Kontrola parkirnih mjesta pomoću umjetne inteligencije

master's thesis

• Title (english): Control of parking spaces using artificial intelligence
• Author: Lucija Zakarija
• Mentor: Daniel Hofman (mentor)
• Committee member: Daniel Hofman (član povjerenstva)
• Committee member: Hrvoje Mlinarić (član povjerenstva)
• Committee member: Mario Brčić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-02-14, Croatia

Abstract

Prepoznavanje objekata u videu područje je koje ima mnoge primjene u stvarnom svijetu. U ovom radu obrađena je primjena prepoznavanja slobodnih i zauzetih mjesta na parkiralištima. Korišten je YOLO model koji se temelji na konvolucijskim mrežama. Pri treniranju i testiranju modela isprobane su različite mogućnosti: različiti skupovi podataka za treniranje, razina pouzdanosti i broj epoha.

Abstract (english)

Object recognition in video is a field that has many real-world applications. This paper deals with the application of recognition of free and occupied spaces in parking lots. The YOLO model based on convolutional networks was used. When training and testing the model, different possibilities were tried: different training data sets, confidence level and number of epochs.

• Keywords: Umjetna inteligencija; yolo; konvolucijske neuronske mreže; kontrola parkirnih mjesta
• Keywords (english): Artificial intelligence; yolo; convolutional neural networks; control of parking spaces
• Language: croatian
• URN:NBN: urn:nbn:hr:168:657752
• 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: 2024-03-28 07:57:28