Estudi sobre la viabilitat de diferents tecnologies per un ecosistema de drons
Visualitza/Obre
Estadístiques de LA Referencia / Recolecta
Inclou dades d'ús des de 2022
Cita com:
hdl:2117/376632
Correu electrònic de l'autorg.lloveras.ogmail.com
Tipus de documentTreball Final de Grau
Data2022-09-15
Condicions d'accésAccés obert
Llevat que s'hi indiqui el contrari, els
continguts d'aquesta obra estan subjectes a la llicència de Creative Commons
:
Reconeixement-NoComercial-SenseObraDerivada 3.0 Espanya
Abstract
This is a study on different technologies that encompass an ecosystem in formation, by "drones". The main objective has been to be able to execute a flight plan, defining which points you want to pass through, and which ones you want to take a photo to recognize objects. The entire project has been developed using Python. First, a communication system between ecosystem modules has been defined using the technology provided by the MQTT broker, a server that distributes information among clients subscribed to specific topics. To be able to show the map and mark the points where you want to fly the drone, the library "Tkinter" has been used. Finally, for object detection, different technologies have been studied, among them, the classifiers provided by OpenCV, a convolutional neural network programmed from 0 based on the Keras library, a classifier trainer made by OpenCV and a color detector .
TitulacióGRAU EN ENGINYERIA DE SISTEMES AEROESPACIALS (Pla 2015)
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
memoria.pdf | 2,013Mb | Visualitza/Obre |