Human action recognition using an ensemble of body-part detectors

This paper describes an approach to human action recognition based on the probabilistic optimization model of body parts using Hidden Markov Model (HMM). Our proposed method is able to distinguish between similar actions by only considering the body parts having major contribution to the actions, for example, legs for walking, jogging and running; hands for boxing, waving and clapping. We apply HMMs to model the stochastic movement of the body-parts for action recognition. The HMM construction requires an ensemble of body-part detectors, followed by grouping of part detections to perform human identification. Three example-based body part detectors are trained to detect three components of the human body: the head, the legs and the arms. These detectors cope with viewpoint changes and self-occlusions through the use of ten sub-classifiers that detect body parts under a specific range of viewpoints. Each sub-classifier is a Support Vector Machine (SVM) trained on features selected for the discriminative power for each particular part/viewpoint combination. Grouping of these detections is then performed using a simple geometric constraint model which yields a viewpoint invariant human detector. We test our approach on the most commonly used action dataset, the KTH