Authors:
Fabio Martinez
1
;
Antoine Manzanera
2
;
Michèle Gouiffès
3
and
Thanh Phuong Nguyen
4
Affiliations:
1
LIMSI-CNRS, Université Paris-Saclay, U2IS/Robotics-Vision, ENSTA-ParisTech and Université Paris-Saclay, France
;
2
U2IS/Robotics-Vision, ENSTA-ParisTech and Université Paris-Saclay, France
;
3
LIMSI-CNRS and Université Paris-Saclay, France
;
4
LSIS, UMR 7296 and Université du Sud Toulon Var, France
Keyword(s):
Action Recognition, Semi Dense Trajectories, Motion Shape Context, On-line Action Descriptors.
Abstract:
This work introduces a novel action descriptor that represents activities instantaneously in each frame of a
video sequence for action recognition. The proposed approach first characterizes the video by computing
kinematic primitives along trajectories obtained by semi-dense point tracking in the video. Then, a frame level
characterization is achieved by computing a spatial action-centric polar representation from the computed trajectories.
This representation aims at quantifying the image space and grouping the trajectories within radial
and angular regions. Motion histograms are then temporally aggregated in each region to form a kinematic
signature from the current trajectories. Histograms with several time depths can be computed to obtain different
motion characterization versions. These motion histograms are updated at each time, to reflect the
kinematic trend of trajectories in each region. The action descriptor is then defined as the collection of motion
histograms fr
om all the regions in a specific frame. Classic support vector machine (SVM) models are used to
carry out the classification according to each time depth. The proposed approach is easy to implement, very
fast and the representation is consistent to code a broad variety of actions thanks to a multi-level representation
of motion primitives. The proposed approach was evaluated on different public action datasets showing
competitive results (94% and 88:7% of accuracy are achieved in KTH and UT datasets, respectively), and an
efficient computation time.
(More)