Please use this identifier to cite or link to this item:
https://hdl.handle.net/11000/32977
An evaluation of CNN models and data augmentation techniques
in hierarchical localization of mobile robots
Title: An evaluation of CNN models and data augmentation techniques
in hierarchical localization of mobile robots |
Authors: Cabrera, Juan José Céspedes, Orlando José Cebollada, Sergio Reinoso, Oscar Paya, Luis |
Editor: Springer |
Department: Departamentos de la UMH::Ingeniería de Sistemas y Automática |
Issue Date: 2024 |
URI: https://hdl.handle.net/11000/32977 |
Abstract:
This work presents an evaluation of CNN models and data augmentation to carry out the hierarchical localization of a mobile
robot by using omnidirectional images. In this sense, an ablation study of diferent state-of-the-art CNN models used as
backbone is presented and a variety of data augmentation visual efects are proposed for addressing the visual localization
of the robot. The proposed method is based on the adaption and re-training of a CNN with a dual purpose: (1) to perform a
rough localization step in which the model is used to predict the room from which an image was captured, and (2) to address
the fne localization step, which consists in retrieving the most similar image of the visual map among those contained in the
previously predicted room by means of a pairwise comparison between descriptors obtained from an intermediate layer of
the CNN. In this sense, we evaluate the impact of diferent state-of-the-art CNN models such as ConvNeXt for addressing the
proposed localization. Finally, a variety of data augmentation visual efects are separately employed for training the model
and their impact is assessed. The performance of the resulting CNNs is evaluated under real operation conditions, including
changes in the lighting conditions.
|
Keywords/Subjects: Mobile robotics Omnidirectional vision Hierarchical localization Deep learning Data augmentation |
Knowledge area: CDU: Ciencias aplicadas: Ingeniería. Tecnología |
Type of document: application/pdf |
Access rights: info:eu-repo/semantics/openAccess Attribution-NonCommercial-NoDerivatives 4.0 Internacional |
DOI: https://doi.org/10.1007/s12530-024-09604-6 |
Appears in Collections: Artículos Ingeniería de Sistemas y Automática
|
???jsp.display-item.text9???