Human Action Recognition Based on Depth Images from Microsoft Kinect

Human action recognition is very important in human computer interaction. In this article, we present a new method of recognizing human actions by using Microsoft Kinect sensor, k-means clustering and Hidden Markov Models (HMMs). Kinect is able to generate human skeleton information from depth images, in addition, features representing specific body parts are generated from the skeleton information and are used for recording actions. Then k-means clustering assigns the features into clusters and HMMs analyze the relationship between these clusters. By doing this, we achieved action learning and recognition. According to our experimental results, the average accuracy was 91.4 %.