prikaz prve stranice dokumenta PREPOZNAVANJE VOZILA SA DUBINSKIM SENZORIMA
Access restricted to students and staff of home institution
undergraduate thesis
PREPOZNAVANJE VOZILA SA DUBINSKIM SENZORIMA
2018. urn:nbn:hr:190:294486
Vidović, Ilija
University of Rijeka
Faculty of Engineering

Cite this document

Vidović, I. (2018). PREPOZNAVANJE VOZILA SA DUBINSKIM SENZORIMA (Undergraduate thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:294486

Vidović, Ilija. "PREPOZNAVANJE VOZILA SA DUBINSKIM SENZORIMA." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2018. https://urn.nsk.hr/urn:nbn:hr:190:294486

Vidović, Ilija. "PREPOZNAVANJE VOZILA SA DUBINSKIM SENZORIMA." Undergraduate thesis, University of Rijeka, Faculty of Engineering, 2018. https://urn.nsk.hr/urn:nbn:hr:190:294486

Vidović, I. (2018). 'PREPOZNAVANJE VOZILA SA DUBINSKIM SENZORIMA', Undergraduate thesis, University of Rijeka, Faculty of Engineering, accessed 18 December 2024, https://urn.nsk.hr/urn:nbn:hr:190:294486

Vidović I. PREPOZNAVANJE VOZILA SA DUBINSKIM SENZORIMA [Undergraduate thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2018 [cited 2024 December 18] Available at: https://urn.nsk.hr/urn:nbn:hr:190:294486

I. Vidović, "PREPOZNAVANJE VOZILA SA DUBINSKIM SENZORIMA", Undergraduate thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:190:294486

Please login to the repository to save this object to your list.
Metadata
TitlePREPOZNAVANJE VOZILA SA DUBINSKIM SENZORIMA
AuthorIlija Vidović
MentorKristijan Lenac (mentor)
Committee memberKristijan Lenac (predsjednik povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
Rijeka
Defense date and country2018-05, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Cilj ovog rada je prepoznavanje vozila sa dubinskim senzorima. Opisana su stvarna mjerenja ZED stereo kamere, njihovo dobivanje te izvlačenje, obrađivanje i manipulacija. Nadalje korišten je 3D simulator Blender za stvaranje simuliranih mjerenja baziranih na stvarnim mjerenjima. Razlog korištenju simuliranih podataka bili su kvalitativni i kvantitativni nedostatci stvarnih mjerenja. Za potrebe prepoznavanja vozila, vozila su podijeljena u različite kategorije, te je napravljen vlastiti sustav neuronske mreže u računalnoj knjižici Keras koja u pozadini koristi Tensorflow strojno učenje. Neuronska mreža namijenjena je učenju i testiranju na simuliranim i stvarnim podatcima. Uspoređeni su rezultati različitih kombinacija mjerenja.
Abstract (english)
The goal of this thesis is vehicle recognition with depth sensors. In it described is the data gathered by ZED Stereo Camera, its gathering as well as extraction, processing and manipulation. Furthermore, Blender, a 3D simulator is used for creating simulated data based on real-world data gathered. Reason for usage of simulated data was deficiency and imperfection of real-world data. For purposes of vehicle recognition, vehicles were divided into various categories, and a own neural network was made with Keras library which uses Tensorflow backend. Neural network is designed for use with training and testing on both real-world and simulated data. Results from various data compositions are compared.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:294486
Study programmeTitle: 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 conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2018-06-14 11:26:16