Modeling Spatial Layout of Features for Real World Scenario RGB-D Action Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2016

Modeling Spatial Layout of Features for Real World Scenario RGB-D Action Recognition

Abstract

Depth information improves skeleton detection, thus skeleton based methods are the most popular methods in RGB-D action recognition. But skeleton detection working range is limited in terms of distance and viewpoint. Most of the skeleton based action recognition methods ignore fact that skeleton may be missing. Local points-of-interest (POIs) do not require skeleton detection. But they fail if they cannot detect enough POIs e.g. amount of motion in action is low. Most of them ignore spatial-location of features. We cope with the above problems by employing people detector instead of skeleton detector. We propose method to encode spatial-layout of features inside bounding box. We also introduce descriptor which encodes static information for actions with low amount of motion. We validate our approach on: 3 public data-sets. The results show that our method is competitive to skeleton based methods, while requiring much simpler people detection instead of skeleton detection.
Fichier principal
Vignette du fichier
koperski_avss16_hal.pdf (824.65 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01399037 , version 1 (18-11-2016)

Identifiers

Cite

Michal Koperski, Francois Bremond. Modeling Spatial Layout of Features for Real World Scenario RGB-D Action Recognition. AVSS 2016, Aug 2016, Colorado Springs, United States. pp.44 - 50, ⟨10.1109/AVSS.2016.7738023⟩. ⟨hal-01399037⟩
149 View
280 Download

Altmetric

Share

Gmail Facebook X LinkedIn More