Genetic Programming-Evolved Spatio-Temporal Descriptor for Human-Action Recognition

The potential value of human action recognition has led to it becoming one of the most active research subjects in computer vision. In this paper, we propose a novel method to automatically generate low-level spatio-temporal descriptors showing good performance, for high-level human-action recognition tasks. We address this as an optimization problem using genetic programming (GP), an evolutionary method, which produces the descriptor by combining a set of primitive 3D operators. As far as we are aware, this is the first report of using GP for evolving spatio-temporal descriptors for action recognition. In our evolutionary architecture, the average cross-validation classification error calculated using the support-vector machine (SVM) classifier is used as the GP fitness function. We run GP on a mixed dataset combining the KTH and the Weizmann datasets to obtain a promising feature-descriptor solution for action recognition. To demonstrate generalizability, the best descriptor generated so far by GP has also been tested on the IXMAS dataset leading to better accuracies compared with some previous hand-crafted descriptors