Programska aplikacija za detekciju kršenja mjera socijalnog distanciranja

undergraduate thesis

• Title (english): Software application for detection of violations of social distancing measures
• Author: Sandra Gubec
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2022-09-28, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Računalni vid je područje umjetne inteligencije koje nastoji omogućiti računalima prepoznavanje i razlikovanje objekata svojstveno ljudskom vidu. Zahvaljujući brojnim istraživanjima, razvoju novih algoritama te velikoj količini vizualnih informacija od strane pametnih telefona, sigurnosnih kamera i drugih uređaja, računalni vid se uz pomoć dubokog učenja i konvolucijskih neuronskih mreža u današnjici sve više primjenjuje u zadacima koji zahtijevaju prepoznavanje. Iz prethodno navedenih razloga, računalni vid je uz strojno učenje i umjetne neuronske mreže temelj programske aplikacije razvijene u ovome radu. Programska aplikacija za detekciju kršenja mjera socijalnog distanciranja izrađena je u programskom jeziku Python uz odgovarajuće biblioteke i module. Dobiveno softversko rješenje eksperimentalno je evaluirano uključujući ljudske subjekte.

Abstract (english)

Computer vision is a field od artificial intelligence that seeks to enable computers to
recognize and distinguish objects characteristic of human vision. Thanks to numerous
researches, the development of new algotithms and the large amount of visual information
from smartphones, security cameras and other devices, computer vision with the help of deep
learning and convolutional neural networks is nowadays increasingly applied in tasks that
require recognition. For the aforementioned reasons, computer vision, along with machine
learning and artificial neural networks, is the basis of the software application developed in
this paper. The software application for detecting violations of social distancing measures was
created in the Python programming language with appropriate libraries and modules. The
obtained software solution was experimentally evaluated including human subjects.

• Keywords: Socijalno distanciranje; Python; umjetna inteligencija; neuronske mreže; konvolucijske neuronske mreže; strojno učenje; računalni vid
• Keywords (english): social distancing; Python; artificial intelligence; neural networks; convolutional neural networks; machine learning; computer vision
• Language: croatian
• URN:NBN: urn:nbn:hr:235:508991
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2022-09-22 16:21:14