MULTIDRONE is an EC funded project of the H2020 research programme.

The recent technological advancement of computing systems allows today to find computers with extremely advanced numerical processing capabilities. In particular, the use of Graphics Processing Units (GPUs) for image and multimedia content processing and classification is experiencing a phase of intense development thanks to the deep-seated scientific research conducted in recent years (Deep Learning). Deep Learning is a branch of Machine Learning that uses complex neural networks for a variety of applications. Among these, the application area of  automatic classification of audiovisual content is certainly one of the most interesting from the strategic point of view for RAI.

Visual search technology allows users to search and match image and video contents depicting the same objects, such as buildings, paintings and logos, based on visual similarities and without the need of querying for manually generated metadata.

RAI CRIT is supporting research to extend cloud object store technologies to address emerging media industry requirements, such as scalability, efficiency and adaptability of production and archiving workflows.

The evolution and the increasingly massive use of dynamic compressors in the audio post-production area has led over the years to have in the music and advertising market a real “Loudness War”, which has reverberated with negative effects in the radio and television areas, literlally without regulations and tools to control this phenomenon in the scenario in which the evolution to digital audio/video would have allowed the transmission of products with greater sound dynamics.