LGD-YOLO: An Asymmetric Lightweight Network with Dynamic Feature Alignment for Greenhouse Tomato Maturity Detection
Open Access
- 14 July 2026
- journal article
- research article
- Published by MDPI AG in Agriculture
- Vol. 16 (14) , 1517
Abstract
Greenhouse tomato detection faces critical challenges due to dense fruit occlusion, background interference, and the stringent computational constraints inherent to edge-deployed harvesting robots. Resolving these bottlenecks requires efficient architectures. We propose LGD-YOLO as an asymmetric lightweight network adapted from YOLOv10n specifically for edge-based tomato maturity detection. The architecture integrates a C2f-GMKSF module utilizing grouped multi-kernel convolutions to extract multi-scale textures with limited computational overhead. Precise feature alignment under occluded conditions is subsequently achieved through a Dy-HSFPN structure, accompanied by a C2f-CFCGLU module that expands the receptive field while preserving linear complexity. Furthermore, replacing the traditional detection head with a partial convolution head reduces memory access costs. A Focaler-Wise-SIoU loss function is utilized to stabilize bounding box regression against the lightweight penalty without introducing inference latency. Performance evaluations on a custom three-class dataset with a 180-image test set yield an 88.0% mAP@50. Relative to the baseline model, LGD-YOLO improves detection accuracy by 0.6 percentage points while shrinking the parameter volume by 37.6% to 1.41 M and lowering computational demand by 41.5% to 3.8 GFLOPs. Hardware deployment on an NVIDIA Jetson AGX Orin achieves a sustained processing speed of 40.6 FPS, while the weight file is 2.99 MB, supporting its feasibility for real-time agricultural robotics.Keywords
Funding Information
- National Natural Science Foundation of China (62476251)
- National Natural Science Foundation of China (32401708)
- National Key Research and Development Program of China (2019YFE0126100)
This publication has 49 references indexed in Scilit:
- SE-YOLO: A sobel-enhanced framework for high-accuracy, lightweight real-time tomato detection with edge deployment capabilityComputers and Electronics in Agriculture, 2025
- Sensing technology for greenhouse tomato production: A systematic reviewSmart Agricultural Technology, 2025
- EggplantDet: An efficient lightweight model for eggplant disease detectionAlexandria Engineering Journal, 2024
- Smart solutions for capsicum Harvesting: Unleashing the power of YOLO for Detection, Segmentation, growth stage Classification, Counting, and real-time mobile identificationComputers and Electronics in Agriculture, 2024
- Accurate leukocyte detection based on deformable-DETR and multi-level feature fusion for aiding diagnosis of blood diseasesComputers in Biology and Medicine, 2024
- Lightweight tomato real-time detection method based on improved YOLO and mobile deploymentComputers and Electronics in Agriculture, 2023
- Efficient tomato harvesting robot based on image processing and deep learningPrecision Agriculture, 2022
- Rachis detection and three-dimensional localization of cut off point for vision-based banana robotComputers and Electronics in Agriculture, 2022
- Development of tomato detection model for robotic platform using deep learningMultimedia Tools and Applications, 2021
- A survey on the 5G network and its impact on agriculture: Challenges and opportunitiesComputers and Electronics in Agriculture, 2021