This study aimed to evaluate the capacity of infrared thermography (IRT) to be used for the in situ clinical assessment of udder health status across lactation in goats. Two epidemiological studies were designed, with 106 purebred Skopelos goats being prospectively monitored over one lactation in the first study and 132 goats of the same breed from a second farm being enrolled in the second, cross-sectional study. Goats were categorized based on the clinical status of each udder half (healthy, fibrotic, both fibrotic and asymmetric, asymmetric, swollen supra-mammary lymph nodes, and abscessed). Skin surface temperature values of teats (TSST) and udder halves (USST), as well as temperature variations between different types of abscesses, based on the stage of their development (superficial developed, superficial fully mature, drained), and the symmetrical sites of the non-affected udder halves, were evaluated. Mixed linear regression analyses indicated that fibrosis, particularly when accompanied by asymmetry, resulted in a decrease of 0.2, 0.3, and 0.3 °C (p < 0.05) and of 0.6, 0.9, and 1.4 °C (p < 0.001) in the maximum, mean, and minimum USST, respectively. Recording season significantly affected USST and TSST (p < 0.001), with both of them increasing between February and August. Additionally, TSST appeared to be an unreliable indicator of udder health status, while abscesses exhibited distinct temperature patterns based on their developmental stage. It is concluded that IRT has the potential to be used on site for the detection of temperature alterations associated with chronic udder health issues, yet future studies on a larger and more diverse population of goats with various udder health conditions is needed to confirm its extensive applicability under real-world conditions.

The most vulnerable parts of tomatoes are the tips of the sepals, which are the primary entry points for fungal spores. Their precise segmentation within hyperspectral images (HSIs) plays a pivotal role in the development of automated and non-destructive systems for assessing tomatoes’ sensitivity to fungal infections. This research addresses the critical need for encoding spectral information in hyperspectral imaging to enhance the efficiency of such automated systems. We investigate four different techniques: Principal Component Analysis (PCA), Independent Component Analysis (ICA), Probabilistic Principal Component Analysis (PPCA), and Non-Negative Matrix Factorization (NMF), to perform transfer learning for tomato sepal instance segmentation using models previously trained on RGB images. A comparative analysis of three Mask Region-based Convolutional Neural Network (Mask R-CNN) backbone models is conducted: the Faster R-CNN, Deformable ConvNet, and Feature Pyramid Network (FPN) on spectral-encoded HSIs of the Brioso tomato variety. The Mask R-CNN with FPN, integrated with the NMF technique achieved the highest level of accuracy, yielding a Mean Average Precision (mAP) of 94.05%. Furthermore, on the second dataset, which included an additional three tomato varieties: Capricia, Provine, and Sao Paolo, the same model achieved mAP score of 86.42% across all tomato varieties with only a single false positive detection. Additionally, we incorporated a custom convolutional layer initialized it with estimated NMF coefficients, and achieved a mAP score of 87.40%. This demonstrates the potential of integrating spectral information encoding with trained deep learning-based instance segmentation models to enable robust and accurate transfer learning for automated agricultural food quality assessments.

Accurate ear counting is essential for determining wheat yield, but traditional manual methods are labour-intensive and time-consuming. This study introduces an innovative approach by developing an automatic ear-counting system that leverages machine learning techniques applied to high-resolution images captured by unmanned aerial vehicles (UAVs). Drone-based images were captured during the late growth stage of wheat across 15 fields in Bosnia and Herzegovina. The images, processed to a resolution of 1024 × 1024 pixels, were manually annotated with regions of interest (ROIs) containing wheat ears. A dataset consisting of 556 high-resolution images was compiled, and advanced models including Faster R-CNN, YOLOv8, and RT-DETR were utilised for ear detection. The study found that although lower-quality images had a minor effect on detection accuracy, they did not significantly hinder the overall performance of the models. This research demonstrates the potential of digital technologies, particularly machine learning and UAVs, in transforming traditional agricultural practices. The novel application of automated ear counting via machine learning provides a scalable, efficient solution for yield prediction, enhancing sustainability and competitiveness in agriculture.

The global decline of pollinator populations is posing a threat to agricultural productivity, increasingly forcing farmers to introduce pollinators to their fields. Selecting suitable pollinator species is critical for effective crop pollination. This study presents an efficient method for early pollination assessment, utilizing unmanned aerial vehicle (UAV) footage for reliable estimation and timely reactions. Twelve oilseed rape ( Brassica napus var. oleracea ) isolation cages with three pollinator treatments were set up, including the control with no pollinators. The trial employed UAV image acquisition, generating high-resolution RGB orthomosaics. A K-means clustering algorithm was implemented to identify oilseed rape flowers, a direct indicator of pollination performance. The percentage of detected oilseed rape flower coverage within each cage was the primary metric for performance assessment. These initial results demonstrated a negative correlation of 0.92 between estimated flower coverage and expert observations, affirming the efficacy of the proposed methodology. By integrating UAVs and clustering image processing, this research contributes to precision agriculture, offering a robust approach for evaluating pollination performance. The findings underscore the potential of advanced technology to support informed decision-making in agricultural practices, addressing the urgent need for sustainable pollination management in the face of declining pollinator populations.

Multispectral optical data significantly enhances cereal crop monitoring by enabling precise tracking of growth stages, early detection of germination issues, and assessment of plant health. This study evaluates the potential of integrating UAV multispectral sensor with the handheld Plant-O-Meter device for high-precision crop monitoring. The aim was to determine the optimal UAV imaging timing that aligns with proximal sensor measurements to improve growth stage assessments. Experiments were conducted on 41 cereal genotypes, including ancient and modern varieties, under two nitrogen top-dress dosages across 130 plots. The top ten performing genotypes were analyzed to identify resilient varieties adaptable to climate change and evolving field conditions. Our results demonstrate that vegetation indices during booting and spike emergence stages consistently predict yield potential, offering a robust framework for early-stage yield estimation. Additionally, we provide a comparative analysis of UAV and handheld sensor data, highlighting their respective strengths and limitations. Three vegetation indices, GRDVI, NDVI and SAVI demonstrated a very strong average positive correlation: 0.957, 0.954 and 0.944 across the selected genotypes from different performance levels. The combined dataset supports improved fertilization strategies, optimized seeding cycles, and identification of genotypes with stable agronomic traits. This study underscores the synergistic potential of aerial and proximal sensing technologies for next-generation cereal crop management and precision agriculture.

Monitoring wheat growth, as one of the most important food grain sources for human nutrition, and forecasting yields are done through different phenological phases. Reliable estimates on yields play a crucial role in securing sufficient food supplies for the world’s growing population. Currently, farmers estimate a wheat yield during the later stages of growth and are often biased in this process. Plant breeding scientists use a more accurate approach that collects data on the number of wheat ears manually counted at various locations throughout the field. A sufficiently precise count of wheat ears is one of the most important parameters for reliable early-stage prediction of wheat yield. To support the development of an affordable and trustworthy automated wheat ear detection approach, this work introduces a novel high-quality RGB smartphone image dataset, BioS-Wheat, comprising 5,696 annotated images across four wheat varieties. Additionally, it evaluates six deep learning models for wheat ear detection. Among the F-RCNN-based models, RetinaNet, YOLOv8, and a Vision Transformer-based detector, RT-DETR, achieved the highest mean Average Precision (mAP@50) of 91%, with significantly higher computational complexity. BioS-Wheat complements Global Wheat Head Detection datasets, introducing a meaningful shift in data complexity with high sowing density and minimal row spacing, emphasizing the impact of agronomic diversity on model performance by an increased object occlusion and dense spatial arrangements. Enriched and agronomically diverse datasets support model robustness at different varieties, growth stages, and locations. This work offers a good baseline for establishing the procedure for image crowdsourcing, further dataset expansions, and model improvements.