Implementacija značajke "slijedi me" na bespilotnoj letjelici

master's thesis

• Title (english): Implementation of the "Follow me" feature on an unmanned aerial vehicle
• Author: Dominik Begić
• Mentor: Marina Bagić Babac (mentor)
• Committee member: Marina Bagić Babac (predsjednik povjerenstva)
• Committee member: Tomislav Kos (član povjerenstva)
• Committee member: Nikica Hlupić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-09-20, Croatia

Abstract

Bespilotne letjelice ili dronovi u zadnjem desetljeću su jako dobili na važnosti. Pokazatelj toga je rastuća potreba za primjenom u dronova u sve više i više različitih industrija pa tako i u svakodnevnom životu običnog čovjeka. Postoje razne značajke dronova koje mogu poboljšati korisničko iskustvo. Jedna od takvih je i značajka “slijedi me”. Ovaj rad će predstaviti korake kojima se takva značajka može implementirati u bespilotnu letjelicu. Pokazat će razne tehnike kojima se svaki od tih koraka može ostvariti te na kraju, predstaviti implementaciju kojom bespilotna letjelica uspješno slijedi izabranu metu.

Abstract (english)

Unmanned aerial vehicles or drones became more and more important in the last decade. That can be seen by the number of different industries that are using them as well as how many ordinary people use them in their everyday lives. There are a lot of features that can improve user experience. One of those features is “Follow me” feature. This thesis will present steps needed for that kind of feature to be implemented in unmanned aerial vehicle. It will show different techniques which can be used for those steps and in the end present the implementation that makes unmanned aerial vehicles that does not have that feature successfully follow selected target.

• Keywords: dron; bespilotna letjelica; računalni vid; konvolucijska neuronska mreža; detekcija; klasifikacija
• Keywords (english): drone; unmanned aerial vehicle; computer vision; convolutional neuron network; detection; classification
• Language: english
• URN:NBN: urn:nbn:hr:168:956862
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 08:24:02