Primitive Based Action Representation and Recognition

Sanmohan Baby; Volker Krüger

doi:10.1007/978-3-642-02230-2_4

Primitive Based Action Representation and Recognition

Sanmohan Baby, Volker Krüger

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › peer review

7 Citationer (Scopus)

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.

Originalsprog	Engelsk
Bogserie	Lecture Notes in Computer Science
Sider (fra-til)	31-40
Antal sider	10
ISSN	0302-9743
DOI	https://doi.org/10.1007/978-3-642-02230-2_4
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

Adgang til dokumentet

10.1007/978-3-642-02230-2_4

http://www.springerlink.com/content/yv5501516404t5h8/?p=d1f1d06139ae4f05ba5d6701fd9a4e2c&pi=3

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Citationsformater

@article{c241cce0ca8b11dda016000ea68e967b,

title = "Primitive Based Action Representation and Recognition",

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.",

author = "Sanmohan Baby and Volker Kr{\"u}ger",

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 Redakt{\o}rer: Arnt-B{\o}rre Salberg Jon Yngve Hardeberg Robert Jenssen; SCIA 2009 ; Conference date: 15-06-2009 Through 18-06-2009",

year = "2009",

doi = "10.1007/978-3-642-02230-2_4",

language = "English",

pages = "31--40",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Physica-Verlag",

}

TY - JOUR

T1 - Primitive Based Action Representation and Recognition

AU - Baby, Sanmohan

AU - Krüger, Volker

N1 - Conference code: 16

PY - 2009

Y1 - 2009

N2 - 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.

AB - 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.

U2 - 10.1007/978-3-642-02230-2_4

DO - 10.1007/978-3-642-02230-2_4

M3 - Journal article

SN - 0302-9743

SP - 31

EP - 40

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

T2 - SCIA 2009

Y2 - 15 June 2009 through 18 June 2009

ER -

Primitive Based Action Representation and Recognition

Abstract

Konference

Bibliografisk note

Adgang til dokumentet

AUB Link

Fingeraftryk

Citationsformater