Relevant kinematic feature selection to support human action recognition in MoCap data

This paper presents a feature selection comparison oriented to human action recognition only with the kinematic features of skeleton representation. For this purpose, three relevance methods are used to rank the contribution of kinematic features for classifying an action is employed. Particularly,...

Full description

Autores:
Pulgarín Giraldo, Juan Diego
Alvarez Meza, Andrés Marino
Ruales Torres, Anderson Alberto
Castellanos-Dominguez, German
Tipo de recurso:
Fecha de publicación:
2017
Institución:
Universidad Autónoma de Occidente
Repositorio:
RED: Repositorio Educativo Digital UAO
Idioma:
eng
OAI Identifier:
oai:red.uao.edu.co:10614/11187
Acceso en línea:
http://hdl.handle.net/10614/11187
https://doi.org/10.1007/978-3-319-59773-7_51
Palabra clave:
Cinemática
Kinematics
Movimientos mecánicos
Mechanical movements
Center kernel alignment
Feature selection
Human motion
Kinematics
Motion capture data
Principal component analysis
Relevance
ReliefF
Rights
openAccess
License
Derechos Reservados - Universidad Autónoma de Occidente