prikaz prve stranice dokumenta Model umjetne inteligencije za detekciju popunjenosti parkirnih mjesta
  Download
PDF 14.94 MB
master's thesis
Model umjetne inteligencije za detekciju popunjenosti parkirnih mjesta
Rijeka: University of Rijeka, Faculty of Engineering, 2022. urn:nbn:hr:190:799409
Severinski, Karlo
University of Rijeka
Faculty of Engineering
Department of Automation and Electronics

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Severinski, K. (2022). Model umjetne inteligencije za detekciju popunjenosti parkirnih mjesta (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:799409

Severinski, Karlo. "Model umjetne inteligencije za detekciju popunjenosti parkirnih mjesta." Master's thesis, University of Rijeka, Faculty of Engineering, 2022. https://urn.nsk.hr/urn:nbn:hr:190:799409

Severinski, Karlo. "Model umjetne inteligencije za detekciju popunjenosti parkirnih mjesta." Master's thesis, University of Rijeka, Faculty of Engineering, 2022. https://urn.nsk.hr/urn:nbn:hr:190:799409

Severinski, K. (2022). 'Model umjetne inteligencije za detekciju popunjenosti parkirnih mjesta', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 28 February 2025, https://urn.nsk.hr/urn:nbn:hr:190:799409

Severinski K. Model umjetne inteligencije za detekciju popunjenosti parkirnih mjesta [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2022 [cited 2025 February 28] Available at: https://urn.nsk.hr/urn:nbn:hr:190:799409

K. Severinski, "Model umjetne inteligencije za detekciju popunjenosti parkirnih mjesta", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:190:799409

Metadata
TitleModel umjetne inteligencije za detekciju popunjenosti parkirnih mjesta
AuthorKarlo Severinski
MentorZlatan Car (mentor)
Committee memberSaša Vlahinić (predsjednik povjerenstva)
Committee memberZlatan Car (član povjerenstva)
Committee memberIvan Volarić (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Automation and Electronics)
Rijeka
Defense date and country2022, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovom se radu opisuje postupak izrade algoritma za detekciju popunjenosti parkirnih mjesta. Zadatak je bio napraviti algoritam tako da koristi neuronske mreže, to jest detekciju objekata. Objašnjeni su neki od algoritama detekcije objekata koji su pogodni za ovu primjenu i pokazano je kako bi oni mogli utjecati na točnost i brzinu rada sustava. Odabran je YOLOv4 model i objašnjena je njegova struktura, prednost i mane u usporedbi s drugim modelima detekcije objekata. Pokazan je postupak prikupljanja podataka za treniranje modela, postupak treniranja modela i testiranja te validacije modela. Sustav detekcije popunjenosti parkirnih mjesta razvijen je pomoću programskog jezika Python. Implementirana je i vizualizacija detekcije popunjenosti. Rad algoritma je testiran i potvrđen na više parkirnih kamera.
Abstract (english)
This paper describes the procedure for creating an algorithm for detecting the occupancy of parking spaces. The task was to create an algorithm that uses neural networks, that is, object detection. Some of the object detection algorithms suitable for this application are explained and it is shown how they could affect the accuracy and speed of the system. The YOLOv4 model is selected and its structure, advantages and disadvantages compared to other object detection models are explained. The procedure for collecting data for model training, the procedure for model training and testing, and model validation is presented. The parking space occupancy detection system was developed using the Python programming language. Occupancy detection visualization has also been implemented. The working algorithm was tested and confirmed on several parking cameras.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:799409
Study programmeTitle: Graduate University Study of Electrical Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike (magistar/magistra inženjer/inženjerka elektrotehnike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2022-09-21 10:34:17