Title :
Invariant action classification with volumetric data
Author :
Cuzzolin, Fabio ; Sarti, Augusto ; Tubaro, Stefano
Author_Institution :
Dipt. di Elettronica e Informazione, Politecnico di Milano, Milan, Italy
fDate :
29 Sept.-1 Oct. 2004
Abstract :
We propose an action recognition algorithm in which the image sequences capturing a moving human body produced by a significant number of cameras are first used to generate a volumetric representation of the body by means of volumetric intersection. Classification is then performed directly on 3D data, making the system inherently insensitive to viewpoint dependence and motion trajectory variability. Suitable features are extracted from the voxset approximating the body, and fed to a hidden Markov model to produce a finite-state description of the motion. The Kullback-Leibler distance is finally used to classify new sequences.
Keywords :
cameras; feature extraction; hidden Markov models; image classification; image representation; image sequences; 3D data; Kullback-Leibler distance; action recognition algorithm; feature extraction; finite-state description; hidden Markov model; image sequence; invariant action classification; motion trajectory variability; moving human body; volumetric data; volumetric intersection; volumetric representation; voxset approximation; Cameras; Computer vision; Data mining; Feature extraction; Hidden Markov models; Humans; Image recognition; Image reconstruction; Image sequences; Telephony;
Conference_Titel :
Multimedia Signal Processing, 2004 IEEE 6th Workshop on
Print_ISBN :
0-7803-8578-0
DOI :
10.1109/MMSP.2004.1436576