Tesis Telecomunicaciones

Permanent URI for this collectionhttp://repositorio.uta.edu.ec/handle/123456789/34848

Browse

Filters

20241

Settings

Author: search.filters.author.Ashqui Balseca, Michelle IvetteSubject: search.filters.subject.INTELIGENCIA ARTIFICIAL

Search Results

Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    Sistema de control de calidad de cultivo de fruta de temporada para etapa de precosecha empleando robótica aérea con planificación de trayectorias y visión artificial
    (Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2024-08) Ashqui Balseca, Michelle Ivette; Aucatoma Matias, Bryan Paul; Córdova Córdova, Edgar Patricio
    Currently, agriculture plays a fundamental role in the global economy. To meet the growing food demand, advanced technological tools have been integrated to optimize agricultural practices, known as Precision Agriculture (PA). These tools offer solutions that will mitigate the difficulties faced by farmers in their daily tasks. In this context, a study was carried out with the aim of implementing a quality control system for seasonal fruit crops for the pre-harvest stage using aerial robotics with trajectory planning and artificial vision. The importance of fruit quality control in Ecuador lies in its high demand both in the national and international markets. Technical standard NTE INEN 1872 establishes criteria for classifying apples according to quality grades for export and consumption. This system is based on the use of YOLOv8, a deep learning tool that evaluates the quality grade and classifies the different types of apples. The system consists of four stages: acquisition, processing, training, and visualization. In the acquisition stage, the Dji Tello drone was used to capture images or videos in real-time. The acquired data undergo preprocessing using OpenCV. A neural network was employed to train a model capable of accurately recognizing the type and quality grade of apples. For visualization, an intuitive graphical interface was designed to allow visual representation of the data derived from the trained model. The system algorithm was developed in Python due to its multiple libraries.