ABSTRACT

Accurate retrieval of the con–guration of an articulated structure from the information provided by multiple cameras is a –eld that found numerous applications in recent years. Computer graphics technology together with motion capture systems have been extensively used by the cinematographic and video games industry to generate virtual avatars [1]. Medicine has also bene–ted from these advances in the –eld of orthopedics, locomotive pathologies assessment, and sports performance improvement [2]. In this –eld, although markerless motion capture systems have attained accurate and reliable performance in some scenarios [3], only motion capture systems aided by markers placed in landmark positions on the body can produce highly accurate results.