2021/2022
This project aims to create a system for the automation identification of horizontal traffic signs on roads. The system's purpose is to inform or alert the users in specific situations. The project aims at creating a versatile dataset to be used in various real-life scenarios. The system is based on the application of modern artificial intelligence methods, where deep learning is used to learn from data.
2021/2022
The use of advanced modeling and simulation approaches, especially in establishing new system functionality, is an effective way to train and educate students and staff in the complex and interdisciplinary field of power systems. Due to the complexity of the system, it is very difficult to create a physical laboratory that would integrate all the elements of a complex system including the unpredictability of renewable energy sources, cognitive visualization, and real-time calculation. This project proposes algorithms for prediction of consumption, estimation of state, power flows and regulation of reactive energy and voltage in real-time using high-performance parallelized heterogeneous processors.
2021/2022
Multi-domain mobile 3D mapping and inspection toolbox for cultural heritage preservation (3DVMS) aims at developing a mobile, remote control, fleet capable of digitization, guarding, and preservation of small and large scale cultural heritage sites. The main focus is on providing a full 3D virtual reality model for the VR inspection and help in preservation of cultural heritage sites.
2020
WiDS Sarajevo @ University of Sarajevo is an independent event organized by the Faculty of Electrical Engineering (ETF) to coincide with the annual Global Women in Data Science (WiDS) Conference held at Stanford University and an estimated 150+ locations worldwide. All genders are invited to attend WiDS regional events, which features outstanding women doing outstanding work.
2017/2018
The result of the project was the development of a new mobile rover for automatic image and video segmentation. The purpose of the system was to detect high severity distresses on asphalt surfaced pavements.