Reconeixement visual del moviment humà en temps real per a la interacció natural home-màquina

• Autores: Antoni Jaume i Capó
• Directores de la Tesis: Javier Varona Gómez, Francisco José Perales López
• Lectura: En la Universitat de les Illes Balears ( España ) en 2009
• Tribunal Calificador de la Tesis: Manuel González Hidalgo (presid.), Ramón Mas Sansó (secret.), José Miguel Sales Dias (voc.), Jordi González Sabaté (voc.), Jose Francisco Ramos Romero (voc.)
• UNESCO :
  • 12 Matemáticas
    • 1203 Ciencia de los ordenadores
      • 120304 Inteligencia artificial
      • 120317 Informática
  • 33 Ciencias tecnológicas
    • 3304 Tecnología de los ordenadores
• Resumen

  • In most of the existing human-computer interfaces, enactive knowledge as new natural interaction paradigm has not been fully exploited yet, Recent technological advances have created the possibility to enhance naturally and significantly the interface perception by means of visual inputs, the so-called Vision-Based Interfaces (VBI). In the present document, first, we explore the recovery of the user's body posture by means of combining robust computer vision techniques and a well known inverse kinematics algorithm in real-time. Then, we present a gesture recognition algorithm where the user's movements are obtained through the real-time vision-based motion capture system. Finally, we present how to add image constraints to inverse kinematics in order to improve the results of the real-time vision-based motion capture system.