Detekcija semafora zasnovana na strojnom učenju

master's thesis

• Title (english): Traffic Light Detection Based on Machine Learning
• Author: Vedran Ivanušić
• Mentor: Igor Sunday Pandžić (mentor)
• Committee member: Igor Sunday Pandžić (predsjednik povjerenstva)
• Committee member: Tomislav Pribanić (član povjerenstva)
• Committee member: Mirko Sužnjević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-02-26, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad pokazuje jedan od mogućih načina detekcije objekata pomoću strojnog učenja. Naglasak je na korištenju najnovijih metoda i alata dostupnih za područje dubokog učenja. Korištenjem ujedinjene arhitekture za lokalizaciju i klasifikaciju moguće je u jednom prolazu kroz neuronsku mrežu detektirati omeđujuće okvire i vjerojatnosti pojave objekata, što pojednostavljuje proces učenja.

Abstract (english)

This paper shows one of the possible methods of object detection using machine learning. Emphasis is on using the latest methods and tools available for
deep learning. Using unified architecture for localization and classification it is possible to detect bounding boxes and object probabilities after one pass through neural network, which simplifies the training process.

• Keywords: Računalni vid; Duboko učenje; Detekcija semafora; Neuronska mreža; Tensorflow
• Keywords (english): Computer vision; Deep learning; Traffic light detection; Neural network; Tensorflow
• Language: croatian
• URN:NBN: urn:nbn:hr:168:219725
• 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: 2023-01-13 09:09:03