prikaz prve stranice dokumenta Metoda za obnavljanje slike degradirane maglom
No public access
master's thesis
Metoda za obnavljanje slike degradirane maglom
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:725106
Grdenić, Tomislav
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Grdenić, T. (2021). Metoda za obnavljanje slike degradirane maglom (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:725106

Grdenić, Tomislav. "Metoda za obnavljanje slike degradirane maglom." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:725106

Grdenić, Tomislav. "Metoda za obnavljanje slike degradirane maglom." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:725106

Grdenić, T. (2021). 'Metoda za obnavljanje slike degradirane maglom', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 04 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:725106

Grdenić T. Metoda za obnavljanje slike degradirane maglom [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 November 04] Available at: https://urn.nsk.hr/urn:nbn:hr:168:725106

T. Grdenić, "Metoda za obnavljanje slike degradirane maglom", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:725106

Metadata
TitleMetoda za obnavljanje slike degradirane maglom
Title (english)Method for Restoration of Images Degrades by Fog
AuthorTomislav Grdenić
MentorSven Lončarić (mentor)
Committee memberSven Lončarić (predsjednik povjerenstva)
Committee memberMarko Subašić (član povjerenstva)
Committee memberZvonko Kostanjčar (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-07-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Metode obnavljanja slike igraju važnu ulogu u mnogim sustavima računalnog vida uključujući sustave za asistenciju vozačima i autonomna vozila. Slike stvarnog svijeta često su loše kvalitete, slabog kontrasta i imaju prisutnost šuma najčešće u obliku sumaglice. U okviru diplomskog rada istražene su i opisane metode za obnavljanje slike degradirane maglom temeljene na strojnom učenju. Implementirane su dvije metode za obnavljanje slike temeljene na strojnom učenju pod nazivom FFA-Net te CycleDehaze. Za usporedbu metoda odabran je RESIDE skup podataka koji se sastoji od umjetno generiranih i stvarnih slika prirodnih scena. Implementirane metode ispitane su pomoću RESIDE skupa ispitnih slika.
Abstract (english)
Image restoration methods play an important role in many computer vision systems, including driver assistance systems and autonomous vehicles. Real-world images are often of poor quality, reduced contrast, and have the presence of noise most often in the form of a haze. In this the diploma thesis, methods for the restoration of images degraded by fog based on machine learning were researched and described. Two image restoration methods called FFA-Net and CycleDehaze have been implemented. To compare the method, a RESIDE datasest was selected, the set is consisting of generated and real images of real world scenes. The implemented methods were tested using the RESIDE set of test images.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:725106
Study programmeTitle: Computing
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 conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 14:59:39