Abstract
There has been a recent interest in segmenting action sequences into
meaningful parts (action primitives) and to model actions on a
higher level based on these action primitives. Unlike previous works where action primitives are defined
a-priori and search is made for them later, we present a sequential and statistical
learning algorithm for
automatic detection of the action primitives and the action grammar
based on these primitives. We model a set of actions using a
single HMM whose structure is learned incrementally as we observe
new types. Actions are modeled with sufficient number of Gaussians which would
become the states of an HMM for an action. For different actions we
find the states that are common in the actions which are then treated
as an action primitive.
meaningful parts (action primitives) and to model actions on a
higher level based on these action primitives. Unlike previous works where action primitives are defined
a-priori and search is made for them later, we present a sequential and statistical
learning algorithm for
automatic detection of the action primitives and the action grammar
based on these primitives. We model a set of actions using a
single HMM whose structure is learned incrementally as we observe
new types. Actions are modeled with sufficient number of Gaussians which would
become the states of an HMM for an action. For different actions we
find the states that are common in the actions which are then treated
as an action primitive.
Originalsprog | Engelsk |
---|---|
Bogserie | Lecture Notes in Computer Science |
Sider (fra-til) | 31-40 |
Antal sider | 10 |
ISSN | 0302-9743 |
DOI | |
Status | Udgivet - 2009 |
Begivenhed | SCIA 2009 - Oslo, Norge Varighed: 15 jun. 2009 → 18 jun. 2009 Konferencens nummer: 16 |
Konference
Konference | SCIA 2009 |
---|---|
Nummer | 16 |
Land/Område | Norge |
By | Oslo |
Periode | 15/06/2009 → 18/06/2009 |
Bibliografisk note
Titel:Image Analysis
Undertitel:
16th Scandinavian Conference, SCIA 2009Oslo, Norway, June 15-18, 2009Proceedings
Oversat titel:
Oversat undertitel:
Forlag:
Springer
ISBN (Trykt):
9783642022296
ISBN (Elektronisk):
Publikationsserier:
Lecture Notes in Computer Science, 0302-9743, 1611-3349, 5575
Redaktører:
Arnt-Børre Salberg
Jon Yngve Hardeberg
Robert Jenssen