Action Recognition from a Small Number of Frames

Computer Vision Winter Workshop

In this paper, we present an efficient system for action
recognition from very short sequences. For action recognition
typically appearance and/or motion information of an
action is analyzed using a large number of frames, which is
often not sufficient, if very fast actions (e.g., in sport analysis)
have to be analyzed. To overcome this limitation, we
propose a method that uses a single-frame representation
for actions based on appearance and on motion information.
In particular, we estimate Histograms of Oriented Gradients
(HOGs) for the current sample as well as for a flow
field. The thus obtained descriptors are then efficiently represented
by the coefficients of a Non-negative Matrix Factorization
(NMF). Actions are classified using one-vs-all Support
Vector Machines. Since the flow can be estimated from
two frames, in the evaluation stage only two consecutive
frames are required for the action analysis. Both, the optical
flow as well as the HOGs, can be computed very efficiently.
In the experiments, we compare the proposed approach to
state-of-the-art methods and show that it yield competitive
results. In addition, we demonstrate