Signal Processing & Multimedia

The group has a long and extended expertise within the field of signal processing and computer vision including audio/image/video/3D data. Investigation activity has been devoted to the acquisition of 2D images, the optimization of 3D imaging sensors, the compression of 2D/3D video signals, as well as to their visualization (perceptual analysis of multimedia) and their authentication (multimedia forensics). More recently, research interests have been focused on deep learning strategies in visual data processing for segmentation, coding, augmented and virtual reality applications, forensic analysis and semantic understanding.

Current activities can be summarized by the following list:

- Image and 3D Data acquisition and processing

- Computer vision

- Multimedia compression and optimization

- Multimedia Forensics

- Perceptual evaluation of immersive media

The group combines different competences ranging from deep and machine learning to signal processing and information theory.

Web page: http://lttm.dei.unipd.it

People (in alphabetical order):

Federica Battisti: perceptual analysis, image processing, video processing

Giancarlo Calvagno: audio and image processing, data compression

Simone Milani: computer vision, data compression, deep learning, multimedia forensics

Pietro Zanuttigh: computer vision, object detection, machine learning, image and 3D data processing