prikaz prve stranice dokumenta Programska podrška za snimanje video sadržaja za verifikaciju ADAS algoritama na strani PC računala
  Download
PDF 1.07 MB
master's thesis
Programska podrška za snimanje video sadržaja za verifikaciju ADAS algoritama na strani PC računala
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. urn:nbn:hr:200:167344
Benke, Ivan
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

Benke, I. (2018). Programska podrška za snimanje video sadržaja za verifikaciju ADAS algoritama na strani PC računala (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:200:167344

Benke, Ivan. "Programska podrška za snimanje video sadržaja za verifikaciju ADAS algoritama na strani PC računala." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:167344

Benke, Ivan. "Programska podrška za snimanje video sadržaja za verifikaciju ADAS algoritama na strani PC računala." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2018. https://urn.nsk.hr/urn:nbn:hr:200:167344

Benke, I. (2018). 'Programska podrška za snimanje video sadržaja za verifikaciju ADAS algoritama na strani PC računala', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 25 December 2024, https://urn.nsk.hr/urn:nbn:hr:200:167344

Benke I. Programska podrška za snimanje video sadržaja za verifikaciju ADAS algoritama na strani PC računala [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2018 [cited 2024 December 25] Available at: https://urn.nsk.hr/urn:nbn:hr:200:167344

I. Benke, "Programska podrška za snimanje video sadržaja za verifikaciju ADAS algoritama na strani PC računala", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:200:167344

Metadata
TitleProgramska podrška za snimanje video sadržaja za verifikaciju ADAS algoritama na strani PC računala
Title (english)Software for video capture for ADAS algorithms verification on the PC side
AuthorIvan Benke
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 country2018-09-26, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Information Systems
Abstract
Tema ovog diplomskog rada izrada je vlastitog rješenja na problem prijenosa i pohrane video sadržaja na računalo za kasniju primjenu u verifikaciji i testiranju ADAS algoritama. Za snimanje video sadržaja može se koristiti najviše devet kamera. Rješenje je realizirano u obliku programske podrške koja video sadržaj s AMV Grabber hardverske ploče prenosi preko PCIe sabirnice na računalo gdje se sprema na trajnu memoriju. U radu su prikazana već postojeća rješenja na navedeni problem te su objašnjene tehnologije i standardi korišteni za realizaciju vlastitog rješenja. Također, predstavljen je način na koji se želi implementirati vlastito rješenje te je opisana stvarna implementacija rješenja. Vlastito rješenje ispravno radi, odnosno podaci se uspješno prenose s AMV Grabber hardverske ploče na računalo gdje se pohranjuju na trajnu memoriju. Iako je vlastito rješenje funkcionalno, prilikom testiranja javili su se problemi koji onemogućuju održavanje konstantne brzine zapisivanja podataka na disk u stvarnom vremenu, odnosno, nakon određenog vremenskog perioda brzina zapisivanja se smanji za otprilike tri puta. Stoga, omogućeno je zapisivanje podataka s najviše tri kamere ako se zapisuje na HDD, te s najviše šest kamera ako se zapisuje na SSD prije nego se brzina zapisivanja podataka smanji. Problem je djelomično riješen te je ponuđena pretpostavka za koju se smatra da bi mogla pomoći u potpunom rješavanju problema.
Abstract (english)
This master's thesis engages in the making of an own solution to the problem of transferring and storing video content on the computer for later use in testing and verifying ADAS algorithms. To record video content, up to nine cameras can be used. The solution is made in the form of software support which transfers video content from AMV Grabber hardware board over PCIe bus to the computer where it is stored on non-volatile memory. Already existing solutions to the problem are shown and technologies and standards used are explained in this thesis. The way the solution is to be implemented is also presented and the process of actual implementation is described. The solution works correctly, i.e. the data is successfully transferred from AMV Grabber bord to the computer where it is stored on non-volatile memory. Even though the solution is functional, during testing some issues occurred which prevent the disk from maintaining constant write speeds, i.e., after a certain amount of time the write speeds decrease by about three times. Therefore, writing data from a maximum of three cameras is supported if writing occurrs on an HDD, and if writing occurrs on an SSD, writing from a maximum of six cameras is supported before the writing speed is decreased. The issue is partially solved and an assumption is offered which is considered to be helpful in solving the issue completely.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:167344
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 on2018-10-03 11:41:35