prikaz prve stranice dokumenta Estimacija poze objekata primjenom konvolucijske neuronske mreže
No public access
master's thesis
Estimacija poze objekata primjenom konvolucijske neuronske mreže
2020. urn:nbn:hr:168:608628
Matijević, Benjamin
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Matijević, B. (2020). Estimacija poze objekata primjenom konvolucijske neuronske mreže (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:608628

Matijević, Benjamin. "Estimacija poze objekata primjenom konvolucijske neuronske mreže." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:608628

Matijević, Benjamin. "Estimacija poze objekata primjenom konvolucijske neuronske mreže." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:608628

Matijević, B. (2020). 'Estimacija poze objekata primjenom konvolucijske neuronske mreže', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 24 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:608628

Matijević B. Estimacija poze objekata primjenom konvolucijske neuronske mreže [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 November 24] Available at: https://urn.nsk.hr/urn:nbn:hr:168:608628

B. Matijević, "Estimacija poze objekata primjenom konvolucijske neuronske mreže", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:608628

Please login to the repository to save this object to your list.
Metadata
TitleEstimacija poze objekata primjenom konvolucijske neuronske mreže
Title (english)Pose estimation by using convolutional neural network
AuthorBenjamin Matijević
MentorStjepan Bogdan (mentor)
Committee memberStjepan Bogdan (predsjednik povjerenstva)
Committee memberZdenko Kovačić (član povjerenstva)
Committee memberMatko Orsag (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-16, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
U sklopu diplomskog rada, proučeno je i testirano dva modela konvolucijskih neuronskih mreža za estimaciju 6 stupnjeva slobode, Dense Fusion i PVNet. Modeli su testirani na često korištenom LineMOD setu podataka. Također, isprobana je i mogućnost korištenja sintetičkih setova podataka generiranih korištenjem alata NVIDIA Deep learning Dataset Synthesizer te su modeli učeni i evaluirani na kreiranim setovima sintetičkih podataka.
Abstract (english)
In this thesis, two 6DoF pose estimation models were examined and tested, Dense Fusion and PVNet. Models were tested on commonly used LineMOD dataset. Also, the posibilty of using synthetic dataset was tested by using NVIDIA Deep learning Dataset Synthesizer tool. Models were trained and evaluated by using created synthetic datasets.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:608628
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije (magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 13:05:03