Author Archives: admin

Shawbak

A technology transfer project realized for the international exhibition From Petra to Shawbak: archeology of a frontier. A multi-touch tableTop was realized for this exhibition that presents the results of the latest international archeology investigations and of the research conducted by the archaeological mission of the University of Florence in these past twenty years in Jordan at the sites of Petra and Shawbak, one of the most important historical areas in the world.

Natural interface realized for the international exhibition "From Petra to Shawbak"

Natural interface realized for the international exhibition "From Petra to Shawbak"

As of 2006, the Shawbak site has been the object of an innovative international Italian-Jordanian agreement of scientific and cultural cooperation between the Department of Antiquities of Jordan and the University of Florence, which combines archaeological research, conservative restoration and valorisation.

Planning the exhibition has offered the opportunity to experiment and re-elaborate the latest practises of exhibition communication, defined in Anglo-Saxon countries and, to date, inedited in Italian archaeology exhibitions, while museological design, defining the approach to exhibition communication, and conceiving a strategy for visitor learning, are all totally innovative.

The exhibition itinerary has been conceived in three sections: 1) the discovery of an authentic capital that reinterprets the Crusader presence of the Seigniory of Transjordan, and begins a succession that crosses the dynasty of Saladin and reaches us; 2) the documentation of the diverse role performed by the frontier as a historical key of interpretation: from the ancient age (Nabataean, Roman, Byzantine), Arab-Islamic (Umayyad, Abbasid, Fatimid) up to the Crusader-Ayyubid and Mameluke ages, explored through the archaeological observatory of the region and of the sites of Petra and Shawbak; 3) the collection and “publication” of visitors’ comments.

The interface design was built on the initial definition of the Information Architecture, based on the contents that the archaelogical research unit intended to deliver during the exhibition.

It appeared immediately evident that all the contents available were related to two different dimensions: the time period and the definition level.

The time span along with the fortress was studied is roughly divided in 5 parts:

  • 2nd crusade, “The coming of the Crusaders”;
  • 3rd crusade, “Rise and fall of the Crusaders”;
  • Ayyubid, “The Ayyubid conquest”;
  • Mamluk, “The rise of Mamluks”;
  • Ottoman, “The Ottoman expansion”.

The different level of resolution, or zoom detail, through which the territory can be explored are five as well: “Transjordan” region, “Shawbak” castle, “The fortified gate”, “Masonries” elevations, and “Stones”.

Contents are made of videos, pictures and texts that show and explain the archaeological site for each of the described time span and zoom level.

Localization and Mapping with a PTZ-Camera

Localization and Mapping with a robotic PTZ sensor aims to perform camera pose estimation while maintaining update the map of a wide area. While this has previously been attempted by adapting SLAM algorithms, no explicit varying focal length estimation has been introduced before and other methods do not address the problem of being operative for a long period of time.

Localization and Mapping with a PTZ-Camera

Localization and Mapping with a PTZ-Camera

In recent years, pan-tilt-zoom cameras are becoming increasingly common, especially for use as surveillance devices in large areas. Despite its widespread usage, there are still issues yet to be resolved regarding their effective exploitation for scene understanding at a distance. A typical operating scenario is that of abnormal behavior detection which requires both simultaneous target 3D trajectories analysis and the indispensable image resolution to perform target biometric recognition.

This cannot generally be achieved with a single stationary camera mainly because of the limited field of view and poor resolution with respect to scene depth. This will be crucial for the challenging task of managing the sensor to track/detect/recognize several targets at high resolution in 3D. In fact, similarly to the human visual system, this can be obtained slewing the video sensor from target to target and zooming in and out as necessary.

This challenging problem however has been largely neglected mostly because of the absence of reliable and robust approaches for PTZ camera localization and mapping with 3D tracking of targets as well. To this end we are interested in the acquisition and maintenance of an estimate of the camera zoom and orientation, relative to some geometric 3D representation of its surroundings, as the sensor performs pan-tilt and zoom operations over time.

Thomas Matteo Alisi

Thomas Matteo Alisi worked for a long time as  project manager and researcher at the Media Integration  and Communication Center, where he received also a Ph.D. in Computer  Engineering, Multimedia and TLC. His research activities spanned from  semantic web to interactive environments, while during the same period  he tried hard not to loose the contact with the real world and helped  with server administration and project management.

Thomas Matteo Alisi

Thomas Matteo Alisi

Among other projects,  he contributed on defining the research lines and writing the grant  proposals for 3 national FIRB and 2 EU framework programmes, while  managing also part of the knowledge transfer activities. He was also  principal lecturer for several modules, all related to web programming languages, web design, information architecture and user experience design. Then he discovered that the time had come to speak of many  other things and he is now freelancing in the UK digital media industry,  but still collaborates with the University, where he  occasionally manages to write a paper and a project proposal.

Lamberto Ballan

Lamberto Ballan received the Laurea degree in computer engineering in 2006 and the PhD degree in computer science in 2011, both from the University of Florence. Currently he is a postdoctoral researcher at the Media Integration and Communication Center. He was a visiting scholar at the Signal and Image Processing department at Telecom Paristech/ENST, Paris, in 2010. His research interests lie at the intersection of Multimedia, Computer Vision and Pattern Recognition. He has published over thirty scientific articles in peer-reviewed, international journals and conference proceedings.

Lamberto Ballan

Lamberto Ballan

Andrew Bagdanov

Andrew Bagdanov received a dual Baccalaureate in Mathematics and Computer Science in 1995 and a Masters of Science in Computer Science in 1996 from the University of Nevada, Las Vegas. He received a PhD from the University of Amsterdam in 2004 and has authored more than fifty books and scientific articles in peer-reviewed, international journals and conferences.

Andrew Bagdanov

Andrew Bagdanov

His publications span a broad spectrum of computer science, including digital image processing, machine learning, image understanding, active camera control, and semantics-driven analysis of video.

Dario Comanducci

Dario Comanducci received the MS degree in computer engineering from the University of Florence, Italy, in 2004 and he is currently waiting for discussing his thesis for the PhD degree on Informatics and Telecommunications at the University of Florence. The thesis deals with the empoyment of 2D warping transformations to recover 3D information, with applications to 3D reconstruction and eye-gaze estimation tasks. His research interests are computer vision and pattern recognition, with applications in 3D reconstruction, human-computer interaction and image based rendering.

Fabrizio Dini

Fabrizio Dini was born in Florence, Italy, the 22th of September 1973. He received the laurea degree in Computer Engineering from the University of Florence in 2006, with a thesis on “Particle filter – based real – time visual tracking with adaptive parameter estimation”. He’s a PhD student currently working as researcher in the Visual Information and Media Lab at the Media Integration and Communication Center, University of Florence. His research interests are mainly focused on visual tracking and pattern recognition.

Fabrizio Dini

Fabrizio Dini

Carles Fernández Tena

Carles Fernández received his BD in Telecommunications Engineering in Universitat Politècnica de Catalunya, specializing later with a MSc in Language and Speech (2006) and another one in Computer Vision and Artificial Intelligence (2008). He received his PhD in computer science from Universitat Autònoma de Barcelona (2010).

Carles Fernández Tena

Carles Fernández Tena

During his predoctoral period, he did several stays in important research centres in Europe, such as IAKS (Karlsruhe), AVL (Oxford), and MICC (Florence). Carles currently holds a postdoctoral position at the Computer Vision Center (Barcelona), where he assists in National and European projects in the areas of video understanding and semantic video analysis, multilingual NL text generation and understanding, ontology development for video retrieval, and advanced user interfacing. He is also an associate lecturer at the Computer Science department of UAB. During his period at MICC, Carles collaborated with the group of Alberto del Bimbo and Marco Bertini on the topics of event interpretation and uncertainty management of human-based video sequences in surveillance scenarios.

Fernando Franco

Fernando Franco was born in Ronciglione, Viterbo, in 1981 and has been living in Florence since 2001. He received the laurea degree in computer engineering from the University of Florence in 2008, with a thesis on “Local shape extraction using interest point”. He’s currently working as researcher at the Visual Information and Media Lab at the Media Integration and Communication Center, University of Florence. His research interests focus on computer vision, pattern recognition and computer graphics.

Fernando Franco

Fernando Franco

Andrea Grifoni

Andrea Grifoni was born in Florence, Italy, the 27th of May 1983. He received the MS degree in computer engineering in 2007 at Universita’ degli Studi di Firenze with a thesis on “An Uncalibrated system to acquire biometric imagery at distance”. He’s been working as researcher at the Visual Information and Media Lab at MICC until April 2008 with research interests focused on Computer Vision, Pattern recognition and Visual tracking for automated video surveillance systems.

Andrea Grifoni

Andrea Grifoni

Now he is currently working as an R&D engineer of critical infrastructure protection systems at Thales where he continues to collaborate with MICC under the framework of a Joint Lab on innovative video surveillance solutions.