Human action recognition based on GMM-UBM supervector using SVM with non-linear GMM KL and GUMI

Nam N. Bui; Young J. Kim

doi:10.1117/12.2197316

Translator Disclaimer

6 July 2015 Human action recognition based on GMM-UBM supervector using SVM with non-linear GMM KL and GUMI

Nam N. Bui, Young J. Kim

Author Affiliations +

Proceedings Volume 9631, Seventh International Conference on Digital Image Processing (ICDIP 2015); 96311G (2015) https://doi.org/10.1117/12.2197316
Event: Seventh International Conference on Digital Image Processing (ICDIP15), 2015, Los Angeles, United States

Abstract

In recent years, Human Action Recognition (HAR) has attracted much attention from the research community due to its challenges as well as wide applications. In this paper, we investigate GMM supervector based Universal Background Model (UBM) and Support Vector Machine (SVM) with dense trajectories and motion bound features for HAR system. A GMM supervector is obtained by adapting with UBM and cascading all the mean vector components. After that, supervectors are applied as input features to SVM classifier. Moreover, we also adopted two modified GMM KL and GUMI kernels in this research. Then we make a comparison and critical analysis of our method with previous systems. Experimental results demonstrate that the proposed approach performs more efficient than current systems.

Citation Download Citation

Nam N. Bui and Young J. Kim "Human action recognition based on GMM-UBM supervector using SVM with non-linear GMM KL and GUMI", Proc. SPIE 9631, Seventh International Conference on Digital Image Processing (ICDIP 2015), 96311G (6 July 2015); https://doi.org/10.1117/12.2197316

ACCESS THE FULL ARTICLE