Système d’Analyse de Mouvements Humains Acrobatiques A Human Acrobatic Motion Analysis System

In the field of computer vision, the motion analysis techniques are increasingly robust and beginning to have an impact beyond laboratories. Computers are able nowadays to perform image processing in real time. Indeed, they could be used to build non-intrusive systems for gesture analysis. In particular, gesture and motion analysis is in strong demand in the athletics field. This is especially true for sports dealing with acrobatics, as acrobatics mix complex spatial rotations over multiple axes and may be combined with various postures. Thus, any sport using acrobatics requires a fine analysis. This paper presents a vision system focused on the analysis of acrobatic gestures from various sports. Instead of classical systems requiring modelizing human bodies, our system is based on the characterization of basic acrobatics movements. The system was successively tested first on trampoline sport movements, but also on other sports (gymnastics, diving, etc.). Within the system, the gestures analysis is mainly carried out by using global measurements, extracted from recorded movies or live video.