Human Action Recognition Based on Boosting

Abstract

Human action recognition is an active research field in computer vision and image processing. In this paper we propose a novel method for the task of recognition of human actions in video image sequences. First of all, a video sequence is represented as a collection of spatial-temporal words by extracting space-time interest points, which is used to characterize action. Then visual words are used to represent human actions by using Bag of Words. Final boosting algorithm is used for human actions recognition. We test our algorithm on a challenging dataset: the KTH human action dataset. The experimental results show that the average recognition accuracy is over 88 %, which validates its effectiveness.

Keywords

• Human action
• Boosting algorithm
• Space-time interest points
• Bag of Words.