Laboratory of Applied Artificial Intelligence and Information Fusion

Cluster

Computer science

Group's website

https://laif.uniud.it/

Description

The Laboratory of Applied Artificial Intelligence and Information Fusion aims to support research in the field of Data and Information Fusion by applying the latest techniques in Artificial Intelligence and Deep Learning.

Data/Information Fusion:

Data fusion is a process aimed at combining multiple sources of information from various sensors, which may be of the same type (homogeneous) or of different kinds (heterogeneous). This technique enhances the estimation of observed physical quantities and the surrounding environment; the data resulting from the fusion process are more accurate than those obtained from a single sensor, leading to reduced errors.

Inspired by the natural world—where this process is commonly used by animals and humans to better understand their surroundings and detect potential threats—systems involving multiple artificial sensors are rapidly evolving. This evolution is driven by the development of new, low-cost hardware with increasing computational capabilities and by ever more robust techniques.

The potential applications span a growing number of fields. To name just a few examples, one can consider the benefits of multi-sensor fusion in smart environments (using audio, video, and presence sensors), in security (expanding the observed space, monitoring sensitive areas), in aviation (flight safety), in the automotive sector (pedestrian and road detection, pre-crash systems), and in industrial process control.

Artificial Intelligence and Deep Learning:

Research in Data Fusion has gained significant momentum in recent years thanks to modern Artificial Intelligence techniques, and particularly to the advances in Deep Learning. New opportunities have emerged, for instance, in the fusion of classifiers, time series analysis, and the handling of imprecise, incomplete, or contradictory data.

These developments are opening new perspectives for Data Fusion across various sectors and application domains.

The laboratory would thus support both ongoing and upcoming research projects led by the proposer, and facilitate the work of PhD students and research fellows involved in these projects. It would also provide resources for thesis students enrolled in the “Artificial Intelligence for Multimedia” and “Creative Computing” courses.