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

Michal Koperski 1 Francois Bremond 1
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.inria.fr/hal-01399037
Contributor : Michal Koperski <>
Submitted on : Friday, November 18, 2016 - 11:31:37 AM
Last modification on : Tuesday, July 24, 2018 - 3:48:17 PM
Long-term archiving on : Tuesday, March 21, 2017 - 9:38:35 AM

File

koperski_avss16_hal.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

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⟩

Share

Metrics

Record views

245

Files downloads

254