immagine top
immagine testata
immagine finetestata
immagine iniziotestata2 immagine finetestata2
immagine shadow_1
immagine finetestata3


 Section Research

ISIP40 Research Group Brochure PDF

ISIP40 Research Group Presentation PDF

The vIdeo and SIgnal Processing For Telecommunications (ISIP40) research team was founded in 1991 by Prof. Carlo Regazzoni starting from the expertise acquired in the Signal Processing and Telecommunications Group of Prof. Gianni Vernazza.
Leader of the group is still prof. Regazzoni, full professor at the University of Genova, and he can rely on the help of assistant professor Marcenaro, 8 PhD students, 4 research grant co-operators and a number of external collaborators. Teaching activities allow involvement of the BS and MS students in the research activities of the team.
Thanks to co-operations with various industrial partners (in particular Selex ES and Sistemi Intelligenti Integrati Tecnologie - SIIT) as well as other university groups, two joint laboratories have been created: Ambient Awareness Laboratory (A2Lab) and Cognitive Radio Laboratory, whose research activities are focused on Cognitive and Video Surveillance; Software Defined Radio and Cognitive Radio, and Emerging Wearable Technologies.
The research group has a number of active projects with national and international industries and academic partners.

Ambient Intelligence

Ambient Intelligence area is oriented to provide increased personalized services to the user.
This task is obtained by developing systems composed by heterogeneous sensors able to extract high-level features.
Subsequently analysis, decision and personalized communications are the main steps in order to satisfy the users query depending to the context.

Cognitive and Video Surveillance research area is involved in developing automated systems able to recognize events of interests, such as occurrences of panic in the monitored areas.
Following this, we are focusing on designing bio-inspired techniques in order to provide the system with the capabilities of learning from the experience of interactions with the external world PDF.
Cognitive crowd monitoring has emerged as one of the most important fields among the video surveillance applications PDF PDF. A successful cognitive crowd monitoring system has to be embedded with the capability to extract the relevant information directly from the environmental observations. ISIP40 researchers have thus developed a proprietary simulator for crowd monitoring and analysis PDF. One of the prospective applications under particular attention is the crowd emotion detection PDF PDF.
An Automatic focusing attention algorithm represents an essential tool in order to support an operator during his monitoring activity of an overcrowding area PDF. One of the key challenges lies in modelling the representation of such relevant information for detecting specific events. To address this, we have recently proposed an appropriate automatic learning algorithm based on the information theory approach PDF.
Certainly, lower-level filtering and tracking algorithms are key facilitators for developing the high-level cognitive applications. Significant research focuses are thus also being placed on developing novel object tracking methods PDF, and joint human tracking and human-to-human interaction recognition systems PDF.

Cognitive surveillance

Cognitive Radio

Software Defined Radios and Cognitive Radios have over the past decade emerged as the most exciting technological paradigms in the telecommunications domain.
One of the "killer applications" associated with Cognitive Radios is the Dynamic Spectrum Access (DSA), which is expected to bring about better RF spectrum utilization. The recent research focuses of our group have been placed on the compressive spectrum sensing techniques PDF PDF PDF, as well as the energy detection spectrum sensing in cooperative relay networks PDF PDF PDF, as the principal enablers for the DSA for wideband Cognitive Radios.
Another research focus is placed on addressing security issuesPDF stemming out from the on-the-fly reconfigurability and cognitive capablities characteristic to Cognitive Radio technology. In particular, Game Theory PDF PDF has proven to be an appropriate mathematical tool for analyzing various Cognitive Radio security issues, such as Intelligent RF jamming PDF.
Being aware that the purely theoretical analysis of wireless problems often leads to many abstractions, and consequently to losing track of important real-life issues, a Cognitive Radio test bed PDF was assembled. The test bed PDF, put together in collaboration with Selex ES and SIIT, is used for development, testing and validation of all the relevant cognitive algorithms PDF PDF


The emergence of new wearable technologies, such as action cameras and smart glasses, has increased the interest of computer vision scientists in the First Person (Egocentric) video perspective. Nowadays, this field is attracting interest and investments of companies looking to develop commercial devices with First Person Vision recording capabilitiesPDF.
ISIP40 is currently putting efforts into developing quantitative and computational methods to exploit the information stemming from First Person Videos PDF PDF. In the process, ISIP40 researchers are using the amassed knowledge in the fields of computer vision, artificial intelligence and cognitive systems in order to embed these emerging wearable devices with cognitive functionalities.
The final objective is aimed at inferring and understanding the connections between the users' actions and gestures, and their internal emotional states, by the means of the available FPV data. Interdisciplinary study such as this one necessitates the possession of in-depth knowledge and expertise in both the mentioned engineering fields that we specialize in, and the complex domains of psychology and human emotions. In order to close the gap between the two study fields, a close research collaboration is being maintained with the Designed Intelligence Group of Eindhoven University of Technology, who are specializing precisely in the field of cognition and human emotions.

Emerging Wearable Technologies

Augmented Mixed Reality Applications

Activities in this area concern exploitation of augmented mixed reality exhibits adaptively suited to visitors’ preferences according to worldwide trend of using interactive applications based on innovative interfaces and image processing algorithms. These applications may provide new form of entertainement to people visiting cultural sites involving them in amusing activities while playing, learning and phisycally interacting.




New accepted papers:

M. Ravanbakhsh, M. Nabi, E. Sangineto, L. Marcenaro, C.S. Regazzoni, and N. Sebe, "Abnormal Event Detection in Videos using Generative Adversarial Nets", 24th IEEE International Conference on Image Processing (ICIP). 17-20 September 2017, Beijing, China

D. Campo, M. Baydoun, L. Marcenaro, and C.S. Regazzoni, "Task-dependent saliency estimation from trajectories of agents in video sequences", 24th IEEE International Conference on Image Processing (ICIP). 17-20 September 2017, Beijing, China

M.O. Mughal, L. Marcenaro, and C.S. Regazzoni, "Energy Detection in Multi-user Relay Networks", Wireless Personal Communications (2017): 1-10

A. Mazzú, P. Morerio, L. Marcenaro, C.S. Regazzoni, "A Cognitive Control-inspired approach to Object Tracking", IEEE Transactions on Image Processing

V. Bastani, L. Marcenaro, C.S. Regazzoni, "Online Nonparametric Bayesian Activity Mining and Analysis From Surveillance Video", IEEE Transactions on Image Processing