Aerial Image Understanding & High Performance Scientific Computing
The High Performance Scientific Computing Group of the Computer Science Department from the Faculty for Automatic Control and Computers provides scientific researchers from academia, industry and research, significant computing resources to solve scientific and engineering problems studied by these groups. The laboratory provides information about the availability and usage of existing computing systems or software libraries, and projects in progress as well as practical advice designed to facilitate the use of these systems within the DataCenters of the UNSTPB.
We are a team of PhD students and experienced researchers with an ambition to push the frontiers of AI and take important steps towards making the technologies of tomorrow possible. We aim to design and implement efficient image processing algorithms, that could be used onboard UAVs and UGVs. Our main objectives are:
- To create fast methods for online and unsupervised learning in large spatiotemporal volumes of data, that have the capabilities of functioning in dynamic, real-world scenarios. We intend to use different kinds of imaging and 4D (3D + time) sensing capabilities, ranging from fixed sensors to cameras present on UAVs. Given the huge amounts of unlabeled data available and the costly manual annotation, unsupervised learning is crucial for the development of new AI technologies. Therefore, we will focus on efficient learning methods without human supervision.
- To develop methods capable of complete scene understanding, from the level of objects and activities involving objects to translating the visual scene into natural language.
- To give drones the capacity to “see” and understand the world in which they fly.
- Emil Slusanschi
- Marius Leordeanu
- Voichita Iancu
- Flavia Oprea
- Vlad Posea
- Alina Marcu
- Dragos Costea
- Cosmin Samoila
- Mihai Masala
- Mihai Pirvu
- Sebastian Mocanu
- Radu Daia
- Rares Folea
- Stefan Gabrian
- Dorin Ionita
- Ionut Ciobanu