Title :
Recognition and re-synthesis of 3D human motion with personalized variations
Author :
Etemad, Seyed Ali ; Arya, Ali
Author_Institution :
Dept. of Syst. & Comput. Eng., Carleton Univ., Ottawa, ON, Canada
Abstract :
This paper proposes a 3D view-invariant human action recognition method based on Hidden Markov Models. The natures of the actions, as well as the characteristics of the actors and different performance styles have been successfully recognized. The results have been compared to nearest neighbor and similarity search based recognition for further evaluation. Also the research addresses the problem of re-synthesis of motion. Transformation of moods, genders, and other characteristics of the actor have successfully been carried out, and the entire action has been re-synthesized for various purposes such as animation.
Keywords :
computer animation; hidden Markov models; image motion analysis; image recognition; solid modelling; 3D human motion re-synthesis; 3D view-invariant human motion recognition; hidden Markov model; human action; nearest neighbor search; personalized animation; personalized variation; similarity search; Animation; Application software; Biological system modeling; Emotion recognition; Hidden Markov models; Humans; Interpolation; Military computing; Mood; Nearest neighbor searches; hidden Markov models; human action; recognition; style transformation; synthesis;
Conference_Titel :
Multimedia Computing and Systems, 2009. ICMCS '09. International Conference on
Conference_Location :
Ouarzazate
Print_ISBN :
978-1-4244-3756-6
Electronic_ISBN :
978-1-4244-3757-3
DOI :
10.1109/MMCS.2009.5256719
