Multi-Action Recognition via Stochastic Modelling of Optical Flow and Gradients
File version
Accepted Manuscript (AM)
Author(s)
Sanderson, Conrad
McCool, Chris
Lovell, Brian C
Griffith University Author(s)
Primary Supervisor
Other Supervisors
Editor(s)
Date
Size
File type(s)
Location
Gold Coast, QLD, Australia
License
Abstract
In this paper we propose a novel approach to multi-action recognition that performs joint segmentation and classification. This approach models each action using a Gaussian mixture using robust low-dimensional action features. Segmentation is achieved by performing classification on overlapping temporal windows, which are then merged to produce the final result. This approach is considerably less complicated than previous methods which use dynamic programming or computationally expensive hidden Markov models (HMMs). Initial experiments on a stitched version of the KTH dataset show that the proposed approach achieves an accuracy of 78.3%, outperforming a recent HMM-based approach which obtained 71.2%.
Journal Title
Conference Title
Proceedings of the MLSDA 2014: The 2nd Workshop on Machine Learning for Sensory Data Analysis
Book Title
Edition
Volume
Issue
Thesis Type
Degree Program
School
Publisher link
Patent number
Funder(s)
Grant identifier(s)
Rights Statement
Rights Statement
© ACM, 2014. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in MLSDA'14: Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, ISBN: 978-1-4503-3159-3, https://doi.org/10.1145/2689746.2689748
Item Access Status
Note
Access the data
Related item(s)
Subject
Computer vision
Machine learning not elsewhere classified
Persistent link to this record
Citation
Carvajal, J; Sanderson, C; McCool, C; Lovell, BC, Multi-Action Recognition via Stochastic Modelling of Optical Flow and Gradients, Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis - MLSDA'14, 2014