Projects per year
Abstract
The number of potential applications has made automatic recognition of human actions a very active research area. Different approaches have been followed based on trajectories through some state space. In this paper we also model an action as a trajectory through a state space, but we represent the actions as a sequence of temporal isolated instances, denoted primitives. These primitives are each defined by four features extracted from motion images. The primitives are recognized in each frame based on a trained classifier resulting in a sequence of primitives. From this sequence we recognize different temporal actions using a probabilistic Edit Distance method. The method is tested on different actions with and without noise and the results show recognition rates of 88.7% and 85.5%, respectively.
Original language | English |
---|---|
Book series | Lecture Notes in Computer Science |
Volume | 5085 |
Issue number | 1 |
Pages (from-to) | 24-35 |
Number of pages | 12 |
ISSN | 0302-9743 |
DOIs | |
Publication status | Published - 2009 |
Keywords
- Computer vision
- Human action recognition
- Motion primitives
Fingerprint
Dive into the research topics of 'Motion Primitives and Probabilistic Edit Distance for Action Recognition'. Together they form a unique fingerprint.Projects
- 2 Finished
-
HERMES - Human-Expressive Representations of Motion and Their Evaluation in Sequences
Fihl, P., Holte, M. B., Reng, L., Moeslund, T. B. & Granum, E.
01/04/2006 → 31/08/2009
Project: Research
-
MoPrim - In search for the motion primitives for a communicative human body language
Moeslund, T. B., Reng, L. & Fihl, P.
01/04/2004 → 01/05/2007
Project: Research