Št. zadetkov: 22
Magistrsko delo
Oznake:
computer vision;deep learning;convolutional neural networks;semantic segmentation;few-shot learning;evaluation protocol;computer science;computer and information science;master's thesis;
Few-shot semantic segmentation, which aims at learning new categories from only a few training examples, has progressed substantially in the last decade. The progress was in part driven by datasets derived from the existing datasets for semantic segmentation. However, these datasets have several dra ...
Leto:
2021
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Diplomsko delo
Oznake:
konvolucija;nevronske mreže;deljenje parametrov;klasifikacija;strojno učenje;računalništvo;računalništvo in informatika;računalništvo in matematika;interdisciplinarni študij;univerzitetni študij;diplomske naloge;
Konvolucijske nevronske mreže dosegajo izjemne rezultate na področju računalniškega vida. Osrednja operacija teh mrež je konvolucija z jedrom majhne in nespremenljive velikosti. V praksi je zato standardni prijem za povečavo dovzetnega polja združevanje sosednjih slikovnih točk, kar pa za mnoge prob ...
Leto:
2019
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Diplomsko delo
Oznake:
diplomske naloge;prometne nezgode;preiskovalne metode;prometna varnost;vozila;primerjalna analiza;elektronski obrazec;
Naraščajoče število prometnih nezgod, tako blažjih z le materialno škodo in lažjimi telesnimi poškodbami kot tudi hujših s hudimi telesnimi poškodbami in smrtnimi žrtvami, zahteva učinkovite preiskovalne metode, prek katerih se lahko formirajo ukrepi za izboljšanje varnosti in zmanjšanje smrtnosti v ...
Leto:
2023
Vir:
Fakulteta za strojništvo (UL FS)
Izvirni znanstveni članek
Oznake:
modeliranje višine morske gladine;globoko učenje;poplavljanje;sea level modeling;deep learning;storm surges;
This paper introduces HIDRA-D, a novel deep-learning model for basin scale dense (gridded) sea level prediction using sparse satellite altimetry and in situ tide gauge data. Accurate sea level prediction is crucial for coastal risk management, marine operations, and sustainable development. While tr ...
Leto:
2026
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Izvirni znanstveni članek
Oznake:
modeliranje višine morske gladine;globoko učenje;poplavljanje;sea level modelling;deep learning;storm surges;
We propose a new deep-learning architecture HIDRA2 for sea level and storm tide modeling, which is extremely fast to train and apply and outperforms both our previous network design HIDRA1 and two state-of-the-art numerical ocean models (a NEMO engine with sea level data assimilation and a SCHISM oc ...
Leto:
2023
Vir:
Fakulteta za računalništvo in informatiko (UL FRI)
Izvirni znanstveni članek
Oznake:
modeliranje višine morske gladine;globoko učenje;poplavljanje;sea level modeling;deep learning;storm surges;
Accurate modeling of sea level and storm surge dynamics with several days of temporal horizons is essential for effective coastal flood responses and the protection of coastal communities and economies. The classical approach to this challenge involves computationally intensive ocean models that typ ...
Leto:
2025
Vir:
Repozitorij Univerze v Ljubljani (RUL)
Raziskovalni podatki
Oznake:
modeliranje višine morske gladine;globoko učenje;poplavljanje;sea level modeling;deep learning;storm surges;
HIDRA3 is a state-of-the-art deep neural model for multi-point sea-level prediction based on past sea level observations and future tidal and geophysical forecasts. Published data contain HIDRA3 pretrained weights, predictions for all 50 ensembles, geophysical training and evaluation data and SSH ob ...
Leto:
2024
Vir:
Repozitorij Univerze v Ljubljani (RUL)
Raziskovalni podatki
Oznake:
modeliranje višine morske gladine;globoko učenje;poplavljanje;sea level modeling;deep learning;storm surges;
HIDRA3 is a state-of-the-art deep neural model for multi-point sea-level prediction based on past sea level observations and future tidal and geophysical forecasts.
Leto:
2024
Vir:
Repozitorij Univerze v Ljubljani (RUL)
Izvirni znanstveni članek
Oznake:
poplavljanje morja;globoko učenje;konvolucijske mreže;sea flooding;deep learning;convolutional networks;
Sea level predictions, typically derived from 3D hydrodynamic models, are computationally intensive and subject to uncertainties stemming from physical representation and inaccuracies in initial or boundary conditions. As a complementary alternative, data-driven machine learning models provide a com ...
Leto:
2025
Vir:
Nacionalni inštitut za biologijo (NIB)
Diplomsko delo
Oznake:
Slovenija;zavarovalstvo;lov;manager;tveganje;odškodninska odgovornost;škoda;primeri;
Zavarovanje pred odgovornostjo upravljalcev lovišč
Leto:
2003
Vir:
Fakulteta za pomorstvo in promet (UL FPP)