Using SAX representation for human action recognition

Human action recognition is an important problem in Computer Vision. Although most of the existing solutions provide good accuracy results, the methods are often overly complex and computationally expensive, hindering practical application. In this regard, we introduce Symbolic Aggregate approximation (SAX) to address the problem of human action recognition. Given motion trajectories of reference points on an actor, SAX efficiently converts this time-series data to a symbolic representation. Moreover, the distance between two time series is approximated by the distance between their SAX representation, which is straight-forward and very simple. Requiring only trajectories of reference points, our method requires neither structure recovery nor silhouette extraction. The proposed method is validated on two public datasets. It has an accuracy comparable to related works and it performs well even in varying conditions, in addition to being faster compared to the existing methods.

► Symbolic Aggregate approXimation (SAX). ► Tremendous dimensionality and complexity reduction. ► No estimation of corresponding points between video sequences.