Leonello Tarabella began his musical training as jazz alto-sax player. He earned his degree in Computer Science at the University of Pisa and started his work on computer music under the direction of M° Pietro Grossi.  As a researcher he coordinates the activities of the  cART Lab (computer art laboratory)  of CNUCE/C.N.R., Pisa and yearly teaches a computer music course at the Computer Science Dept. of Pisa University.  His research mainly concerns the design of languagues for algorithmic composition and original gestural man/machine interfaces for interactive computer music/graphics performaces.  As a musician he composes and performs his own computer music with the systems realized the performed in Madrid, The Netherlands, Shanghai, Thessaloniki, NewYork, La Habana and on the italian national TV networks.

photo by C.Warde-Jones

The CNUCE Institute was founded in 1965 as Computing Center for the University of Pisa; later it was attached to the National Council of Research (C.N.R.) of Italy and at the moment it has a staff of about 80 active in the laboratories of logic programming, computer network, satellite flight control, data bases, parallel computing, structural engineering, remote sensing, computer graphics and computer music. At the beginning of 2000 the CNUCE institute  moved  to the new "Area della Ricerca del C.N.R., Pisa".
The activities at the cART Lab mainly consist of Applied Research, Education, Production. The keywords characterising the activity of the Lab are man-machine interaction and real-time gesture control. Infrared beams and video captured image processing technologies have been taken into consideration in order to design and carry out original gesture interfaces for remote sensing (i.e. without mechanical and/or electrical links) moving objects handled by performers or direct gesture of the human body. Many interactive multimedia operas have been produced and presented in various important events at national and international levels.

Gesture, that is movement of the hands and head and posture of the mouth and eyes, plays a very important role in human communication: it can be seen as a parallel language for enriching the semantic content of speech or as an alternative way to communicate basic concepts and information between people of different cultures and mother tongues.
The milestones of tools and paradigms in man-computer communication have been punched-cards and character printers, keyboards and character screens and finally mouse and graphic screens. Due to the daily increase of the power of computer and electronics systems able to sense presence, distance, position, temperature (and so on...) of objects, a new field of investigation and implementation as been started in the last few years: the recognition of human gesture.
In this direction, one the most promising areas of application is computer vision this is due to two main causes: first, vision is for people the natural way of recognising the gestures of other humans; second, the required hardware is simple, economic and standard enough, i.e. ordinary video cameras and digitizer cards. Whatever the technology used, the whole problem consists of two main steps and field of research. Such as in speech recognition where the main steps are from acoustic-signal to words and from sequences-of-words to semantics, in gesture recognition the steps mainly are: - recognition of figures (hands, face) in terms of shape and position in space; - dynamics, i.e. changing of shapes in time, trajectories, detection of starting and ending points of trajectories; - semantics of gesture.
In contemporary electronic music, the synchronization between musicians and computers, and the possibility of affecting with gesture the synthesized music in order to regain human feeling and sensitivity during the live performance, is greatly taken into consideration. Besides the MIDI controllers such as keyboard, drum-pads, pitch-to-midi converters.. which issue messages for controlling digital sound machines, and devices such as the Dataglove used in Virtual Reality applications, many researchers active in the field of computer music, realized special devices and systems able to detect as much as possible information from the movements of human body .
At the cART Lab of CNUCE, Leonello Tarabella focused his attention for designing and developing original new man-machine interfaces taking into consideration sensors and technologies typically used in robotics: infra-red beams and real time analysis of video captured images. The basic idea consists of remote sensing, (i.e. without mechanical and/or electrical links) moving objects handled by performers and/or remote sensing gesture of the human body. Some original gesture recognition devices and systems are here described.
The TwinTowers device, based on the infrared technology, detects height and angular positions of the hands.
After some previuos experiences, a system for recognizing shape, position and rotation of the hands has been developed. The performer moves his/her hands in a video-camera capture area, the camera sends the signal to a video digitizer card plugged into a computer and the computer processes the mapped figures of the performerís hands and produces data concerning x-y positions, shape (posture) and the angle of rotation of both the hands. Data extracted from the image analysis every frame are used for controlling real-time interactive computer music and computer graphics performances. With this system, an number of applications have been implemented. The most important are here reported:
The Imaginary Piano where the hands of a pianist play in the air with no real keyboard;
The PAGe (Painting by Aerial Gesture) system where the hands of a performer paint in the air images projected onto a large video screen.
In order to put at work the power of the algorithmic composition and the gestural control approach for real time interactive performances, a special language called Real-Time Concurrent PascalMusic (RTCPM) [1][2] has been developed in the last years. As an evolution of the RTCPM language a new language named GALileo which includes visual programming, algorithmic composition and signal processing facilities, has been designed and is now under development.