prikaz prve stranice dokumenta Filtriranje slike po boji na realnoj razvojnoj platformi za napredne sustave za pomoć vozaču
  Download
PDF 2.57 MB
master's thesis
Filtriranje slike po boji na realnoj razvojnoj platformi za napredne sustave za pomoć vozaču
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. urn:nbn:hr:200:773766
Budak, Luka
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

Budak, L. (2021). Filtriranje slike po boji na realnoj razvojnoj platformi za napredne sustave za pomoć vozaču (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:200:773766

Budak, Luka. "Filtriranje slike po boji na realnoj razvojnoj platformi za napredne sustave za pomoć vozaču." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:773766

Budak, Luka. "Filtriranje slike po boji na realnoj razvojnoj platformi za napredne sustave za pomoć vozaču." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:773766

Budak, L. (2021). 'Filtriranje slike po boji na realnoj razvojnoj platformi za napredne sustave za pomoć vozaču', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 30 May 2024, https://urn.nsk.hr/urn:nbn:hr:200:773766

Budak L. Filtriranje slike po boji na realnoj razvojnoj platformi za napredne sustave za pomoć vozaču [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2021 [cited 2024 May 30] Available at: https://urn.nsk.hr/urn:nbn:hr:200:773766

L. Budak, "Filtriranje slike po boji na realnoj razvojnoj platformi za napredne sustave za pomoć vozaču", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:200:773766

Metadata
TitleFiltriranje slike po boji na realnoj razvojnoj platformi za napredne sustave za pomoć vozaču
Title (english)Image color filtering using real development platform for advanced driver assistance systems
AuthorLuka Budak
MentorRatko Grbić (mentor)
Committee memberRatko Grbić (predsjednik povjerenstva)
Committee memberMarijan Herceg (član povjerenstva)
Committee memberMario Vranješ (član povjerenstva)
GranterJosip 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 country2021-12-23, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Ovaj rad se bavi metodom filtriranja slike po boji u različitim prostorima boje za slike dohvaćene kamerom s pogledom od naprijed. Cilj ovog rada je bila implementacija metode filtriranja slike po boji u različitim prostorima boje na ugradbenu ADAS razvojnu platformu. Najprije je predstavljena teorijska podloga za metodu koja se koristila u ovom radu uz pregled postojećih rješenja. Metoda se temelji na obradi elemenata slike gdje se za svaki element slike provjerava njegova pripadnost podprostoru koji predstavlja određenu boju unutar zadanog prostora boja. Sljedeći korak u radu je bila izrada koncepta rješenja u Python programskom jeziku korištenjem biblioteke OpenCV na osobnom računalu. Zatim se rješenje implementiralo i optimiziralo u programskom jeziku C na osobnom računalu. Nadalje, to optimizirano rješenje se implementiralo na ADAS razvojnu platformu unutar Vision SDK razvojnog okruženja programskog jezika C. Zatim je izvršena evaluacija implementacija s obzirom na ispravnost filtriranja slike po boji na skupu slika u tri različite rezolucije za pet formata zapisa slike. Na razvojnoj platformi je također odrađena pravilna raspodjela poslova na procesore koji su dostupni na razvojnoj platformi. Rezultati brzine izvođenja pokazali su da je implementirano rješenje pogodno za uporabu u stvarnom vremenu.
Abstract (english)
This paper deals with the method of filtering an image by color in different color spaces for images captured by a front view camera. The aim of this paper was to implement the method of filtering image by color on the embedded ADAS development platform. First, the theoretical basis for the method used in this paper was presented along with an overview of existing solutions. The method is based on the processing of image pixels, where for each pixel its belonging to the subspace that represents a certain color within a given color space is checked. The next step in the paper was to develop a concept solution in the Python programming language using the OpenCV library on a personal computer. The solution was then implemented and optimized in the C programming language on a personal computer. Furthermore, this optimized solution was implemented on the ADAS development platform within the Vision SDK development environment of the C programming language. Additionally, the implementations were evaluated with regard to the correctness of color image filtering on a dataset with three different resolutions for five image formats. The proper distribution of jobs on the processors available on the development platform was performed. Execution time results showed that the implemented solution is suitable for realtime use.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:773766
Study programmeTitle: 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 resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-02-14 14:07:22