Distribution of Action Movements (DAM): A Descriptor for Human Action Recognition

Human action recognition from skeletal data is an important and active area of research in which the state of the art has not yet achieved near-perfect accuracy on many wellknown datasets. In this paper, we introduce the Distribution of Action Movements Descriptor, a novel action descriptor based on...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ronchetti, Franco, Quiroga, Facundo Manuel, Lanzarini, Laura Cristina, Estrebou, César Armando
Formato: Articulo Preprint
Lenguaje:Inglés
Publicado: 2015
Materias:
Ciencias Informáticas
Human action recognition
Descriptor
Prob Som
MSRC12
Action3D,
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/120542
https://link.springer.com/article/10.1007%2Fs11704-015-4320-x
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-120542
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Human action recognition
Descriptor
Prob Som
MSRC12
Action3D,
spellingShingle Ciencias Informáticas
Human action recognition
Descriptor
Prob Som
MSRC12
Action3D,
Ronchetti, Franco
Quiroga, Facundo Manuel
Lanzarini, Laura Cristina
Estrebou, César Armando
Distribution of Action Movements (DAM): A Descriptor for Human Action Recognition
topic_facet Ciencias Informáticas
Human action recognition
Descriptor
Prob Som
MSRC12
Action3D,
description Human action recognition from skeletal data is an important and active area of research in which the state of the art has not yet achieved near-perfect accuracy on many wellknown datasets. In this paper, we introduce the Distribution of Action Movements Descriptor, a novel action descriptor based on the distribution of the directions of the motions of the joints between frames, over the set of all possible motions in the dataset. The descriptor is computed as a normalized histogram over a set of representative directions of the joints, which are in turn obtained via clustering. While the descriptor is global in the sense that it represents the overall distribution of movement directions of an action, it is able to partially retain its temporal structure by applying a windowing scheme. The descriptor, together with a standard classifier, outperforms several state-of-the-art techniques on many wellknown datasets.
format Articulo
Preprint
author Ronchetti, Franco
Quiroga, Facundo Manuel
Lanzarini, Laura Cristina
Estrebou, César Armando
author_facet Ronchetti, Franco
Quiroga, Facundo Manuel
Lanzarini, Laura Cristina
Estrebou, César Armando
author_sort Ronchetti, Franco
title Distribution of Action Movements (DAM): A Descriptor for Human Action Recognition
title_short Distribution of Action Movements (DAM): A Descriptor for Human Action Recognition
title_full Distribution of Action Movements (DAM): A Descriptor for Human Action Recognition
title_fullStr Distribution of Action Movements (DAM): A Descriptor for Human Action Recognition
title_full_unstemmed Distribution of Action Movements (DAM): A Descriptor for Human Action Recognition
title_sort distribution of action movements (dam): a descriptor for human action recognition
publishDate 2015
url http://sedici.unlp.edu.ar/handle/10915/120542
https://link.springer.com/article/10.1007%2Fs11704-015-4320-x
work_keys_str_mv AT ronchettifranco distributionofactionmovementsdamadescriptorforhumanactionrecognition
AT quirogafacundomanuel distributionofactionmovementsdamadescriptorforhumanactionrecognition
AT lanzarinilauracristina distributionofactionmovementsdamadescriptorforhumanactionrecognition
AT estreboucesararmando distributionofactionmovementsdamadescriptorforhumanactionrecognition
bdutipo_str Repositorios
_version_ 1764820447891816450

Ejemplares similares