Authors:
Geoffrey Vaquette
1
;
Catherine Achard
2
and
Laurent Lucat
1
Affiliations:
1
CEA and LIST, France
;
2
Sorbonne University, UPMC Univ Paris 06 and CNRS, France
Keyword(s):
Action Recognition, Action Detection, Feature Fusion, TUM Dataset, DOHT, Hough Transform.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Segmentation and Grouping
Abstract:
Automatic human action recognition is a challenging and largely explored domain. In this work, we focus
on action segmentation with Hough Transform paradigm and more precisely with Deeply Optimised Hough
Transform (DOHT). First, we apply DOHT on video sequences using the well-known dense trajectories features
and then, we propose to extend the method to efficiently merge information coming from various sensors.
We have introduced three different ways to perform fusion, depending on the level at which information is
merged. Advantages and disadvantages of these solutions are presented from the performance point of view
and also according to the ease of use. Thus, one of the fusion level has the advantage to stay suitabe even if
one or more sensors is out of order or disturbed.