Action recognition using bag of features extracted from a beam of trajectories

A new spatio temporal descriptor is proposed for action recognition. The action is modelled from a beam of trajectories obtained using semi dense point tracking on the video sequence. We detect the dominant points of these trajectories as points of local extremum curvature and extract their corresponding feature vectors, to form a dictionary of atomic action elements. The high density of these informative and invariant elements allows effective statistical action description. Then, human action recognition is performed using a bag of feature model with SVM classifier. Experimentations show promising results on several well-known datasets.