Paper Info
Title
Hidden Markov models with graph densities for action recognition
Abstract
Human action recognition in video streams is a fast developing field in pattern recognition and machine learning. Local image representations, e.g. space-time interest points [1], have proven to be the current most reliable choice of feature in sequences in which the region of interest is difficult to determine [2]. However, the question how to deal with more severe occlusions has large been ignored [2]. This work proposes a new approach which directly addresses heavy occlusions by modeling the skeleton-based features using a probability density functions (PDF) defined over graphs. We integrated the proposed density into an hidden Markov model (HMM) to model sequences of graphs of arbitrary sizes, i.e. occlusions setting may change over time. The approach is evaluated using a dataset embracing three action classes, studying six different types of occlusions (involving the removal of subgraphs from the graphical representation of action sequence). The presented study shows clearly that actions from even heavily occluded sequences can be reliably recognized.
Year
DOI
Venue
2013
10.1109/IJCNN.2013.6706841
Neural Networks
Keywords
Field
DocType
gesture recognition,graph theory,hidden Markov models,image representation,learning (artificial intelligence),probability,HMM,PDF defined over graphs,action sequence,graph density,graphical representation,hidden Markov models,human action recognition,local image representations,machine learning,occluded sequences,occlusions,pattern recognition,probability density functions,region of interest,skeleton-based features,space-time interest points,video streams,Action recognition,incomplete data
Graph theory,Pattern recognition,Markov model,Computer science,Action recognition,Gesture recognition,Artificial intelligence,Graphical model,Region of interest,Hidden Markov model,Probability density function,Machine learning
Conference
ISSN
ISBN
Citations 
2161-4393
978-1-4673-6128-6
2
PageRank 
References 
Authors
0.36
10
4
Name
Order
Citations
PageRank
Michael Glodek129516.76
Edmondo Trentin228629.25
Friedhelm Schwenker3116096.59
G&#252/nther Palm41249135.67