prikaz prve stranice dokumenta Detekcija prepreka na cesti korištenjem kamere iz automobila
  Download
PDF 3.86 MB
undergraduate thesis
Detekcija prepreka na cesti korištenjem kamere iz automobila
2020. urn:nbn:hr:200:743939
Lukačević, Filip
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Visual Computing

Cite this document

Lukačević, F. (2020). Detekcija prepreka na cesti korištenjem kamere iz automobila (Undergraduate 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:200:743939

Lukačević, Filip. "Detekcija prepreka na cesti korištenjem kamere iz automobila." Undergraduate 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:200:743939

Lukačević, Filip. "Detekcija prepreka na cesti korištenjem kamere iz automobila." Undergraduate 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:200:743939

Lukačević, F. (2020). 'Detekcija prepreka na cesti korištenjem kamere iz automobila', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 28 October 2024, https://urn.nsk.hr/urn:nbn:hr:200:743939

Lukačević F. Detekcija prepreka na cesti korištenjem kamere iz automobila [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2024 October 28] Available at: https://urn.nsk.hr/urn:nbn:hr:200:743939

F. Lukačević, "Detekcija prepreka na cesti korištenjem kamere iz automobila", Undergraduate 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:200:743939

Please login to the repository to save this object to your list.
Metadata
TitleDetekcija prepreka na cesti korištenjem kamere iz automobila
Title (english)Detection of obstacles on the road using a car camera
AuthorFilip Lukačević
MentorIrena Galić (mentor)
MentorKrešimir Romić (sumentor)
Committee memberIrena Galić (predsjednik povjerenstva)
Committee memberAlfonzo Baumgartner (član povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Visual Computing)
Osijek
Defense date and country2020-09-23, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
S obzirom na nagli rast područja razvoja programske potpore za autonomna vozila sposobnost detekcije i klasifikacije objekata u neposrednom okruženju automobila relevantnija je nego ikad. U ovom radu predstavljena je jedna od mogućih metoda koja rješava takav problem – metoda linearnih potpornih vektora. Kao prvi korak implementacije ove metode izdvojene su svojstvene značajke promatranih objekata pomoću histograma usmjerenih gradijenata. Na temelju dobivenih vektora istreniran je model za prepoznavanje automobila. Za potrebe implementacije višeklasne klasifikacije iskorišten je model za prepoznavanje pješaka iz biblioteke OpenCV, te su dobivene vrijednosti pouzdanosti detekcije uspoređene u svrhu donošenja konačne odluke. Potrebni parametri dobiveni su provođenjem iterativnih testova prilagođeni konkretnim primjerima. Konačni rezultat je uspješna detekcija i klasifikacija automobila i pješaka u većini slučajeva.
Abstract (english)
Due to the rapid growth of the software development area for autonomous vehicles, the ability to detect and classify objects in the immediate vicinity of a car is more relevant than ever. This paper presents one of the possible methods that solves such a problem - the method of linear support vectors. As the first step in the implementation of this method, the features of the observed objects were extracted using histograms of oriented gradients. Based on the obtained vectors, a car recognition model was trained. For the purposes of implementing the multi-class classification, a model for pedestrian recognition from the OpenCV library was used, and the final decision was made by comparing the obtained detection reliability values. The required parameters were obtained by conducting iterative tests adapted to specific examples. The end result is successful detection and classification of cars and pedestrians in most cases.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:743939
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-12-02 16:13:24