A group of novel approaches and a toolkit for motion capture data reusing

摘要: Now more and motion capture (MoCap) systems are used to acquire realistic highly detailed data which widely for producing animations of human-like characters in a variety applications, such as simulations, video games animation films. And recently large MoCap databases available. As kind emerging multimedia data, 3D human has its own specific form standard format. But the best our knowledge, only few approaches have been explored feature representation reusing. This paper proposes group novel posture representation, sequence segmentation, key-frame extraction content-based retrieval, all very important reusing benefit efficient production. To validate these approaches, we set up database implemented prototype toolkit. The experiments show that proposed algorithms could achieve approvable results.