Prepoznavanje i praćenje objekata kamerom pomoću strojnog vida

master's thesis

• Title (english): Recognition and tracking of objects with a camera using machine vision.
• Author: Luka Bačevina
• Mentor: Željko Šitum (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2024-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering; General Mechanical Engineering (Construction)

Abstract

Računalni vid interdisciplinarno je područje koje se bavi obradom vizualnih podataka za računalnu interpretaciju. Uz pomoć naprednih algoritama i strojnog učenja sustavi računalnog vida imaju mogućnost prepoznavati uzorke i detektirati objekte i radnje u stvarnom vremenu. Danas je u uporabi u raznim poljima, od medicinske robotike do autonomnih vozila.
U ovom radu predstavljen je postupak razvoja sustava računalnog vida za prepoznavanje stanja na semaforima za pješake u svrhu pomaganja slijepim osobama prilikom prelaska ceste. Potrebno je razviti prijenosni sustav koji će se sastojati od kamere i integriranog računalnog sustava na kojem će se obrađivati podaci sa kamere u stvarnom vremenu. Takav sustav moći će pomoći slijepim osobama da se lakše i neovisnije snalaze u urbanim sredinama

Abstract (english)

Computer vision is an interdisciplinary field which is concerned with processing visual data for use in computer interpretation. With the help of advanced algorithms and machine learning, computer vision systems have the ability to detect patterns, objects and other actions in real time. Today it is used in various fields, from medical robotics to autonomous vehicles.
This thesis will concern itself with developing a system of machine vision for detecting the state of crosswalk signals for the purpose of assisting blind persons when crossing the road. It is necessary to develop a portable system that will consist of a camera and an integrated computer on which the data from the camera will be processed in real-time. Such a system will be able to assist blind persons to navigate in urban environments more easily and independently.

• Keywords: Ključne riječi: računalni vid; detekcija objekata u stvarnom vremenu; prijenosni sustav; pomoć slijepim osobama
• Keywords (english): Key words: computer vision; real-time object detection; portable system; blind person assistance
• Language: croatian
• URN:NBN: urn:nbn:hr:235:568753
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-07-11 16:54:02