Integrating artificial intelligence and Internet of Things (IoT) for enhanced crop monitoring and management in precision agriculture

Sensors International, Journal Year: 2024, Volume and Issue: 5, P. 100292 - 100292

Published: Jan. 1, 2024

The integration of Artificial Intelligence (AI) and Internet Things (IoT) technologies is transforming precision agriculture by enhancing crop monitoring management. This review explores cutting-edge methodologies innovations in modern agriculture, including high-throughput phenotyping, remote sensing, automated agricultural robots (AgroBots). These automate tasks such as harvesting, sorting, weed detection, significantly reducing labor costs environmental impacts. High-throughput phenotyping leverages spectral imaging, robotics to collect data on plant traits, enabling informed decisions fertilization, irrigation, pest DGPS sensing offer precise, real-time essential for soil condition assessment health monitoring. Advanced image segmentation techniques ensure accurate detection plants fruits, overcoming challenges posed varying lighting conditions complex backgrounds. Case studies like the PACMAN SCRI project apple load management Project PANTHEON's SCADA system hazelnut orchard demonstrate transformative potential AI IoT optimizing practices. upcoming 5G future 6G mobile networks promises address connectivity challenges, promoting widespread adoption smart However, several research gaps remain. Integrating diverse datasets, ensuring scalability small medium-sized farms, decision-making need further investigation. Developing robust models devices varied conditions, creating user-friendly interfaces farmers, addressing privacy security concerns are essential. Addressing these can enhance effectiveness leading more sustainable productive farming

Language: Английский

---

Unlocking plant secrets: A systematic review of 3D imaging in plant phenotyping techniques

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 222, P. 109033 - 109033

Published: May 18, 2024

Language: Английский

---

OrangeStereo: A navel orange stereo matching network for 3D surface reconstruction

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 217, P. 108626 - 108626

Published: Jan. 14, 2024

Language: Английский

---

Vineyard Zoning and Vine Detection Using Machine Learning in Unmanned Aerial Vehicle Imagery

Remote Sensing, Journal Year: 2024, Volume and Issue: 16(3), P. 584 - 584

Published: Feb. 3, 2024

Precision viticulture systems are essential for enhancing traditional intensive viticulture, achieving high-quality results, and minimizing costs. This study explores the integration of Unmanned Aerial Vehicles (UAVs) artificial intelligence in precision focusing on vine detection vineyard zoning. Vine employs YOLO (You Only Look Once) deep learning algorithm, a remarkable 90% accuracy by analysing UAV imagery with various spectral ranges from phenological stages. Vineyard zoning, achieved through application K-means incorporates geospatial data such as Normalized Difference Vegetation Index (NDVI) assessment nitrogen, phosphorus, potassium content leaf blades petioles. approach enables efficient resource management tailored to each zone’s specific needs. The research aims develop decision-support model viticulture. proposed demonstrates high defines zones variable weighting factors assigned while preserving location information, revealing significant differences variables. model’s advantages lie its rapid results minimal requirements, offering profound insights into benefits precise management. has potential expedite decision making, allowing adaptive strategies based unique conditions zone.

Language: Английский

---

Grape yield estimation with a smartphone’s colour and depth cameras using machine learning and computer vision techniques

Computers and Electronics in Agriculture, Journal Year: 2023, Volume and Issue: 213, P. 108174 - 108174

Published: Sept. 6, 2023

A smartphone with both colour and time of flight depth cameras is used for automated grape yield estimation Chardonnay grapes. new technique developed to automatically identify berries in the smartphone's maps. This utilises distortion peaks map caused by diffused scattering light within each berry. then extended allow unsupervised training a YOLOv7 model detection images. correlation coefficient (R2) 0.946 was achieved when comparing count observed RGB images those accurately identified YOLO. Additionally, an average precision score 0.970 attained. Two techniques are presented estimate size generate 3D models bunches using information.

Language: Английский

---

Vine variety identification through leaf image classification: a large-scale study on the robustness of five deep learning models

The Journal of Agricultural Science, Journal Year: 2024, Volume and Issue: 162(1), P. 19 - 32

Published: Feb. 1, 2024

Abstract Varietal identification plays a pivotal role in viticulture for several purposes. Nowadays, such is accomplished using ampelography and molecular markers, techniques requiring specific expertise equipment. Deep learning, on the other hand, appears to be viable cost-effective alternative, as recent studies claim that computer vision models can identify different vine varieties with high accuracy. Such works, however, limit their scope handful of selected do not provide accurate figures external data validation. In current study, five well-known were applied leaf images verify whether results presented literature replicated over larger set consisting 27 26 382 images. It was built 2 years dedicated field sampling at three geographically distinct sites, validation collected from Internet. Cross-validation purpose-built confirm results. However, same models, when validated against independent set, appear unable generalize training retain performances measured during cross These indicate further enhancement have been done filling gap developing more reliable model discriminate among grape varieties, underlining that, achieve this purpose, image resolution crucial factor development models.

Language: Английский

---

Design of a Multifunctional Resin-Based Outdoor Spherical Robot Shell for Ultrahigh Visible to Near-Infrared Transmittance and Mid-Infrared Radiative Cooling

ACS Omega, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 11, 2025

As robots undertake increasingly complex tasks, such as real-time visible image sensing, environmental analysis, and weather monitoring under harsh conditions, design of an appropriate robot shell has become crucial to ensure the reliability internal electronic components. Several key factors, cooling efficiency, transparency, mechanical performance, weathering resistance material, are proposed in this research future functionality. In study, a polymeric double-layered for fabrication by stereolithography 3D printing was designed, featuring porous outer layer spherical inner shell. The provides approximately 90% transmission near-infrared wavelength range (450-1050 nm) ensures proper functioning optical devices, cameras, lidar, solar cells, inside robot. addition, material displays high emittance mid-infrared (5-20 μm) facilitate effective radiative protect control system from thermal damage. 3D-printed is exposed real environment three months, its stable performance confirms ability. Moreover, promotes strength while moving. optimal 50% designed continuous moving impact. Finite element simulations also used show that porosity significantly reduces strain energy upon Compared with conventional single-layer 130 mJ, exhibits reduced 22.09 mJ. This design, which offers excellent resistance, cooling, promising applications both land water shells.

Language: Английский

---

Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines

Sensors, Journal Year: 2025, Volume and Issue: 25(2), P. 431 - 431

Published: Jan. 13, 2025

Assessing vines’ vigour is essential for vineyard management and automatization of viticulture machines, including shaking adjustments berry harvesters during grape harvest or leaf pruning applications. To address these problems, based on a standardized growth class assessment, labeled ground truth data precisely located grapevines were predicted with specifically selected Machine Learning (ML) classifiers (Random Forest Classifier (RFC), Support Vector Machines (SVM)), utilizing multispectral UAV (Unmanned Aerial Vehicle) sensor data. The input features ML model training comprise spectral, structural, texture feature types generated from orthomosaics (spectral features), Digital Terrain Surface Models (DTM/DSM- structural Gray-Level Co-occurrence Matrix (GLCM) calculations (texture features). specific extensive literature research, especially the fields precision agri- viticulture. integrate only vine canopy-exclusive into classifications, different extracted spatially aggregated (zonal statistics), combined pixel- object-based image-segmentation-technique-created row mask around each single grapevine position. canopy progressively grouped seven groups training. Model overall performance metrics optimized grid search-based hyperparameter tuning repeated-k-fold-cross-validation. Finally, ML-based prediction results extensively discussed evaluated (accuracy, f1-weighted) specific- classification user- producer accuracy).

Language: Английский

---

Three-Dimensional Reconstruction, Phenotypic Traits Extraction, and Yield Estimation of Shiitake Mushrooms Based on Structure from Motion and Multi-View Stereo

Agriculture, Journal Year: 2025, Volume and Issue: 15(3), P. 298 - 298

Published: Jan. 30, 2025

Phenotypic traits of fungi and their automated extraction are crucial for evaluating genetic diversity, breeding new varieties, estimating yield. However, research on the high-throughput, rapid, non-destructive fungal phenotypic using 3D point clouds remains limited. In this study, a smart phone is used to capture multi-view images shiitake mushrooms (Lentinula edodes) from three different heights angles, employing YOLOv8x model segment primary image regions. The segmented were reconstructed in Structure Motion (SfM) Multi-View Stereo (MVS). To automatically individual mushroom instances, we developed CP-PointNet++ network integrated with clustering methods, achieving an overall accuracy (OA) 97.45% segmentation. computed phenotype correlated strongly manual measurements, yielding R2 > 0.8 nRMSE < 0.09 pileus transverse longitudinal diameters, = 0.53 RMSE 3.26 mm height, 0.79 0.12 stipe diameter, 0.65 4.98 height. Using these parameters, yield estimation was performed PLSR, SVR, RF, GRNN machine learning models, demonstrating superior performance (R2 0.91). This approach also adaptable extracting other fungi, providing valuable support initiatives.

Language: Английский

---

Developing an ISO11783-compliant prescription map for variable rate spraying in vineyards based on 3D canopy reconstruction

Smart Agricultural Technology, Journal Year: 2025, Volume and Issue: unknown, P. 100870 - 100870

Published: Feb. 1, 2025

Language: Английский

---