prikaz prve stranice dokumenta Programsko rješenje za pomoć pri parkiranju vozila
  Download
PDF 2.68 MB
master's thesis
Programsko rješenje za pomoć pri parkiranju vozila
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. urn:nbn:hr:200:380959
Kuprešak, Marko
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

Kuprešak, M. (2020). Programsko rješenje za pomoć pri parkiranju vozila (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:200:380959

Kuprešak, Marko. "Programsko rješenje za pomoć pri parkiranju vozila." 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:200:380959

Kuprešak, Marko. "Programsko rješenje za pomoć pri parkiranju vozila." 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:200:380959

Kuprešak, M. (2020). 'Programsko rješenje za pomoć pri parkiranju vozila', 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:200:380959

Kuprešak M. Programsko rješenje za pomoć pri parkiranju vozila [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2024 May 30] Available at: https://urn.nsk.hr/urn:nbn:hr:200:380959

M. Kuprešak, "Programsko rješenje za pomoć pri parkiranju vozila", 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:200:380959

Metadata
TitleProgramsko rješenje za pomoć pri parkiranju vozila
Title (english)Software solution for vehicle park assistance
AuthorMarko Kuprešak
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 country2020-05-18, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Program Engineering
Abstract
U ovom radu razvijeno je programsko rješenje za autonomno parkiranje vozila. Algoritam obrađuje okvire dobivene s kamere postavljenje na bočnoj strani automobila, detektira i klasificira parkirna mjesta te potom parkira vozilo na prvo slobodno mjesto koje je pronašao. Kompletan kod za detekciju i klasifikaciju parkinga se sastoji od sekvence funkcija za obradu slike pomoću kojih se na posljetku dobiju informacije o lokaciji parkinga i njegovoj zauzetosti. Osim dijela za detekciju i klasifikaciju parkirnih mjesta, rješenje sadrži i dio vezan za manevriranje vozilom kako bi se ono parkiralo na detektirano slobodno mjesto. Algoritam je sposoban obrađivati deset okvira u sekundi, što omogućuje rad u stvarnom vremenu za tipične brzine kretanja po parkiralištu. Kompletan kod je napisan u Python programskom jeziku uz korištenje OpenCV biblioteke za obradu slike. Algoritam je testiran u CARLA simulatoru za tri različite brzine kretanja vozila 5km/h, 7.5km/h i 10km/h, za tri scenarija parkiranja unaprijed i dva scenarija parkiranja unatrag za lijevu i desnu stranu. Prilikom testiranja utvrđeno je da je algoritam u 100% slučajeva ispravno detektirao i klasificirao parkirna mjesta te da je ukupni postotak točnosti parkiranja nakon detekcije i klasifikacije 88.67%.
Abstract (english)
In this work, an autonomous parking assistance software solution was developed. An algorithm detects and classifies parking spaces by processing frames received from the camera placed on the side of the ego vehicle and parks itself on the first detected free parking spot. Complete code is made of sequence of image processing functions which provide information on the location of the parking spot and its occupation. In addition to image processing, the algorithm consists of a set of predefined parking maneuvers, which are used to park vehicle on a vacant parking space. The algorithm is capable of processing ten frames per second, allowing real-time operation for typical speeds around parking lot. Complete algorithm is written in Python programming language using OpenCV image processing library. The algorithm was tested in CARLA simulator for three different speeds of 5km/h, 7.5km/h and 10km/h, for three forward parking scenarios and two reverse parking scenarios for parking on the left and right side of the parking lot. While testing, it was found that the algorithm correctly detected and classified parking spaces in 100% of cases, and overall parking accuracy after parking detection and classification was 88.67%.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:380959
Study programmeTitle: UNIVERSITY STUDY AUTOMOBILE COMPUTER AND COMMUNICATION
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka automobilskog računarstva i komunikacija (magistar/magistra inženjer/inženjerka automobilskog računarstva i komunikacija)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-09-04 07:21:21