Pregled bibliografske jedinice broj: 1126478
Binary visual features for ROV motion estimation
Binary visual features for ROV motion estimation // 2013 MTS/IEEE OCEANS - Bergen
Bergen, Norveška: Institute of Electrical and Electronics Engineers (IEEE), 2013. 13811507, 7 doi:10.1109/oceans-bergen.2013.6608116 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 1126478 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Binary visual features for ROV motion estimation
Autori
Ferreira, F. ; Veruggio, G. ; Caccia, M. ; Bruzzone, G.
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
2013 MTS/IEEE OCEANS - Bergen
/ - : Institute of Electrical and Electronics Engineers (IEEE), 2013
ISBN
978-1-4799-0001-5
Skup
2013 MTS/IEEE OCEANS - Bergen
Mjesto i datum
Bergen, Norveška, 10.06.2013. - 14.06.2013
Vrsta sudjelovanja
Poster
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
feature extraction , geophysical image processing , motion estimation , oceanographic techniques , remotely operated vehicles , robot vision , underwater vehicles
Sažetak
Binary feature descriptors are a recent and promising trend in the computer vision field. Nonetheless, they are not yet enough studied when compared to the more established floating-point features. Thus, the need of testing this kind of feature descriptors arises. In particular, in the underwater domain very few works used binary feature descriptors. Therefore, this article tries to explore this recent trend and to test the latest algorithms of this kind. The context of application is Remotely Operated Vehicle (ROV) motion estimation. Experimental data is used to validate each approach and both a qualitative and quantitative analysis is shown. The results show that BRIEF is the best approach for this kind of application.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika, Računarstvo
