FIPUlab - rad na mnogobrojnim projektima

Naše istraživačke aktivnosti

Glavni cilj FIPU laboratorija je poticanje i razvoj istraživačkih aktivnosti u području informacijskih tehnologija. Istraživački rad u laboratoriju usmjeren je na razvoj novih i unapređenje postojećih tehnologija, algoritama i softverskih rješenja.

FIPU laboratorij aktivno sudjeluje na domaćim i međunardnim konferencijama, uključujući SISY, MIPRO i THECUC.

Objavljeni Radovi

AI Computer Vision
13. 07. 2023.

Using a Monocular Camera for 360∘ Dynamic Object Instance Segmentation in Traffic

Ovaj rad istražuje detekciju i klasifikaciju pokretnih objekata na razini piksela korištenjem samo prednje kamere u CARLA simulatoru, testirajući generalizacijske sposobnosti modela na različitim kamerama uz primjenu algoritama Mask R-CNN i YOLOv7 za segmentaciju instanci.

Goran Oreški avatarGoran Oreški
Lucija Babić avatarLucija Babić
Fakultet
22. 06. 2023.

Modeling Low-Code Databases With Executable UML

This study presents an automated framework that transforms UML class models into open-source end-user databases with a web interface, facilitating easier use and learning for less-experienced software engineers, especially students.

Alan Bubalo avatarAlan Bubalo
Nikola Tanković avatarNikola Tanković

Konferencije

AI
25. 07. 2024.

A Method for Extracting BPMN Models from Textual Descriptions Using Natural Language Processing

This research introduces an automated method for generating BPMN models from text descriptions using advanced NLP and deep learning tools, achieving up to 96% accuracy with GPT-4 in visualizing complex business processes.

Josip Tomo Licardo avatarJosip Tomo Licardo
Nikola Tanković avatarNikola Tanković
Darko Etinger avatarDarko Etinger
AI Computer Vision
21. 09. 2023.

Classification of Visual Perception EEG Signals for a 2D Platformer Game

This research focuses on classifying visual perception brain signals using an OpenBCI headset to capture the EEG signals from the participants.

Alesandro Žužić avatarAlesandro Žužić
Robert Šajina avatarRobert Šajina
Nikola Tanković avatarNikola Tanković
AI Computer Vision
22. 05. 2023.

Usporedba funkcija gubitka za semantičku segmentaciju objekata u prometu

Ovo istraživanje analizira utjecaj različitih funkcija gubitka na performanse semantičke segmentacije na 23 različita objekta prisutna u prometu.

Goran Oreški avatarGoran Oreški
Simon Aničić avatarSimon Aničić
AI Computer Vision
10. 03. 2023.

Performance comparison of novel object detection models on traffic data

This research evaluated the performance of 14 novel object detection models on a traffic dataset to reveal significant differences between the selected models. The goal was to generate recommendations for best-performing models for researchers coming into the domain.

Lucia Vareško avatarLucia Vareško
Goran Oreški avatarGoran Oreški