Human motion analysis and synthesis using graphical biomechanics models applied to disable swimming people

In many applications the study of human movement using a computer vision and graphics techniques is very useful. One of these applications is the three-dimensional reconstruction of the structure of the human body and its movement using sequences of images and biomechanical graphics models. We present a special study about disable people and swimming activities, high level competition in particular. This kind of study needs accuracy on the analysis and reconstruction of the person’s body, therefore the virtual human (avatar) must have similar anthropometric characteristics than the person who is doing the movement. We define a semi-automatic process to adjust the humanoid to the morphology of the person. It could be very laborious and subjective if done manually or by selection of points, but in this article we present a global human motion system capturing, modeling and matching a semiautomatic process between the real person and the modeled humanoid or synthetic avatar. Once this process is carried out we are ready to analyze and represent the movements under study. It must be defined a specific set of parameter for every kind of sport. The study is adapted to specific sport activities, in our case swimming activities with an additional complexity: water occlusion and distortion. In these cases the adjustment process must be assisted by the computer using rules and models to help the expert user in correspondence tasks. Until now it is been used in indoor spaces and controlled environments. The system requires no markers or special clothing to be worn by the swimmer, and therefore its range of application is very wide. In other cases, special clothing could help very much in segmentation process. It is also very important its portability into domestic environments using VRML 2.0 and the H-anim standard for specification of virtual humanoids. In the following sections we explain the whole system, the capture process, the segmentation process, some of our results and future work.