Naslov
Real time prediction of the ship position with the postgis function ST_Project

Autori
Brozović, Vladimir ; Kezić, Danko ; Bošnjak, Rino ; Vujović, igor

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
20th International Conference on Transport Science ICTS 2022 : Maritime, transport and logistics science : Conference proceedings / Zanne, Marina ; Slovenia – President Bajec, Patricija ; Slovenia – Secretary Twrdy, Elen ; Slovenia Vidan, Pero Croatia ; - Portorož : Fakulteta za pomorstvo in promet Univerza v Ljubljani, 2022, 69-74

Skup
20th International Conference on Transport Science (ICTS 2022)

Mjesto i datum
Portorož, Slovenija, 23.05.2022. - 24.05.2022

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Collision Avoidance ; Position Prediction ; PostGIS extension

Sažetak
In this article it is shown how future ship positions in a CAS (Collision Avoidance System) can be predicted in real time from the AIS data with the help of the PostGIS function ST_Project. PostGIS is an extension of the Postgres database software. Different subproblems of this predic- tion with corresponding solutions are explained. These are resampling of the real time AIS data to a fixed time grid, FIR data filtering with filter design of the corresponding filter and using the ST_Project function of PostGIS. The differences between the PostGIS function argument types geometry and geography are shown. C code examples of using PostGIS functions in a C program are presented. On the basis of the recorded real AIS data, comparisons of the predicted and the real sailed ship positions are made. These comparisons are shown for prediction intervals of 5, 10, 20 and 30 minutes in the future.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Tehnologija prometa i transport, Temeljne tehničke znanosti

POVEZANOST RADA