Paper Info
Title
Human action recognition based on estimated weak poses.
Abstract
We present a novel method for human action recognition (HAR) based on estimated poses from image sequences. We use 3D human pose data as additional information and propose a compact human pose representation, called a weak pose, in a low-dimensional space while still keeping the most discriminative information for a given pose. With predicted poses from image features, we map the problem from image feature space to pose space, where a Bag of Poses (BOP) model is learned for the final goal of HAR. The BOP model is a modified version of the classical bag of words pipeline by building the vocabulary based on the most representative weak poses for a given action. Compared with the standard k-means clustering, our vocabulary selection criteria is proven to be more efficient and robust against the inherent challenges of action recognition. Moreover, since for action recognition the ordering of the poses is discriminative, the BOP model incorporates temporal information: in essence, groups of consecutive poses are considered together when computing the vocabulary and assignment. We tested our method on two well-known datasets: HumanEva and IXMAS, to demonstrate that weak poses aid to improve action recognition accuracies. The proposed method is scene-independent and is comparable with the state-of-art method.
Year
DOI
Venue
2012
10.1186/1687-6180-2012-162
EURASIP J. Adv. Sig. Proc.
Keywords
Field
DocType
Human action recognition, Human pose estimation, Gaussian process regression, Bag of words
Bag-of-words model,Computer science,Action recognition,Artificial intelligence,Cluster analysis,Discriminative model,Kriging,Computer vision,Feature vector,Pattern recognition,Feature (computer vision),Speech recognition,Vocabulary,Machine learning
Journal
Volume
Issue
ISSN
2012
1
1687-6180
Citations 
PageRank 
References 
9
0.45
39
Authors
3
Name
Order
Citations
PageRank
Wenjuan Gong18010.28
Jordi Gonzalez261748.02
Francesc Xavier Roca3130.87