Efficient Human Action Recognition by Cascaded Linear Classification

1st IEEE Workshop on Video-Oriented Object and Event Classification

We present a human action recognition system suitable
for very short sequences. In particular, we estimate Histograms
of Oriented Gradients (HOGs) for the current
frame as well as the corresponding dense flow field estimated
from two frames. The thus obtained descriptors are
then efficiently represented by the coefficients of a Nonnegative
Matrix Factorization (NMF). To further speed up
the overall process, we apply an efficient cascaded Linear
Discriminant Analysis (CLDA) classifier. In the experimental
results we show the benefits of the proposed approach
on standard benchmark datasets as well as on more challenging
and realistic videos. In addition, since other stateof-
the-art methods apply weighting between different cues,
we provide a detailed analysis of the importance of weighting
for action recognition and show that weighting is not
necessarily required for the given task.

PDF