Robust crop-row detection from field imagery is an important perception capability for agricultural guidance and robotic systems operating under variable field conditions. However, many existing approaches rely on strong geometric assumptions, specific crop configurations, or large annotated datasets. This study proposes a transparent deterministic image-processing framework for automatic crop-row detection in RGB imagery. The method progressively extracts vegetation structures, analyses their spatial organization, reconstructs directional gaps, and derives crop-row geometry through centroid-based guidance, skeletonization, polynomial modelling, line connection, and extension. The framework does not require prior knowledge of row number, row spacing, planting geometry, camera calibration, or crop identity. Experiments were conducted using 1,373 manually annotated images covering multiple crops and field conditions. On a common 150-image held-out test set, the proposed method yielded the lowest point estimates for row-count MAE (2.3 rows), lateral MAE (8.9 pixels), and RMSE (10.4 pixels), and the highest Precision (95.3
The global population is expected to exceed ten billion by 2050 and food demand is projected to increase by up to 100
Plant breeders use unmanned aerial vehicles (UAVs) to collect multispectral (MS) imagery for field-based phenotyping; however, plotlevel analysis remains limited by the time and user intervention required to delineate plot boundaries and extract phenotyping data across large breedingtrials. This study aimed to develop and quantitatively evaluate an automated workflow that integrates planter-recorded real-time kinematic global navigation satellite system (RTK-GNSS) data with UAV MS imagery for breeding-plot delineation and phenotyping-data extraction. Plot boundaries were generated from planter RTK-GNSS points grouped using HDBSCAN, with a generalized plot-offset formulation supporting flexible rowsper-plot configurations and unique plot identification. The workflow integrated batch vegetation index (VI) calculation and zonal-statistics extraction within a graphical user interface. Automated boundaries were evaluated against expert manually delineated polygons for 1,360 two-row soybean plotsusing centroid displacement, orientation, dimensions, intersection-over-union (IoU), and VI agreement. Processing time was compared with manual andgrid-based ArcGIS Pro workflows by two users. Mean centroid displacement was 17.62 cm (RMSE 18.89 cm), orientation differences were negligible, and mean IoU was 0.778. Approximately 99.63
This study investigates the reconstruction of spatio-temporal variability in vineyards by combining data from fixed and mobile sensors: fixed sensors monitor temporal changes on a few specific plants, while mobile sensors collect spatial data at specific times. It focuses on the Leaf Area Index (LAI) as a key indicator of crop development that can be measured on almost any plant at any time. The methodology involves the simulation of LAI data from April to October, taking into account phenological, environmental and plant variability, as well as sensor errors. Data fusion methods, spatio-temporal inverse distance weighting (STIDW), spatio-temporal kriging (STK) and generalized additive models (GAM), were evaluated to reconstruct LAI dynamics from available sensor data. Although these three methods all gave satisfactory results with reconstruction error not higher than 10% , STK and GAM performed better than STIDW in reconstructing spatial structure. However, GAM showed flexibility in modelling non-linear relationships and outperformed other models in the case of a more heterogeneous plot. Different sampling scenarios showed that increasing the number of spatial maps and fixed sensors improved the reconstruction by about 5% , with spatial maps having a greater impact. The spatio-temporal variability of the vineyard can be reconstructed with a limited number of fixed sensors and monthly acquisitions with mobile sensors at the beginning of the season, for example 4 monthly acquisitions from April to July and from 3 to 8 fixed sensors per hectare depending on the complexity of the plot. This study highlights the benefits of data fusion to improve precision farming applications.
This paper analyzes the current state of precision agriculture technologies in Ukraine and the specific features of their implementation across different natural and climatic regions of the country. The study investigates the trends of digital transformation in the agricultural sector and examines the influence of natural and climatic, economic, and production-related factors on the adoption of innovative agricultural technologies by farms of different sizes and organizational forms. Particular attention is paid to the main technological components of precision agriculture, including the use of Global Navigation Satellite Systems (GNSS), Geographic Information Systems (GIS), remote sensing, unmanned aerial vehicles (UAVs), sensor-based monitoring systems, and variable-rate application technologies. Their role in collecting and analyzing spatial data, monitoring crop conditions, assessing soil heterogeneity, and optimizing the use of material and technical resources is discussed. The study demonstrates that the level of implementation of digital agricultural technologies varies considerably depending on regional natural and climatic conditions, agricultural specialization, farm size, the level of technical equipment, and the economic capacity of agricultural enterprises. It is shown that modern precision agriculture technologies are most widely adopted by large agricultural enterprises, whereas their dissemination among small and medium-sized farms remains constrained by financial, technical, and human resource limitations. The principal benefits of implementing precision agriculture technologies for Ukraine's agricultural sector are identified, including increased agricultural productivity, reduced consumption of material resources, optimization of fertilizer and plant protection product application, improved environmental sustainability, and enhanced efficiency of land resource management. The paper also outlines the major challenges limiting the widespread adoption of advanced digital technologies, such as the high cost of equipment, insufficient digital infrastructure, and the shortage of qualified specialists. Finally, promising directions for the further development of precision agriculture under the conditions of the digital transformation of Ukraine's agri-food sector are substantiated. These include the expanded application of artificial intelligence, big data analytics, the Internet of Things (IoT), and integrated geospatial information platforms to support management decision-making and improve the competitiveness of agricultural production.
