Human Activity Recognition via 3-D joint angle features and Hidden Markov models

This paper presents a novel approach of Human Activity Recognition (HAR) using the joint angles of the human body in 3-D. From each pair of activity video images acquired by a stereo camera, the body joint angles are estimated by co-registering a 3-D body model to the stereo information: our approach uses no attached sensors on the human. The estimated joint angle features from the time-sequential activity video frames are then mapped into codewords to generate a sequence of discrete symbols for a Hidden Markov Model (HMM) of each activity. With these symbols, each activity HMM is trained and used for activity recognition. The performance of our joint angle-based HAR has been compared to that of the conventional binary silhouette-based HAR, producing significantly better results in the recognition rate: especially for those activities that are not discernible with the conventional approaches.

1. INTRODUCTION

Human Activity Recognition (HAR) can be defined as recognizing various human activities utilizing external sensors such as motion, acceleration, or video sensors. In recent years, HAR from video has evoked significant interest among the researchers in the fields of proactive computing, computer vision, and image understanding [1]–[3]. A key reason for this is to utilize the outcome of such recognition in practical applications such as human computer interaction, human healthcare applications etc.