Detekcija otklona položaja kamere i korekcija položaja kamere za primjenu u ADAS algoritmima

Sabo, Željko

master's thesis

Detekcija otklona položaja kamere i korekcija položaja kamere za primjenu u ADAS algoritmima

Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. urn:nbn:hr:200:778656

Sabo, Željko

Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

APA 6th Edition

Sabo, Ž. (2020). Detekcija otklona položaja kamere i korekcija položaja kamere za primjenu u ADAS algoritmima (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:778656

MLA 8th Edition

Sabo, Željko. "Detekcija otklona položaja kamere i korekcija položaja kamere za primjenu u ADAS algoritmima." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:778656

Chicago 17th Edition

Harvard

Sabo, Ž. (2020). 'Detekcija otklona položaja kamere i korekcija položaja kamere za primjenu u ADAS algoritmima', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 13 January 2025, https://urn.nsk.hr/urn:nbn:hr:200:778656

Vancouver

Sabo Ž. Detekcija otklona položaja kamere i korekcija položaja kamere za primjenu u ADAS algoritmima [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2025 January 13] Available at: https://urn.nsk.hr/urn:nbn:hr:200:778656

IEEE

Ž. Sabo, "Detekcija otklona položaja kamere i korekcija položaja kamere za primjenu u ADAS algoritmima", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:200:778656

Cite this item: https://urn.nsk.hr/urn:nbn:hr:200:778656

Metadata

Title	Detekcija otklona položaja kamere i korekcija položaja kamere za primjenu u ADAS algoritmima
Title (english)	Camera position deviation detection and camera position correction for the usage in ADAS algorithms
Author	Željko Sabo
Mentor	Ratko Grbić (mentor)
Committee member	Ratko Grbić (predsjednik povjerenstva)
Committee member	Marijan Herceg (član povjerenstva)
Committee member	Mario Vranješ (član povjerenstva)
Granter	Josip Juraj Strossmayer University of Osijek Faculty of Electrical Engineering, Computer Science and Information Technology Osijek (Department of Computer Engineering and Automation) (Chair of Automation and Robotics) Osijek
Defense date and country	2020-12-11, Croatia
Scientific / art field, discipline and subdiscipline	TECHNICAL SCIENCES Computing Artificial Intelligence
Abstract	U radu je razvijeno i implementirano programsko rješenja za ADAS ALPHA razvojnu ploču na temu detekcije otklona položaja kamere i korekcije položaja kamere za primjenu u ADAS algoritmima. Prvo je izvršena implementacija programskog rješenja na osobnom računalu pomoću Python programskog jezika, te biblioteke OpenCV i NumPy. Na osnovu programskog rješenja implementiranog na osobnom računalu izvršena je implementacija na ADAS razvojnoj ploči pomoću programskog jezika C i VisionSDK programskog okruženja. Kreirano programsko rješenje implementirano na ADAS razvojnoj ploči je potom testirano, te je vršena usporedba rezultata dobivenih pomoću programskog rješenja implementiranog na osobnom računalu i programskog rješenja implementiranog na ADAS razvojnoj ploči. Kreirana rješenja su testirana na setu slika snimljenih pomoću automotiv kamere spojene na ADAS razvojnu ploču, rezolucije 1280x720 elemenata slike. Set slika korišten pri testiranju je samostalno snimljen, te se sastoji od 55 slika snimljenih kamerom otklonjenom od referentnog položaja prema naprijed, nazad, lijevo, desno, naprijed lijevo, naprijed desno, nazad lijevo i nazad desno za 1, 2 i 3 centimetra. Kamera je i rotirana u lijevu i desnu stranu za 5, 10 i 15 stupnjeva. Dobiveni rezultati prilikom testiranja su predstavljeni, te su navedeni detektirani problemi. Za detektirane probleme su predložena neka od mogućih rješenja.
Abstract (english)	The paper develops and implements software solutions for the ADAS ALPHA development board on the topic of camera position deflection detection and camera position correction for application in ADAS algorithms. First, the software solution was implemented on a personal computer using the Python programming language, and the OpenCV and NumPy libraries. Based on the software solution implemented on the personal computer, the implementation was performed on the ADAS development board using the programming language C and the VisionSDK programming environment. The software solution implemented on the ADAS development board was then tested, and the results obtained using the software solution implemented on a personal computer and the software solution implemented on the ADAS development board were compared. The created solutions were tested on a set of images taken using an automotive camera connected to an ADAS development board, with a resolution of 1280x720 image elements. The set of images used in the test was taken independently, and consists of 55 images taken by the camera removed from the reference position forward, backward, left, right, forward left, forward right, back left, and back right by 1, 2, and 3 centimeters. The camera is also rotated to the left and right by 5, 10, and 15 degrees. The results obtained during testing are presented, and the detected problems are listed. Some of the possible solutions have been suggested for the detected problems.
Keywords
Keywords (english)
Language	croatian
URN:NBN	urn:nbn:hr:200:778656
Study programme	Title: Graduate University Study Programme in Computer Engineering 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	Open access
Terms of use
Created on	2020-12-18 09:56:17

Search form