Detection of young fruit for “Yuluxiang” pears in natural environments using YOLO-CiHFC

Signal Image and Video Processing, Год журнала: 2025, Номер 19(5)

Опубликована: Март 10, 2025

Язык: Английский

---

CO-YOLO: A lightweight and efficient model for Camellia oleifera fruit object detection and posture determination

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 235, С. 110394 - 110394

Опубликована: Апрель 12, 2025

Язык: Английский

---

FEW-YOLO: a lightweight ripe fruit detection algorithm in wolfberry based on improved YOLOv8

Journal of Food Measurement & Characterization, Год журнала: 2025, Номер unknown

Опубликована: Май 20, 2025

Язык: Английский

---

Persimmon fruit detection in complex scenes based on PerD-YOLOv8

Journal of Food Measurement & Characterization, Год журнала: 2025, Номер unknown

Опубликована: Май 29, 2025

Язык: Английский

---

YOLOv8n-DDA-SAM: Accurate Cutting-Point Estimation for Robotic Cherry-Tomato Harvesting

Agriculture, Год журнала: 2024, Номер 14(7), С. 1011 - 1011

Опубликована: Июнь 26, 2024

Accurately identifying cherry-tomato picking points and obtaining their coordinate locations is critical to the success of robots. However, previous methods for semantic segmentation alone or combining object detection with traditional image processing have struggled accurately determine point due challenges such as leaves well targets that are too small. In this study, we propose a YOLOv8n-DDA-SAM model adds branch target achieve desired compute point. To be specific, YOLOv8n used initial model, dynamic snake convolutional layer (DySnakeConv) more suitable stems in neck model. addition, large kernel attention mechanism adopted backbone use ADown convolution resulted better fusion stem features certain decrease number parameters without loss accuracy. Combined SAM, mask effectively obtained then accurate by simple shape-centering calculation. As suggested experimental results, proposed significantly improved from models not only detecting but also stem’s masks. [email protected] F1-score, achieved 85.90% 86.13% respectively. Compared original YOLOv8n, YOLOv7, RT-DETR-l YOLOv9c, has 24.7%, 21.85%, 19.76%, 15.99% F1-score increased 16.34%, 12.11%, 10.09%, 8.07% respectively, 6.37M. branch, does it need produce relevant datasets, its mIOU 11.43%, 6.94%, 5.53%, 4.22% 12.33%, 7.49%, 6.4%, 5.99% compared Deeplabv3+, Mask2former, DDRNet SAN summary, can satisfy requirements high-precision provides strategy system cherry-tomato.

Язык: Английский

---

YOLO-IAPs: A Rapid Detection Method for Invasive Alien Plants in the Wild Based on Improved YOLOv9

Agriculture, Год журнала: 2024, Номер 14(12), С. 2201 - 2201

Опубликована: Дек. 2, 2024

Invasive alien plants (IAPs) present a significant threat to ecosystems and agricultural production, necessitating rigorous monitoring detection for effective management control. To realize accurate rapid of invasive in the wild, we proposed approach grounded an advanced YOLOv9, referred as YOLO-IAPs, which incorporated several key enhancements including replacing down-sampling layers model’s backbone with DynamicConv module, integrating Triplet Attention mechanism into model, original CIoU MPDloU. These targeted collectively resulted substantial improvement accuracy robustness. Extensive training testing on self-constructed dataset demonstrated that model achieved 90.7%, corresponding recall, mAP50, mAP50:95 measured at 84.3%, 91.2%, 65.1%, speed 72 FPS. Compared baseline, showed increases 0.2% precision, 3.5% 1.0% mAP50. Additionally, YOLO-IAPs outperformed other state-of-the-art object models, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv10 series, Faster R-CNN, SSD, CenterNet, RetinaNet, demonstrating superior capabilities. Ablation studies further confirmed was effective, contributing overall performance, underscored its pre-eminence domain plant offered marked over traditional methodologies. The findings suggest has potential advance technological landscape monitoring.

Язык: Английский

---

Phenotypic-Based Maturity Detection and Oil Content Prediction in Xiangling Walnuts

Agriculture, Год журнала: 2024, Номер 14(8), С. 1422 - 1422

Опубликована: Авг. 22, 2024

The maturity grading of walnuts during harvesting relies on experience. In this paper, walnut images in a natural environment were collected to construct dataset, and deep learning algorithms utilized combine internal physical chemical indicators carry out research detection methods further oil content prediction by combining with indicators. main contents paper include collecting environment, constructing datasets, using combined indexes study methods. First, two image acquisition schemes designed, total 9504 from 23 August 21 September 2021. dataset was expanded 18,504 through data preprocessing enhancement. A self-supervised Gaussian attention network (GATCluster) ripeness method based clustering is proposed develop criteria unsupervised clustering, the accuracy verified analysis variance (ANOVA). test set 1500 88.33%. Secondly, improved ResNet34 proposed. feature extraction capability introducing Squeeze-and-Excitation Networks (SENet) channel mechanism convolutional self-attention module. results 50 show that root mean square error, average absolute percentage regression coefficient are 2.96, 0.103, 0.8822, respectively. experiments performs well predicting at different levels.

Язык: Английский

---

Analysis of Leaf cover on Raspberry Fruits Based on Hyperspectral Techniques Combined with Machine Learning Models

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Июль 15, 2024

The aim of this study is to explore the potential application hyperspectral technology in detecting problem fruit cover orchard. Three types data were collected using a instrument raspberry fruits with leaves. Machine learning models used classify and regress covered uncovered fruits. results show that can effectively differentiate under different conditions, spectral intensity performing better addressing issues. Random forest (RF) multilayer perceptron (MLP) demonstrated high accuracy classification analysis, MLP achieving ROC AUC value 0.99 on full-band data. Regression analysis also revealed significant correlation between degree coverage features, highlighting particular explanatory power light predicting coverage. This not only confirms precision agriculture, but provides new technical support for intelligent orchard management automated harvesting. Future research will focus improving generalisation ability models, integrating multi-source further improve detection, exploring development real-time monitoring automatic control systems achieve comprehensive intelligence management.

Язык: Английский

---