Recognizing Involuntary Actions from 3D Skeleton Data Using Body States

TL;DR

This paper introduces a novel 3D skeleton-based action recognition method using body states, Fisher LDA, Mahalonobis distance, and HMM, achieving high accuracy in recognizing involuntary actions from Kinect data.

Contribution

It proposes a new approach modeling actions as sequences of body states with improved classification using Fisher LDA and Mahalonobis distance, outperforming existing methods.

Findings

Recognition rate of 88.64% for eight actions

Up to 96.18% accuracy for fall detection

Significant performance improvement over prior methods

Abstract

Human action recognition has been one of the most active fields of research in computer vision for last years. Two dimensional action recognition methods are facing serious challenges such as occlusion and missing the third dimension of data. Development of depth sensors has made it feasible to track positions of human body joints over time. This paper proposes a novel method of action recognition which uses temporal 3D skeletal Kinect data. This method introduces the definition of body states and then every action is modeled as a sequence of these states. The learning stage uses Fisher Linear Discriminant Analysis (LDA) to construct discriminant feature space for discriminating the body states. Moreover, this paper suggests the use of the Mahalonobis distance as an appropriate distance metric for the classification of the states of involuntary actions. Hidden Markov Model (HMM) is then used to model the temporal transition between the body states in each action. According to the results, this method significantly outperforms other popular methods, with recognition rate of 88.64% for eight different actions and up to 96.18% for classifying fall actions.