prikaz prve stranice dokumenta Implementacija algoritma za detekciju rubova u slici na realnu ADAS platformu
  Download
PDF 2.51 MB
master's thesis
Implementacija algoritma za detekciju rubova u slici na realnu ADAS platformu
2020. urn:nbn:hr:200:109625
Ćorić, Dario
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Communications
Chair of Electronics and Microelectronics

Cite this document

Ćorić, D. (2020). Implementacija algoritma za detekciju rubova u slici na realnu ADAS platformu (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:200:109625

Ćorić, Dario. "Implementacija algoritma za detekciju rubova u slici na realnu ADAS platformu." 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:200:109625

Ćorić, Dario. "Implementacija algoritma za detekciju rubova u slici na realnu ADAS platformu." 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:200:109625

Ćorić, D. (2020). 'Implementacija algoritma za detekciju rubova u slici na realnu ADAS platformu', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 19 April 2024, https://urn.nsk.hr/urn:nbn:hr:200:109625

Ćorić D. Implementacija algoritma za detekciju rubova u slici na realnu ADAS platformu [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2024 April 19] Available at: https://urn.nsk.hr/urn:nbn:hr:200:109625

D. Ćorić, "Implementacija algoritma za detekciju rubova u slici na realnu ADAS platformu", 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:200:109625

Please login to the repository to save this object to your list.
Metadata
TitleImplementacija algoritma za detekciju rubova u slici na realnu ADAS platformu
Title (english)Implementation of edge detection algorithm in the image on a real ADAS platform
AuthorDario Ćorić
MentorMarijan Herceg (mentor)
Committee memberMarijan Herceg (predsjednik povjerenstva)
Committee memberMario Vranješ (član povjerenstva)
Committee memberRatko Grbić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Communications)
(Chair of Electronics and Microelectronics)
Osijek
Defense date and country2020-10-02, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Telecommunications and Informatics
Abstract
U ovom diplomskom radu opisana je implementacija Sobelovog, Prewitt i Laplaceovog operatora te Cannyjevog algoritma za detekciju rubova na realnu ADAS platformu. Detektori su najprije napisani u programskom jeziku C++ koristeći funkcionalnosti biblioteke OpenCV te su zatim preneseni u VisionSDK okruženje u programskom jeziku C i implementirani na ADAS ploču. Za testiranje rješenja korišteni su Berkeley i Kitti skupovi podataka. Svojstva implementiranih detektora evaulirana su kroz vrijeme izvođenja, memorijski otisak te kroz usporedbu izlaznih slika detektora sa slikama označenima temeljnom istinom u slučaju Berkeley skupa, odnosno izlaznim slikama postojećih detektora u OpenCV-u u slučaju Kitti skupa podataka. Pokazano je kako Cannyjev algoritam ima najdulje vrijeme izvođenja na ploči i računalu te najveći memorijski otisak dok Laplaceov operator ima najkraće vrijeme izvođenja. Također je pokazano da izlazne slike Cannyjevog algoritma na ADAS ploči imaju najmanje različitih elemenata u odnosu na slike označene temeljnom istinom odnosno izlazne slike detektora iz OpenCV-a.
Abstract (english)
This master's thesis describes the implementation of the Sobel, Prewitt and Laplace operators and the Canny edge detection algorithm onto a real ADAS platform. The detectors were first written in C++ using OpenCV functionalities and then transfered into the VisionSDK environment in the C programming language and implemented on the ADAS board. The Berkeley and Ktti datasets were used during testing. The performance of the solutions was evalueated through execution time, memory imprint and comparing the detectors' output images with ground truth labeled images for images from the Berkeley and the output images of existing OpenCV detectors for images from the Kitti dataset. It was shown that the Canny algorithm's execution time was the longest on both the board and computer and that it had the largest memory imprint, while the Laplace operator had the shortest execution time. It was also shown that the output images of the Canny algorithm on the ADAS board has the least total different pixels compared to ground-truth labeled images and OpenCV detector output images.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:109625
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 on2020-12-08 09:21:17