Automatic Human Action Recognition from Video Using Hidden Markov Model

Posture classification is a key process for evaluating the behaviors of human being. Computer vision techniques can play a vital role in automating the overall process, however, occlusions, cluttered environment and illumination changes can make the whole task difficult. Using multiple cameras and warping known object appearance into the occluded view can solve the occlusion problem. In this paper, we present an automatic human detection and action recognition system using Hidden Markov Model and bag of Words. Background subtraction is performed using Gaussian mixture model. The algorithm is able to perform robust detection in the cluttered environment and severe occlusions. The novelty of this work is the dataset used. A private dataset has been created for this research at university of Minho. The experimental results show promising results.