Vizijski sustav za prebrojavanje osoba temeljen na YOLOv8 modelu za prepoznavanje objekata

master's thesis

• Title (english): A vision system for counting people based on the YOLOv8 object recognition model
• Author: Lora Lovreković
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2023-07-20, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering

Abstract

Razvitak računalnog vida, grane dubokog učenja, zadnjih je godina doveo do napretka u području prepoznavanja objekata, koje računalima omogućuje identifikaciju, klasifikaciju i lokaciju objekata na slikama i videima. Za prepoznavanje objekata u ovome je radu korišten YOLOv8 algoritam, te je implementiran i model DeepSORT za praćenje objekata. U ovome radu prepoznavanje i praćenje bit će primijenjeno na ljudske osobe, koje će u konačnici biti prebrojane na temelju svojih kretanja. Nakon što se model primijeni na nekoliko primjera, slijedi analiza rezultata i prostori za poboljšanje rada modela.

Abstract (english)

The development of computer vision, a branch of deep learning, in the last years has led to development of object detection, that enables computers to identify, classify and localize objects in photos and videos. In this paper, YOLOv8 algorithm is used to detect objects and the DeepSORT model for object tracking is implemented as well. Detection and tracking in this paper will be applied to people, who are going to be counted based on their movements. After the model has been applied to several examples, results will be analyzed and space for improvements will be presented.

• Keywords: duboko učenje; računalni vid; prepoznavanje objekata; praćenje objekata; lokalizacija; klasifikacija; YOLOv8; DeepSORT
• Keywords (english): deep learning; computer vision; object detection; object tracking; localization; classification; YOLOv8; DeepSORT
• Language: croatian
• URN:NBN: urn:nbn:hr:235:979223
• Study programme: Title: Mechanical Engineering; specializations in: Design, Process and Energy Engineering, Production Engineering, Engineering Modelling and Computer Simulation, Marine Engineering, Industrial Engineering and Management, Materials Engineering, Mechatronics and Robotics, Autonomous Systems; Course: Autonomous Systems; 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: 2023-07-14 09:13:42