Motion Capture System Contextualization – Application to game development
Résumé
The notion of contextualization has been introduced in an existing motion capture system driven by the segmented silhouettes of a person filmed from several points of view. The principle is to create a dependence of each module of the process (in this case, the different modules are the motion capture itself, the adaptive background modelling and the silhouette segmentation) from the results of the preceding ones. Thus, the influence of these elements, one with the other, guides locally the different computations. So, this optimization increases the reliability of the whole process while decreasing significantly its processing time, making possible, thanks to the development of the algorithm on the GPU of graphics cards, the animation in real time of a 3D character in a physics-based virtual world. But it is obvious that this concept can be applied on several aspects of a motion capture system. As a matter of fact, it is possible to contextualize the captured motion, by modelling the context in which it takes place, allowing making strong assumptions about the following sequence of movements executed by the filmed person. Thus, by recognizing the current and the next gestures of a captured person, the system can adapt its reactions and evolve with the constantly changing comprehension of the context by the player. By creating immersive environments in which it is possible to interact directly and in real time with this adaptive system, thanks to the movements of the player, several games for education, research and of course entertainment can be easily imagined and developed.