The exponential growth of global poultry production highlights the critical need for efficient flock management, particularly in accurately counting chickens to optimize operations and minimize economic losses. This study advances the application of artificial intelligence (AI) in agriculture by developing and validating an AI-driven automated poultry flock management system using the YOLOv8 object detection model. The scientific objective was to address challenges such as occlusions, lighting variability, and high-density flock conditions, thereby contributing to the broader understanding of computer vision applications in agricultural environments. The practical objective was to create a scalable and reliable system for automated monitoring and decision-making, optimizing resource utilization and improving poultry management efficiency. The prototype achieved high precision (93.1%) and recall (93.0%), demonstrating its reliability across diverse conditions. Comparative analysis with prior models, including YOLOv5, highlights YOLOv8’s superior accuracy and robustness, underscoring its potential for real-world applications. This research successfully achieves its objectives by delivering a system that enhances poultry management practices and lays a strong foundation for future innovations in agricultural automation.
Finding an appropriate image representation is a crucial problem in robotics. This problem has been classically addressed by means of computer vision techniques, where local and global features are used. The selection or/and combination of different features is carried out by taking into account repeatability and distinctiveness, but also the specific problem to solve. In this article, we propose the generation of image descriptors from general purpose semantic annotations. This approach has been evaluated as source of information for a scene classifier, and specifically using Clarifai as the semantic annotation tool. The experimentation has been carried out using the ViDRILO toolbox as benchmark, which includes a comparison of state-of-the-art global features and tools to make comparisons among them. According to the experimental results, the proposed descriptor performs similarly to well-known domain-specific image descriptors based on global features in a scene classification task. Moreover, the proposed descriptor is based on generalist annotations without any type of problem-oriented parameter tuning.
En los últimos años, técnicas de Inteligencia Artificial (IA) como el aprendizaje automático o Machine Learning (ML) y el Aprendizaje profundo o Deep Learning (DL), han impactado de forma positiva el avance de distintos campos del conocimiento entre ellos la educación. La educación es un importante motor de todas las sociedades, permite a los individuos ser más productivos y resolver problemas con mayor efectividad aplicando generalmente enfoques creativos. En la educación se ha utilizado las técnicas de ML antes mencionadas para distintas tareas entre ellas predicción de deserción y ayuda al rendimiento del estudiante. En este estudio analizaremos los trabajos más relevantes en estos campos, otorgando una perspectiva de cómo han influenciado los algoritmos de ML y DL en la educación.