Category Archives: Institutional projects

Media Integration and Communication Centre institutional projects

SISSI: Intermodal System Integrated for Security and Signaling on Rail

The SISSI project is a three-year project focusing on the design and development of a multi-sensor portal for train safety. MICC participates in this project. SISSI is funded by the Region of Tuscany and MICC contributes its expertise in video and image analysis to the project in order to analyze passing cargo trains and measure and detect critical situations.

This project involves the exploitation of high speed sensors (up to 18000Hz), both linear and matrix, in the visible spectrum and thermal spectrum in order to measure critical factors in passing cargo trains. The matrix sensor (640×480 pixels @ 300Hz) works in the visible spectrum and is used to detect the train pantograph in order to avoid false-alarm in the shape analysis system.

Pantograph detection samples

Pantograph detection samples

Two linear cameras (4096×1 pixels @ 18500Hz) are used to observe the profile of train and stitch a complete image of the train seen laterally. These images can then be used to extract the identifier of each wagon. Finally, two thermal cameras (256×1 pixels @512Hz) are used to segment train temperature and compute maximum and average temperature over a grid of sub-regions.

SISSI: train safety from MICC on Vimeo.

Web Framework for cultural tourism in smart cities

Prototype of a web framework for the definition and modification of a personalized visit in the city of Florence accessible through different devices. In particular the system exploits a wall mounted touchscreen in a visitor center for the early definition of a city visit plan transferrable on a mobile phone. Once the route plan is transferred, the mobile application allows updates and changes of the plan as well as to access geolocalized information of each Point Of Interest during the visit in the city. An application server platform and a network infrastructure permits to record user activities as well as search and retrieve personalized data.

People Interacting with the touchscreen

People Interacting with the touchscreen

The prototype system is currently under test at the Media Integration and Communication Center of the University of Florence and is developed in a joint project between the University of Florence and the Municipality of Florence. It will be part of the newly started project Social Museum and Smart Tourism that has been funded under the Cluster program of MIUR. It is expected to be in operation by January 1st 2014.

The mobile application interface

The mobile application interface

VIVIT. Vivi l’Italiano web portal

VIVIT is a three-years project led by Media Integration and Communication Center (MICC) and Accademia della Crusca, funded on government FIRB funding. As a part of this project, the VIVIT web portal has been developed by MICC in order to give visibility to culture-related contents that may appeal to second and third generation Italians living abroad.

Vivit web portal

Vivit web portal

The main aim of the VIVIT web portal is to provide people of italian origins with quality content related to the history of the nation and that of the language, together with learning materials for self-assessment and improvement of the viewer’s language proficiency.

The development of the VIVIT web portal has officially started in 2010, when the information architecture and content organization were first discussed. The VIVIT project stated that the web portal should give users and potential teachers ways to interact with each other and to produce and reorganize contents to be shown online to language and culture learners. Given these premises, it was decided to make use of a CMS (Content Management System), the possibility of user roles definition and interaction being part of its nature.

VIVIT is being developed on Drupal. Free and open-source PHP-based software, Drupal has come a long way over recent years in features development and is now considered one of the best CMS systems together with the well-known WordPress and Joomla. A large amount of user-contributed plugins (modules, in Drupal terms) and layout themes is available, since the development process itself is relatively simple and widely documented.

At this time, the architecture of the VIVIT portal is mostly complete: users may browse content, comment on it, bookmark pages and reorganize them from inside the platform (users with the role of teachers may also share these self-created content units with other users, to create their own learning path through the contents of the web portal); audio and video resources are available as well as learning materials that allow user interaction granted by the use of a custom jQuery plugin developed internally at MICC.

It is also possible, for users with enough rights, to semantically process and annotate (that is, assign resources that describe the content) texts inside the portal by using the named entities and topic extraction servlet Homer, also developed at MICC: the tagging possibility is part of Drupal core modules, while the text analysis feature is a combination of the contributed tagging module and a custom module written specifically for the VIVIT portal. The Homer servlet is a Java application based on GATE, a toolkit for a broad range of NLP (Natural Language Processing) tasks.

LIT. Lexicon of Italian Television search engine

LIT. Lexicon of Italian Television search engine

The VIVIT web portal gives access to additional resources related to the same cultural field: in particular LIT (Lexicon of Italian Television) and LIR (Lexicon of Italian Radio). The former, LIT, is a Java search engine that uses Lucene in order to index about 160 video excerpts from Italian TV programs of about 30 minutes each, chosen from the RAI video archive. LIT also offers a backend system where it is possible to stream the video sequences, synchronize the transcriptions with the audio-video sources, annotate the materials by means of customized taxonomies and furthermore add specific metadata. The latter, LIR, is a similar system that relies on an audio archive composed of radio segments from several Italian sources. Linguists are currently using LIT and LIR for computational linguistics based research.

LIR. Lexicon of Italian Radio backend

LIR. Lexicon of Italian Radio backend