Spatio-Temporal Co-Occurrence Characterizations For Human Action Classification

Main Article Content

Aznul Qalid Md Sabri
Jacques Boonaert
Erma Rahayu Mohd Faizal Abdullah
Ali Mohammed Mansoor

Abstract

The human action classification task is a widely researched topic and is still an open problem. Many state-ofthe- arts approaches involve the usage of bag-of-video-words with spatio-temporal local features to construct characterizations for human actions. In order to improve beyond this standard approach, we investigate the usage of co-occurrences between local features. We propose the usage of co-occurrences information to characterize human actions. A trade-off factor is used to define an optimal trade-off between vocabulary size and classification rate. Next, a spatio-temporal co-occurrence technique is applied to extract co-occurrence information between labeled local features. Novel characterizations for human actions are then constructed. These include a vector quantized correlogram-elements vector, a highly discriminative PCA (Principal Components Analysis) co-occurrence vector and a Haralick texture vector. Multi-channel kernel SVM (support vector machine) is utilized for classification. For evaluation, the well known KTH as well as the UCF-Sports action datasets are used. We obtained state-of-the-arts classification performance. We also demonstrated that we are able to fully utilize co-occurrence information, and improve the standard bag-of-video-words approach.

Downloads

Download data is not yet available.

Article Details

How to Cite
Md Sabri, A. Q., Boonaert, J., Mohd Faizal Abdullah, E. R., & Mansoor, A. M. (2017). Spatio-Temporal Co-Occurrence Characterizations For Human Action Classification. Malaysian Journal of Computer Science, 30(3), 154–173. https://doi.org/10.22452/mjcs.vol30no3.1
Section
Articles