Affine-Invariant Feature Extraction for Activity Recognition

<table>GMM background subtraction: the first and third rows display two sequences of walking and running actions from KTH and Weizmann action datasets, respectively, while the second and fourth rows show the results of background subtraction where foreground objects are shown in cyan color.</table>

International Scholarly Research Notices

fig1

Figure 1

Figure 1: Affine-Invariant Feature Extraction for Activity Recognition 