fields for occlusion-adaptive feature extraction and to decompose features into multi-frequency sub-bands, respectively, thus preserving critical edge details of obscured targets. Traditional down-sampling is replaced with a dynamic sample (DySample) operator to minimize information loss during resolution transitions, while a multi-scale convolutional attention (MSCA) mechanism prioritizes discriminative regions under varying illumination. Additionally, we introduce Focaler-IoU, a novel loss function that addresses sample imbalance by dynamically re-weighting gradients for partially occluded and multi-scale targets. Experiments on greenhouse tomato data sets demonstrate that SWMD-YOLO achieves 93.47% mAP50 with a detection speed of 75.68 FPS, outperforming baseline models in accuracy while reducing parameters by 18.9%. Cross-data set validation confirms the model’s robustness to complex backgrounds and lighting variations. Overall, the proposed model provides a computationally efficient solution for real-time crop monitoring in resource-constrained precision agriculture systems.
format Article
id doaj-art-f0c8784a078d4e85b96e5437fa90af45
institution Kabale University
issn 2073-4395
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Agronomy
spelling doaj-art-f0c8784a078d4e85b96e5437fa90af452025-08-20T03:55:48ZengMDPI AGAgronomy2073-43952025-06-01157159310.3390/agronomy15071593SWMD-YOLO: A Lightweight Model for Tomato Detection in Greenhouse EnvironmentsQuan Wang0Ye Hua1Qiongdan Lou2Xi Kan3School of Internet of Things Engineering, Wuxi University, Wuxi 214105, ChinaSchool of Computer Science, Nanjing University of Information Science & Technology, Nanjing 210044, ChinaSchool of Internet of Things Engineering, Wuxi University, Wuxi 214105, ChinaSchool of Internet of Things Engineering, Wuxi University, Wuxi 214105, ChinaThe accurate detection of occluded tomatoes in complex greenhouse environments remains challenging due to the limited feature representation ability and high computational costs of existing models. This study proposes SWMD-YOLO, a lightweight multi-scale detection network optimized for greenhouse scenarios. The model integrates switchable atrous convolution (SAConv) and wavelet transform convolution (WTConv) for the dynamic adjustment of receptive fields for occlusion-adaptive feature extraction and to decompose features into multi-frequency sub-bands, respectively, thus preserving critical edge details of obscured targets. Traditional down-sampling is replaced with a dynamic sample (DySample) operator to minimize information loss during resolution transitions, while a multi-scale convolutional attention (MSCA) mechanism prioritizes discriminative regions under varying illumination. Additionally, we introduce Focaler-IoU, a novel loss function that addresses sample imbalance by dynamically re-weighting gradients for partially occluded and multi-scale targets. Experiments on greenhouse tomato data sets demonstrate that SWMD-YOLO achieves 93.47% mAP50 with a detection speed of 75.68 FPS, outperforming baseline models in accuracy while reducing parameters by 18.9%. Cross-data set validation confirms the model’s robustness to complex backgrounds and lighting variations. Overall, the proposed model provides a computationally efficient solution for real-time crop monitoring in resource-constrained precision agriculture systems.https://www.mdpi.com/2073-4395/15/7/1593tomato detectionlightweight modelwavelet transformattention mechanismmulti-scale feature fusion
spellingShingle Quan Wang
Ye Hua
Qiongdan Lou
Xi Kan
SWMD-YOLO: A Lightweight Model for Tomato Detection in Greenhouse Environments
Agronomy
tomato detection
lightweight model
wavelet transform
attention mechanism
multi-scale feature fusion
title SWMD-YOLO: A Lightweight Model for Tomato Detection in Greenhouse Environments
title_full SWMD-YOLO: A Lightweight Model for Tomato Detection in Greenhouse Environments
title_fullStr SWMD-YOLO: A Lightweight Model for Tomato Detection in Greenhouse Environments
title_full_unstemmed SWMD-YOLO: A Lightweight Model for Tomato Detection in Greenhouse Environments
title_short SWMD-YOLO: A Lightweight Model for Tomato Detection in Greenhouse Environments
title_sort swmd yolo a lightweight model for tomato detection in greenhouse environments
topic tomato detection
lightweight model
wavelet transform
attention mechanism
multi-scale feature fusion
url https://www.mdpi.com/2073-4395/15/7/1593
work_keys_str_mv AT quanwang swmdyoloalightweightmodelfortomatodetectioningreenhouseenvironments
AT yehua swmdyoloalightweightmodelfortomatodetectioningreenhouseenvironments
AT qiongdanlou swmdyoloalightweightmodelfortomatodetectioningreenhouseenvironments
AT xikan swmdyoloalightweightmodelfortomatodetectioningreenhouseenvironments