Activity recognition using binary tree SVM


Autoria(s): Umakanthan, Sabanadesan; Denman, Simon; Fookes, Clinton; Sridharan, Sridha
Data(s)

2014

Resumo

This paper presents an effective classification method based on Support Vector Machines (SVM) in the context of activity recognition. Local features that capture both spatial and temporal information in activity videos have made significant progress recently. Efficient and effective features, feature representation and classification plays a crucial role in activity recognition. For classification, SVMs are popularly used because of their simplicity and efficiency; however the common multi-class SVM approaches applied suffer from limitations including having easily confused classes and been computationally inefficient. We propose using a binary tree SVM to address the shortcomings of multi-class SVMs in activity recognition. We proposed constructing a binary tree using Gaussian Mixture Models (GMM), where activities are repeatedly allocated to subnodes until every new created node contains only one activity. Then, for each internal node a separate SVM is learned to classify activities, which significantly reduces the training time and increases the speed of testing compared to popular the `one-against-the-rest' multi-class SVM classifier. Experiments carried out on the challenging and complex Hollywood dataset demonstrates comparable performance over the baseline bag-of-features method.

Formato

application/pdf

Identificador

http://eprints.qut.edu.au/92900/

Publicador

IEEE

Relação

http://eprints.qut.edu.au/92900/1/SSP14_Camera_Ready.pdf

DOI:10.1109/SSP.2014.6884622

Umakanthan, Sabanadesan, Denman, Simon, Fookes, Clinton, & Sridharan, Sridha (2014) Activity recognition using binary tree SVM. In IEEE Workshop on Statistical Signal Processing (SSP 2014), IEEE, Gold Coast, Qld, pp. 248-251.

Direitos

Copyright 2014 IEEE

Fonte

School of Electrical Engineering & Computer Science; Science & Engineering Faculty

Palavras-Chave #Gaussian processes, Image classification, Image representation, Support vector machines, Video signal processing
Tipo

Conference Paper