Por favor, use este identificador para citar o enlazar este ítem:
https://hdl.handle.net/11000/31595
Analysis of Data Augmentation Techniques
for Mobile Robots Localization by Means
of Convolutional Neural Networks
Ver/Abrir: 11-978-3-031-34111-3_42 (1).pdf
736,12 kB
Adobe PDF
Compartir:
Este recurso está restringido
Título : Analysis of Data Augmentation Techniques
for Mobile Robots Localization by Means
of Convolutional Neural Networks |
Autor : Céspedes, Orlando Jose Cebollada, Sergio Cabrera, Juan José Reinoso, Oscar ![](/image/ORCID.jpg) Paya, Luis ![](/image/ORCID.jpg) |
Editor : Springer |
Departamento: Departamentos de la UMH::Ingeniería de Sistemas y Automática |
Fecha de publicación: 2023-06 |
URI : https://hdl.handle.net/11000/31595 |
Resumen :
This work presents an evaluation regarding the use of data
augmentation to carry out the rough localization step within a hierarchical
localization framework. The method consists of two steps: first, the
robot captures an image and it is introduced into a CNN in order to estimate
the room where it was captured (rough localization). After that, a
holistic descriptor is obtained from the network and it is compared with
the descriptors stored in the model. The most similar image provides the
position where the robot captured the image (fine localization). Regarding
the rough localization, it is essential that the CNN achieves a high
accuracy, since an error in this step would imply a considerable localization
error. With this aim, several visual effects were separately analyzed
in order to know their impact on the CNN when data augmentation
is tackled. The results permit designing a data augmentation which is
useful for training a CNN that solves the localization problem in real
operation conditions, including changes in the lighting conditions
|
Palabras clave/Materias: Mobile Robotics Omnidirectional Vision Hierarchical Localization Deep Learning Data Augmentation |
Área de conocimiento : CDU: Ciencias aplicadas: Ingeniería. Tecnología |
Tipo documento : application/pdf |
Derechos de acceso: info:eu-repo/semantics/closedAccess Attribution-NonCommercial-NoDerivatives 4.0 Internacional |
Aparece en las colecciones: Artículos Ingeniería de Sistemas y Automática
|
La licencia se describe como: Atribución-NonComercial-NoDerivada 4.0 Internacional.