Efficient-tomato: a high-precision and lightweight method for cherry tomato ripeness and disease detection
- 1College of Electrical Engineering, Hebei University of Architecture
- 2College of Electrical Engineering, Yanshan University
- 3The First Affiliated Hospital of Hebei North University
Abstract
Accurate detection of cherry tomatoes at different ripeness and disease stages is important for automated harvesting and crop-quality monitoring, but illumination variation, fruit overlap, leaf occlusion, complex backgrounds, and small target sizes remain challenging. This study proposes Efficient-Tomato, a lightweight detector developed from YOLOv8s through the coordinated use of EfficientViT, BiFormer, CARAFE, and WIoUv1. EfficientViT serves as the backbone for lightweight multiscale feature extraction. BiFormer is inserted into the neck to enhance informative spatial regions, while CARAFE and lightweight neck-channel adaptation improve content-aware feature reconstruction. WIoUv1 replaces the CIoU component of the bounding-box regression loss, with DFL retained. The model was evaluated on a consolidated dataset of 1,583 original images containing six categories: disease, half-ripe, overripe, ripe, rotten, and unripe. The original images were divided into training, validation, and test subsets before augmentation, and only the training subset was augmented. Each model configuration was trained independently three times, and arithmetic means were reported. Compared with YOLOv8s, Efficient-Tomato increased precision from 89.5% to 97.5%, recall from 87.3% to 96.9%, [email protected] from 88.5% to 96.7%, and [email protected]:0.95 from 81.6% to 87.9%. The F1 score calculated from the tabulated mean precision and recall increased from 88.4% to 97.2%. FPS increased from 150.2 to 172.5, while the parameter count decreased from 22.5 M to 14.9 M. These results indicate that the coordinated design improves detection performance while reducing model complexity. Because inference speed was measured on an NVIDIA V100 GPU, further validation on embedded devices and harvesting robots is required before field deployment.
Related
- Lightweight visual detection approach for apple ripeness perception in intelligent orchard harvesting scenarios
- Cross-level attention and lightweight feature extraction for improved tomato ripeness detection in complex greenhouse environments
- ISD-YOLO: A lightweight and efficient feature extraction network for invoice seal detection
- LeafXNet: A Lightweight Explainable Model With Integrated Attention Mechanism for Fruit Leaf Disease Detection
- Hybrid local–global vision transformer framework for robust plant disease detection in precision agriculture
BibTeX
@article{zheng2026efficienttomato,
title = {{Efficient-tomato: a high-precision and lightweight method for cherry tomato ripeness and disease detection}},
author = {Yunchang Zheng and Mengfan Wang and Jiacheng Sun and Leyi Han and Yunlong Ye},
journal = {Frontiers in Plant Science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1880973},
url = {https://www.frontiersin.org/articles/10.3389/fpls.2026.1880973/full},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Efficient-tomato: a high-precision and lightweight method for cherry tomato ripeness and disease detection
AU - Yunchang Zheng
AU - Mengfan Wang
AU - Jiacheng Sun
AU - Leyi Han
AU - Yunlong Ye
PY - 2026
DA - 2026/10/14
JO - Frontiers in Plant Science
DO - 10.3389/fpls.2026.1880973
UR - https://www.frontiersin.org/articles/10.3389/fpls.2026.1880973/full
AB - Accurate detection of cherry tomatoes at different ripeness and disease stages is important for automated harvesting and crop-quality monitoring, but illumination variation, fruit overlap, leaf occlusion, complex backgrounds, and small target sizes remain challenging. This study proposes Efficient-Tomato, a lightweight detector developed from YOLOv8s through the coordinated use of EfficientViT, BiFormer, CARAFE, and WIoUv1. EfficientViT serves as the backbone for lightweight multiscale feature extraction. BiFormer is inserted into the neck to enhance informative spatial regions, while CARAFE and lightweight neck-channel adaptation improve content-aware feature reconstruction. WIoUv1 replaces the CIoU component of the bounding-box regression loss, with DFL retained. The model was evaluated on a consolidated dataset of 1,583 original images containing six categories: disease, half-ripe, overripe, ripe, rotten, and unripe. The original images were divided into training, validation, and test subsets before augmentation, and only the training subset was augmented. Each model configuration was trained independently three times, and arithmetic means were reported. Compared with YOLOv8s, Efficient-Tomato increased precision from 89.5% to 97.5%, recall from 87.3% to 96.9%, [email protected] from 88.5% to 96.7%, and [email protected]:0.95 from 81.6% to 87.9%. The F1 score calculated from the tabulated mean precision and recall increased from 88.4% to 97.2%. FPS increased from 150.2 to 172.5, while the parameter count decreased from 22.5 M to 14.9 M. These results indicate that the coordinated design improves detection performance while reducing model complexity. Because inference speed was measured on an NVIDIA V100 GPU, further validation on embedded devices and harvesting robots is required before field deployment.
SN - 1664-462X
ER -