Naslov
Application of YOLO algorithm on student UAV

Autori
Grebo, Alen ; Konsa, Toni ; Gasparovic, Goran ; Klarin, Branko

Vrsta, podvrsta i kategorija rada
Sažeci sa skupova, sažetak, znanstveni

Izvornik
5th International Conference on Smart and Sustainable Technologies (SpliTech 2020) / Šolić, Petar ; Sandro, Nižetić ; Rodrigues, Joel J. P. C. ; López-de-Ipiña González-de-Artaza, Diego ; Perković, Toni ; Catarinucci, Luca ; Patrono, Luigi - Piscataway (NJ) : Institute of Electrical and Electronics Engineers (IEEE), 2020

ISBN
978-953-290-105-4

Skup
5th International Conference on Smart and Sustainable Technologies (SpliTech 2020)

Mjesto i datum
Online, 23.09.2020. - 26.09.2020

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
YOLO , YOLOv2 , YOLOv3 , MATLAB , Python , Object detection application , UAV

Sažetak
The main concern of this paper will be to explain the workflow of YOLO2 and YOLO3 object detection algorithms with regards to training on custom dataset for the purpose of deploying said algorithms on NVIDIA Jetson mini board that is placed inside the shell of an unmanned aerial vehicle made for a purpose of student unmanned aerial vehicle(SUAV) competition. A walk through the key concepts and intuition regarding neural nets, typical data augmentation processes, the training process and deployment, both from software and hardware point of view, will be given.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Strojarstvo, Zrakoplovstvo, raketna i svemirska tehnika, Interdisciplinarne tehničke znanosti

POVEZANOST RADA