Skoči na glavni sadržaj

Prethodno priopćenje

https://doi.org/10.17818/NM/2020/1.2

Using Pretrained AlexNet Deep Learning Neural Network for Recognition of Underwater Objects

Piotr Szymak orcid id orcid.org/0000-0002-4714-6192 ; Institute of Electrical Enginnering and Automatics Polish Naval Academy Gdynia Poland
Marek Gasiorowski ; Institute of Electrical Enginnering and Automatics Polish Naval Academy Gdynia Poland


Puni tekst: engleski pdf 745 Kb

str. 9-13

preuzimanja: 448

citiraj


Sažetak

Recently, the growing number of Autonomous Underwater Vehicles (AUVs) can be seen. These vehicles are power supplied and controlled from the sources located on their boards. To operate autonomously underwater robots have to be equipped with the different sensors and software for making decision based on the signals from these sensors. The goal of the paper is to show initial research carried out for underwater objects recognition based on video images. Based on several examples included in the literature, the object recognition algorithm proposed in the paper is based on the deep neural network. In the research, the network and training algorithms accessible in the Matlab have been used. The final software will be implemented on board of the Biomimetic Autonomous Underwater Vehicle (BAUV), driven by undulating propulsion imitating oscillating motion of fins, e.g. of a fish.

Ključne riječi

deep learning; underwater objects recognition; Matlab

Hrčak ID:

226914

URI

https://hrcak.srce.hr/226914

Datum izdavanja:

11.3.2020.

Posjeta: 1.106 *