Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS

To achieve accurate detection of tomato fruit maturity and enable automated harvesting in natural environments, this paper presents a more lightweight and efficient maturity detection algorithm, YOLO-DGS, addressing the challenges of subtle maturity differences between regular and cherry tomatoes, a...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengyuan Zhao, Beibei Cui, Yuehao Yu, Xiaoyi Zhang, Jiaxin Xu, Fengzheng Shi, Liang Zhao
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/9/2664
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312674639249408
author Mengyuan Zhao
Beibei Cui
Yuehao Yu
Xiaoyi Zhang
Jiaxin Xu
Fengzheng Shi
Liang Zhao
author_facet Mengyuan Zhao
Beibei Cui
Yuehao Yu
Xiaoyi Zhang
Jiaxin Xu
Fengzheng Shi
Liang Zhao
author_sort Mengyuan Zhao
collection DOAJ
description To achieve accurate detection of tomato fruit maturity and enable automated harvesting in natural environments, this paper presents a more lightweight and efficient maturity detection algorithm, YOLO-DGS, addressing the challenges of subtle maturity differences between regular and cherry tomatoes, as well as fruit occlusion. First, to enhance feature extraction at various levels of abstraction in the input data, this paper proposes a novel segment-wise convolution module, C2f-GB. This module performs convolution in stages on the feature map, generating more feature maps with fewer parameters and computational resources, thereby improving the model’s feature extraction capability while reducing parameter count and computational cost. Next, based on the YOLO v10 algorithm, this paper removes redundant detection layers to enhance the model’s ability to capture specific features and further reduce the number of parameters. This paper then integrates a bidirectional feature pyramid network (BiFPN) into the neck network to improve feature capture across different scales, enhancing the model’s ability to handle objects of varying sizes and complexities. Finally, we introduce a novel channel attention mechanism that allows the network to dynamically adjust its focus on channels, efficiently utilizing available information. Experimental results demonstrate that the improved YOLO-DGS model achieves a 2.6% increase in F1 score, 2.1% in recall, 2% in mAP50, and 1% in mAP50-95. Additionally, inference speed is improved by 12.5%, and the number of parameters is reduced by 26.3%. Compared to current mainstream lightweight object detection models, YOLO-DGS outperforms them, offering an efficient solution for the tomato harvesting robot vision system in natural environments.
format Article
id doaj-art-85f3c0db60f44af2a80d072bad3fbc47
institution Kabale University
issn 1424-8220
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-85f3c0db60f44af2a80d072bad3fbc472025-08-20T03:53:01ZengMDPI AGSensors1424-82202025-04-01259266410.3390/s25092664Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGSMengyuan Zhao0Beibei Cui1Yuehao Yu2Xiaoyi Zhang3Jiaxin Xu4Fengzheng Shi5Liang Zhao6School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaCollege of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, ChinaTo achieve accurate detection of tomato fruit maturity and enable automated harvesting in natural environments, this paper presents a more lightweight and efficient maturity detection algorithm, YOLO-DGS, addressing the challenges of subtle maturity differences between regular and cherry tomatoes, as well as fruit occlusion. First, to enhance feature extraction at various levels of abstraction in the input data, this paper proposes a novel segment-wise convolution module, C2f-GB. This module performs convolution in stages on the feature map, generating more feature maps with fewer parameters and computational resources, thereby improving the model’s feature extraction capability while reducing parameter count and computational cost. Next, based on the YOLO v10 algorithm, this paper removes redundant detection layers to enhance the model’s ability to capture specific features and further reduce the number of parameters. This paper then integrates a bidirectional feature pyramid network (BiFPN) into the neck network to improve feature capture across different scales, enhancing the model’s ability to handle objects of varying sizes and complexities. Finally, we introduce a novel channel attention mechanism that allows the network to dynamically adjust its focus on channels, efficiently utilizing available information. Experimental results demonstrate that the improved YOLO-DGS model achieves a 2.6% increase in F1 score, 2.1% in recall, 2% in mAP50, and 1% in mAP50-95. Additionally, inference speed is improved by 12.5%, and the number of parameters is reduced by 26.3%. Compared to current mainstream lightweight object detection models, YOLO-DGS outperforms them, offering an efficient solution for the tomato harvesting robot vision system in natural environments.https://www.mdpi.com/1424-8220/25/9/2664tomatoripeness detectionYOLO-DGSC2f-GBBiFPNchannel attention
spellingShingle Mengyuan Zhao
Beibei Cui
Yuehao Yu
Xiaoyi Zhang
Jiaxin Xu
Fengzheng Shi
Liang Zhao
Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS
Sensors
tomato
ripeness detection
YOLO-DGS
C2f-GB
BiFPN
channel attention
title Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS
title_full Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS
title_fullStr Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS
title_full_unstemmed Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS
title_short Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS
title_sort intelligent detection of tomato ripening in natural environments using yolo dgs
topic tomato
ripeness detection
YOLO-DGS
C2f-GB
BiFPN
channel attention
url https://www.mdpi.com/1424-8220/25/9/2664
work_keys_str_mv AT mengyuanzhao intelligentdetectionoftomatoripeninginnaturalenvironmentsusingyolodgs
AT beibeicui intelligentdetectionoftomatoripeninginnaturalenvironmentsusingyolodgs
AT yuehaoyu intelligentdetectionoftomatoripeninginnaturalenvironmentsusingyolodgs
AT xiaoyizhang intelligentdetectionoftomatoripeninginnaturalenvironmentsusingyolodgs
AT jiaxinxu intelligentdetectionoftomatoripeninginnaturalenvironmentsusingyolodgs
AT fengzhengshi intelligentdetectionoftomatoripeninginnaturalenvironmentsusingyolodgs
AT liangzhao intelligentdetectionoftomatoripeninginnaturalenvironmentsusingyolodgs