First and Second Order Dynamics in a Hierarchical SOM system for Action Recognition
Författare
Summary, in English
Human recognition of the actions of other humans is very efficient and is based on patterns of movements. Our theoretical starting point is that the dynamics of the joint movements is important to action categorization. On the basis of this theory, we present a novel action recognition system that employs a hierarchy of Self-Organizing Maps together with a custom supervised neural network that learns to categorize actions. The system preprocesses the input from a Kinect like 3D camera to exploit the information not only about joint positions, but also their first and second order dynamics. We evaluate our system in two experiments with publicly available datasets, and compare its performance to the performance with less sophisticated preprocessing of the input. The results show that including the dynamics of the actions improves the performance. We also apply an attention mechanism that focuses on the parts of the body that are the most involved in performing the actions.
Publiceringsår
2017-06-04
Språk
Engelska
Sidor
574-585
Publikation/Tidskrift/Serie
Applied Soft Computing
Volym
59
Länkar
Dokumenttyp
Artikel i tidskrift
Förlag
Elsevier
Ämne
- Computer Vision and Robotics (Autonomous Systems)
Status
Published
Projekt
- What you say is what you did (WYSIWYD)
- Ikaros: An infrastructure for system level modelling of the brain
- Thinking in Time: Cognition, Communication and Learning
Forskningsgrupp
- Lund University Cognitive Science (LUCS)
ISBN/ISSN/Övrigt
- ISSN: 1568-4946