prikaz prve stranice dokumenta Algoritam za dobivanje pogleda odozgo na vozilo
  Download
PDF 2.64 MB
master's thesis
Algoritam za dobivanje pogleda odozgo na vozilo
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. urn:nbn:hr:200:865712
Marinić, Ivan
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Multimedia Systems and Digital Television

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

Cite this document

Marinić, I. (2023). Algoritam za dobivanje pogleda odozgo na vozilo (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:200:865712

Marinić, Ivan. "Algoritam za dobivanje pogleda odozgo na vozilo." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:865712

Marinić, Ivan. "Algoritam za dobivanje pogleda odozgo na vozilo." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:865712

Marinić, I. (2023). 'Algoritam za dobivanje pogleda odozgo na vozilo', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 19 May 2024, https://urn.nsk.hr/urn:nbn:hr:200:865712

Marinić I. Algoritam za dobivanje pogleda odozgo na vozilo [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 May 19] Available at: https://urn.nsk.hr/urn:nbn:hr:200:865712

I. Marinić, "Algoritam za dobivanje pogleda odozgo na vozilo", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:865712

Metadata
TitleAlgoritam za dobivanje pogleda odozgo na vozilo
Title (english)Algorithm for obtaining a top-view of a vehicle
AuthorIvan Marinić
MentorMario Vranješ (mentor)
Committee memberMario Vranješ (predsjednik povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
Committee memberMarijan Herceg (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Communications)
(Chair of Multimedia Systems and Digital Television)
Osijek
Defense date and country2023-09-11, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Telecommunications and Informatics
Abstract
Diplomski rad opisuje algoritme za dobivanje pogleda odozgo na vozilo koji se mogu koristiti u sustavu za autonomna vozila. U radu su opisane važne smjernice i koraci za uspješnu kalibraciju kamere. Algoritam za generiranje pogleda prostora oko automobila definira geometrijske operacije nad slikom kako bi se generirao cjeloviti i povezani pogled odozgo. Ove operacije uključuju ispravljanje izobličenja, transformaciju perspektive i spajanje slika. Algoritam se uspješno izvodi kada su kamere postavljene na vozilo s poznatim kalibracijskim parametrima i kada se nalaze na predviđenoj poziciji na vozilu. Važno je osigurati točnost kalibracijskih parametara i pravilno postavljanje kamera kako bi se postigao pouzdan i precizan pogled prostora oko vozila. Algoritam izrađen s YUV420SP formatom zapisa s brzinom obrade od 2.5 FPS za rezoluciju 1280 x 720 elemenata slike dobio je bolje subjektivne ocjene ispitanika od YUYV422I formata s brzinom obrade od 6.5 FPS za rezoluciju 640 x 360 elemenata slike. Daljnji napredak ovog algoritma može se postići nadogradnjom samog hardvera ploče i programske podrške kako bi se osigurala veća dostupna memorija i poboljšala ukupna izvedba sustava.
Abstract (english)
The thesis describes algorithms for obtaining a top-down view of a vehicle that can be used in an autonomous vehicle system. The work outlines important guidelines and steps for successful camera calibration. The algorithm for generating a surround view of the vehicle defines geometric operations on the image to create a comprehensive and connected top-down view. These operations include distortion correction, perspective transformation, and image stitching. The algorithm performs successfully when cameras are mounted on the vehicle with known calibration parameters and positioned as intended. Ensuring the accuracy of calibration parameters and proper camera placement is crucial to achieving a reliable and precise surround view. The algorithm implemented with the YUV420SP format, processing at 2.5 frames per second for a resolution of 1280 x 720, received better subjective ratings from the participants compared to the YUYV422I format, processing at 6.5 frames per second for a resolution of 640 x 360. Further advancement of this algorithm can be achieved by improving the hardware of the board and the software support to provide increased available memory and enhance the overall system performance.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:865712
Study programmeTitle: Graduate University Study Programme in Electrical Engineering; specializations in: Communications and Informatics, Power Engineering
Course: Communications and Informatics
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 In copyright icon
Created on2023-10-09 08:36:25