Multi-action recognition via stochastic modelling of optical flow and gradients

Carvajal, Johanna, Sanderson, Conrad, McCool, Christopher, & Lovell, Brian C. (2014) Multi-action recognition via stochastic modelling of optical flow and gradients. In Rahman, Ashfaqur, Deng, Jeremiah D., & Li, Jiuyoung (Eds.) Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis, ACM, Gold Coast, Australia, pp. 19-24.

View at publisher


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%.

Impact and interest:

6 citations in Scopus
Search Google Scholar™

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

ID Code: 82379
Item Type: Conference Paper
Refereed: Yes
Keywords: Human action recognition, Multi-action recognition, Segmentation, Stochastic modelling, Gaussian mixture models
DOI: 10.1145/2689746.2689748
ISBN: 9781450331593
Divisions: Current > Schools > School of Electrical Engineering & Computer Science
Current > Institutes > Institute for Future Environments
Current > QUT Faculties and Divisions > Science & Engineering Faculty
Copyright Owner: Copyright 2014 ACM New York, NY, USA
Deposited On: 11 Mar 2015 00:07
Last Modified: 11 Mar 2015 23:33

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page