Applying Space State Models in Human Action Recognition: A Comparative Study

This paper presents comparative results of applying different architectures of generative classifiers (HMM, FHMM, CHMM, Multi-Stream HMM, Parallel HMM ) and discriminative classifier as Conditional Random Fields (CRFs) in human action sequence recognition. The models are fed with histogram of very i...

Full description

Saved in:
Bibliographic Details
Published inArticulated Motion and Deformable Objects Vol. 5098; pp. 53 - 62
Main Authors Mendoza, M. Ángeles, Pérez de la Blanca, Nicolás
Format Book Chapter
LanguageEnglish
Published Germany Springer Berlin / Heidelberg 2008
Springer Berlin Heidelberg
SeriesLecture Notes in Computer Science
Subjects
Action Recognition
Feature Vector
Gesture Recognition
Hide Markov Model
Hide State
Online AccessGet full text

Cover

More Information
Summary:This paper presents comparative results of applying different architectures of generative classifiers (HMM, FHMM, CHMM, Multi-Stream HMM, Parallel HMM ) and discriminative classifier as Conditional Random Fields (CRFs) in human action sequence recognition. The models are fed with histogram of very informative features such as contours evolution and optical-flow. Motion orientation discrimination has been obtained tiling the bounding box of the subject and extracting features from each tile. We run our experiments on two well-know databases, KTH´s database and Weizmann´s. The results show that both type of models reach similar score, being the generative model better when used with optical flow features and being the discriminative one better when uses with shape-context features.
ISBN:3540705163
9783540705161
ISSN:0302-9743
1611-3349
DOI:10.1007/978-3-540-70517-8_6