Action Recognition Using Motion Primitives and Probabilistic Edit Distance

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

12 Citationer (Scopus)

Resumé

In this paper we describe a recognition approach based on the notion of primitives. As opposed to recognizing actions based on temporal trajectories or temporal volumes, primitive-based recognition is based on representing a temporal sequence containing an action by only a few characteristic time instances. The human whereabouts at these instances are extracted by double difference images and represented by four features. In each frame the primitive, if any, that best explains the observed data is identified. This leads to a discrete recognition problem since a video sequence will be converted into a string containing a sequence of symbols, each representing a primitives. After pruning the string a probabilistic Edit Distance classifier is applied to identify which action best describes the pruned string. The approach is evaluated on five one-arm gestures and the recognition rate is 91.3%. This is concluded to be a promising result but also leaves room for further improvements.
OriginalsprogEngelsk
TitelArticulated Motion and Deformable Objects
RedaktørerFrancisco J. Perales, Robert B. Fisher
Antal sider10
ForlagIEEE Computer Society Press
Publikationsdato2006
Sider375-384
ISBN (Trykt)9783540360315
StatusUdgivet - 2006
Begivenhed4th International Conference on Articulated Motion and Deformable Objects - Port d'Andratx, Spanien
Varighed: 11 jul. 200614 jul. 2006
Konferencens nummer: 4

Konference

Konference4th International Conference on Articulated Motion and Deformable Objects
Nummer4
LandSpanien
ByPort d'Andratx
Periode11/07/200614/07/2006
NavnLecture Notes in Computer Science
Nummer4069
Vol/bind1
ISSN0302-9743

Fingerprint

Classifiers
Trajectories

Citer dette

Fihl, P., Holte, M. B., Moeslund, T. B., & Reng, L. (2006). Action Recognition Using Motion Primitives and Probabilistic Edit Distance. I F. J. Perales, & R. B. Fisher (red.), Articulated Motion and Deformable Objects (s. 375-384). IEEE Computer Society Press. Lecture Notes in Computer Science, Nr. 4069, Bind. 1
Fihl, Preben ; Holte, Michael Boelstoft ; Moeslund, Thomas B. ; Reng, Lars. / Action Recognition Using Motion Primitives and Probabilistic Edit Distance. Articulated Motion and Deformable Objects. red. / Francisco J. Perales ; Robert B. Fisher. IEEE Computer Society Press, 2006. s. 375-384 (Lecture Notes in Computer Science; Nr. 4069, Bind 1).
@inproceedings{91917e808a8011dbbb3d000ea68e967b,
title = "Action Recognition Using Motion Primitives and Probabilistic Edit Distance",
abstract = "In this paper we describe a recognition approach based on the notion of primitives. As opposed to recognizing actions based on temporal trajectories or temporal volumes, primitive-based recognition is based on representing a temporal sequence containing an action by only a few characteristic time instances. The human whereabouts at these instances are extracted by double difference images and represented by four features. In each frame the primitive, if any, that best explains the observed data is identified. This leads to a discrete recognition problem since a video sequence will be converted into a string containing a sequence of symbols, each representing a primitives. After pruning the string a probabilistic Edit Distance classifier is applied to identify which action best describes the pruned string. The approach is evaluated on five one-arm gestures and the recognition rate is 91.3{\%}. This is concluded to be a promising result but also leaves room for further improvements.",
author = "Preben Fihl and Holte, {Michael Boelstoft} and Moeslund, {Thomas B.} and Lars Reng",
year = "2006",
language = "English",
isbn = "9783540360315",
series = "Lecture Notes in Computer Science",
publisher = "IEEE Computer Society Press",
number = "4069",
pages = "375--384",
editor = "Perales, {Francisco J.} and Fisher, {Robert B.}",
booktitle = "Articulated Motion and Deformable Objects",
address = "United States",

}

Fihl, P, Holte, MB, Moeslund, TB & Reng, L 2006, Action Recognition Using Motion Primitives and Probabilistic Edit Distance. i FJ Perales & RB Fisher (red), Articulated Motion and Deformable Objects. IEEE Computer Society Press, Lecture Notes in Computer Science, nr. 4069, bind 1, s. 375-384, 4th International Conference on Articulated Motion and Deformable Objects, Port d'Andratx, Spanien, 11/07/2006.

Action Recognition Using Motion Primitives and Probabilistic Edit Distance. / Fihl, Preben; Holte, Michael Boelstoft; Moeslund, Thomas B.; Reng, Lars.

Articulated Motion and Deformable Objects. red. / Francisco J. Perales; Robert B. Fisher. IEEE Computer Society Press, 2006. s. 375-384 (Lecture Notes in Computer Science; Nr. 4069, Bind 1).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Action Recognition Using Motion Primitives and Probabilistic Edit Distance

AU - Fihl, Preben

AU - Holte, Michael Boelstoft

AU - Moeslund, Thomas B.

AU - Reng, Lars

PY - 2006

Y1 - 2006

N2 - In this paper we describe a recognition approach based on the notion of primitives. As opposed to recognizing actions based on temporal trajectories or temporal volumes, primitive-based recognition is based on representing a temporal sequence containing an action by only a few characteristic time instances. The human whereabouts at these instances are extracted by double difference images and represented by four features. In each frame the primitive, if any, that best explains the observed data is identified. This leads to a discrete recognition problem since a video sequence will be converted into a string containing a sequence of symbols, each representing a primitives. After pruning the string a probabilistic Edit Distance classifier is applied to identify which action best describes the pruned string. The approach is evaluated on five one-arm gestures and the recognition rate is 91.3%. This is concluded to be a promising result but also leaves room for further improvements.

AB - In this paper we describe a recognition approach based on the notion of primitives. As opposed to recognizing actions based on temporal trajectories or temporal volumes, primitive-based recognition is based on representing a temporal sequence containing an action by only a few characteristic time instances. The human whereabouts at these instances are extracted by double difference images and represented by four features. In each frame the primitive, if any, that best explains the observed data is identified. This leads to a discrete recognition problem since a video sequence will be converted into a string containing a sequence of symbols, each representing a primitives. After pruning the string a probabilistic Edit Distance classifier is applied to identify which action best describes the pruned string. The approach is evaluated on five one-arm gestures and the recognition rate is 91.3%. This is concluded to be a promising result but also leaves room for further improvements.

M3 - Article in proceeding

SN - 9783540360315

T3 - Lecture Notes in Computer Science

SP - 375

EP - 384

BT - Articulated Motion and Deformable Objects

A2 - Perales, Francisco J.

A2 - Fisher, Robert B.

PB - IEEE Computer Society Press

ER -

Fihl P, Holte MB, Moeslund TB, Reng L. Action Recognition Using Motion Primitives and Probabilistic Edit Distance. I Perales FJ, Fisher RB, red., Articulated Motion and Deformable Objects. IEEE Computer Society Press. 2006. s. 375-384. (Lecture Notes in Computer Science; Nr. 4069, Bind 1).