The rapid and accurate identification of pathogenic spores is essential for the early diagnosis of diseases in modern agriculture. Gray mold disease, caused by Botrytis cinerea, is a significant threat to several crops and is traditionally controlled using fungicides or, alternatively, by UV-C radiation. Classically, the determination of conidial germination percentage, a key indicator for assessing pathogen viability, has been a manual, time-consuming, and error-prone process. This study proposes an approach based on deep learning, using one-stage detectors to automate the detection and counting of germinated and non-germinated conidia in microscopy images. We trained and assessed the performance of three models under several metrics: YOLOv8, YOLOv11, and RetinaNET. The results show that these three architectures provide an efficient and accurate solution for the recognition of gray mold conidia viability. Selecting the best model, we performed the task of detecting and counting conidia for determining the germination percentage on samples treated with different UV-C radiation dosages. The results show that these deep-learning models achieved counting accuracies that closely matched those obtained with conventional manual methods, yet they delivered results far more rapidly. Because they operate continuously without fatigue or operator bias, these models begin to open possibilities, after widening field tests and datasets, for efficient and fully automated monitoring pipelines for disease management in the agro-industry.

The World Health Organization (WHO) states that over 55% of road traffic accident fatalities involve vulnerable road users, including 3% who are cyclists. While autonomous vehicles are capable of detecting objects and individuals on roadways, the detection of cyclists and the prediction of their movements continue to pose significant challenges. This paper presents results from the comparison of YOLOv7, YOLOv8, and YOLO-NAS architectures for urban cyclist detection. The methodology ensures that the detectors were trained under the same conditions. Subsequently, they were evaluated using 111 cyclist images with metrics such as IoU, precision, and recall. The results highlight advantages and disadvantages within each architecture, suggesting a priority for either inference time or the quality of cyclist detection in future work. La OMS establece que más del 55% de las muertes en accidentes viales son de usuarios vulnerables, incluyendo un 3% de ciclistas. Aunque los vehículos autónomos pueden detectar objetos y personas en las carreteras, la detección de ciclistas y la predicción de sus movimientos siguen siendo desafíos significativos. Este artículo presenta resultados al comparar las arquitecturas YOLOv7, YOLOv8 y YOLO-NAS para detectar ciclistas urbanos. La metodología garantiza que los detectores se entrenaron bajo las mismas condiciones. Luego, se evaluaron con 111 imágenes de ciclistas utilizando métricas como IoU, precisión y recall. Los resultados destacan ventajas y desventajas en cada arquitectura, lo que sugiere priorizar el tiempo de inferencia o la calidad de la detección de ciclistas en futuros trabajos.

Background Cyclists are among the most vulnerable road users in urban traffic environments. For autonomous vehicles to interact safely and effectively with cyclists, perception systems must go beyond detection and segmentation to include an explicit understanding of cyclist orientation. However, most existing cyclist datasets lack synchronized inertial metadata describing body orientation, limiting their use in multimodal and orientation-aware perception studies. Methods This Data Note presents a multimodal visual–inertial dataset acquired using the CYCLIST+IMU framework, which synchronizes monocular RGB images captured from a vehicle-mounted camera with inertial measurements recorded by bicycle-mounted and vehicle-mounted inertial measurement units. Data were collected during multiple real-world urban acquisition sessions, resulting in 3,606 RGB images, each temporally aligned with inertial measurements, including cyclist orientation angles (yaw and roll). From these acquisitions, cyclist-centered image crops were generated and manually annotated, resulting in polygon-based semantic segmentation labels, region-of-interest detection files, and relative depth maps estimated from the RGB images. To improve angular coverage, a targeted data augmentation strategy based on horizontal image flipping was applied to underrepresented orientation ranges, resulting in the generation of 718 additional samples. The final dataset comprises 4,324 synchronized multimodal samples organized in a hierarchical directory structure that preserves one-to-one correspondence across all data modalities. Conclusions The CYCLIST+IMU dataset provides synchronized RGB image crops, inertial orientation metadata, semantic segmentation annotations, relative depth maps, and detection files for 4,324 cyclist instances captured under real urban traffic conditions. By explicitly integrating visual and inertial data with precise temporal alignment and detailed documentation, this dataset enables reproducible research on cyclist orientation estimation, semantic segmentation, and multimodal sensor fusion for intelligent transportation systems.

Background Cyclists are among the most vulnerable road users in urban traffic environments. For autonomous vehicles to interact safely and effectively with cyclists, perception systems must go beyond detection and segmentation to include an explicit understanding of cyclist orientation. However, most existing cyclist datasets lack synchronized inertial metadata describing body orientation, limiting their use in multimodal and orientation-aware perception studies. Methods This Data Note presents a multimodal visual–inertial dataset acquired using the CYCLIST+IMU framework, which synchronizes monocular RGB images captured from a vehicle-mounted camera with inertial measurements recorded by bicycle-mounted and vehicle-mounted inertial measurement units. Data were collected during multiple real-world urban acquisition sessions, resulting in 3,606 RGB images, each temporally aligned with inertial measurements, including cyclist orientation angles (yaw and roll). From these acquisitions, cyclist-centered image crops were generated and manually annotated, resulting in polygon-based semantic segmentation labels, region-of-interest detection files, and relative depth maps estimated from the RGB images. To improve angular coverage, a targeted data augmentation strategy based on horizontal image flipping was applied to underrepresented orientation ranges, resulting in the generation of 718 additional samples. The final dataset comprises 4,324 synchronized multimodal samples organized in a hierarchical directory structure that preserves one-to-one correspondence across all data modalities. Conclusions The CYCLIST+IMU dataset provides synchronized RGB image crops, inertial orientation metadata, semantic segmentation annotations, relative depth maps, and detection files for 4,324 cyclist instances captured under real urban traffic conditions. By explicitly integrating visual and inertial data with precise temporal alignment and detailed documentation, this dataset enables reproducible research on cyclist orientation estimation, semantic segmentation, and multimodal sensor fusion for intelligent transportation systems.

Estimating aboveground biomass (AGB) supports monitoring cereal crop development and agricultural management, including applications in rainfed production. This systematic review examined 39 retained peer-reviewed articles, reported following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020, to characterize unmanned aerial vehicle (UAV)-based biomass estimation in wheat, maize, barley, oat and sorghum. Rotary-wing platforms and multispectral sensors were the most frequently reported platform and sensor categories, respectively; their prevalence describes adoption rather than predictive superiority or an optimal cost–performance balance. Spectral indices, canopy structure, image texture and biophysical descriptors supplied model inputs. Within-study comparisons reported improvements from combining information in particular predictor–model configurations and evaluation settings, alongside configurations with little or no improvement. Conventional regression and machine-learning approaches coexisted, with random forest and support vector regression being the most frequently reported individual estimators. R²-type statistics and root mean square error were the most frequently reported performance measures. Reported associations and predictive performance varied with phenology, environmental setting, acquisition scale and processing choices. The synthesis supports reproducible workflows linking reference biomass measurements, UAV-derived predictors, model development, evaluation and biomass mapping. We propose common validation and reporting criteria that specify the target and units; separate model development from evaluation; and test the fields, seasons or sites relevant to the intended application. These criteria provide a basis for future methodological agreement and practical application in cereal production.