prikaz prve stranice dokumenta Detekcija objekata u oblaku točaka lidara na vozilu primjenom dubokih neuronskih mreža
No public access
master's thesis
Detekcija objekata u oblaku točaka lidara na vozilu primjenom dubokih neuronskih mreža
2020. urn:nbn:hr:168:078201
Kontić, Anton
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Kontić, A. (2020). Detekcija objekata u oblaku točaka lidara na vozilu primjenom dubokih neuronskih mreža (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:078201

Kontić, Anton. "Detekcija objekata u oblaku točaka lidara na vozilu primjenom dubokih neuronskih mreža." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:078201

Kontić, Anton. "Detekcija objekata u oblaku točaka lidara na vozilu primjenom dubokih neuronskih mreža." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2020. https://urn.nsk.hr/urn:nbn:hr:168:078201

Kontić, A. (2020). 'Detekcija objekata u oblaku točaka lidara na vozilu primjenom dubokih neuronskih mreža', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 14 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:078201

Kontić A. Detekcija objekata u oblaku točaka lidara na vozilu primjenom dubokih neuronskih mreža [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2020 [cited 2024 November 14] Available at: https://urn.nsk.hr/urn:nbn:hr:168:078201

A. Kontić, "Detekcija objekata u oblaku točaka lidara na vozilu primjenom dubokih neuronskih mreža", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:168:078201

Please login to the repository to save this object to your list.
Metadata
TitleDetekcija objekata u oblaku točaka lidara na vozilu primjenom dubokih neuronskih mreža
Title (english)Object detection in point cloud of a lidar on a vehicle using deep neural networks
AuthorAnton Kontić
MentorIvan Petrović (mentor)
Committee memberIvan Petrović (predsjednik povjerenstva)
Committee memberMarija Seder (član povjerenstva)
Committee memberIvan Marković (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2020-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
Detekcija objekata u okolini vozila dubokim mrežama ključna je komponenta autonomne vožnje. Lidar je uz klasičnu kameru najčešće korišten senzor za tu zadaću, te se uglavnom koristi tako da se više snimaka lidara agregira u jedan kadar u kojemu se detektiraju objekti. Eksperimentalno su ispitane performanse metode za detekciju objekti kada se za predviđanje koristi manji broj snimaka agregiran u jedan kadar u odnosu na broj agregiranih snimaka korištenih kod učenja metode.
Abstract (english)
Object detection in the vicinity of a vehicle by using deep networks is a key component of autonomous driving. Besides the regular camera, lidar is the most often used sensor for that task. Multiple lidar sweeps are often aggregated into a single frame for detecting objects. Performance characteristics of an object detection method trained on a larger amount of aggregated sweeps applied to the frame with a smaller amount of aggregated sweeps have been experimentally studied.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:078201
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 12:42:20