Action classification algorithm based on EGEI and LPP

A foreground extraction algorithm based on background subtraction and edge detection was proposed to obtain the foreground with a little change. An action classification method based on Enhanced Gait Energy Image (EGEI) and Locality Preserving Projections (LPP) was used. The high dimensional feature space was non-linearly reduced to lower dimensional space, which outperformed PCA and 2DPCA. The nearest-neighbor classifier was adopted to distinguish different actions. This algorithm needn't extract the period of the video, which was indispensable in some other methods. Experimental results show that the algorithm is simple, and achieves higher classification accuracy with less running time.