Human action categorization using discriminative local spatio-temporal feature weighting

Article type: Research Article

Authors: Ghodrati, Amir | Kasaei, Shohreh^{; *}

Affiliations: Department of Computer Engineering, Sharif University of Technology, Tehran, Iran

Correspondence: [*] Corresponding author: Shohreh Kasaei, Department of Computer Engineering, Sharif University of Technology, Tehran, Iran. Tel.: +98 21 6616 6646; Fax: +98 21 6601 9246; E-mail: [email protected]

Abstract: New methods based on local spatio-temporal features have exhibited significant performance in action recognition. In these methods, feature selection plays an important role to achieve a superior performance. Actions are represented by local spatio-temporal features extracted from action videos. Action representations are then classified by applying a classifier (such as k-nearest neighbor or SVM). In this paper, we have proposed two feature weighting methods to better discriminate similar actions. We have proposed a definition of feature discrimination power to be used in the feature selection process. Our proposed weighting schemes have greatly improved the final categorization accuracy on the well-known KTH and Weizmann datasets.

Keywords: Human action categorization, feature weighting, local spatio-temporal features, bag of spatio-temporal words, feature space discriminating

DOI: 10.3233/IDA-2012-0538

Journal: Intelligent Data Analysis, vol. 16, no. 4, pp. 537-550, 2012