RESIDUAL NEURAL NETWORKS FOR MONOCULAR DEPTH ESTIMATION IN NATURAL ENVIRONMENTS
DYNA NEW TECHNOLOGIES · 2024
DOI: 10.6036/nt11086 ↗Kurz gefasst
Fachartikel in der Zeitschrift DYNA NEW TECHNOLOGIES, 2024. Verfasst von ALEXANDRA ROMERO LUGO und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Presently, depth estimation research has focused on deep learning, mainly on monocular depth estimation, because this technique has proven to be an excellent alternative for methods that use expensive sensors or require high computational consumption, providing higher performance and accuracy. Despite there being a large number of works, most have focused on indoor and urban datasets. Due to this, we review the variants of the residual networks being trained with images of natural environments with a high presence of vegetation. We proposed a new dataset specialized in natural environments using the AirSim simulation to evaluate the variants of the ResNet and ResNeXt families and verify that these can be used to detect leaves and thin branches with their corresponding depth. We conclude that a deeper residual neural network is not always the best option for monocular depth estimation. It is necessary to consider the type of network architecture, computing resources available, and the content and size of the data set. Keywords: Deep Learning, Residual Networks, Monocular Depth Estimation
Zitieren
APA
LUGO, A. R., SALAZAR, A. M., PACHECO, J. F., ELIAS, R. P., & FRANCO, N. G. (2024). RESIDUAL NEURAL NETWORKS FOR MONOCULAR DEPTH ESTIMATION IN NATURAL ENVIRONMENTS. DYNA NEW TECHNOLOGIES. https://doi.org/10.6036/nt11086
Vancouver
LUGO AR, SALAZAR AM, PACHECO JF, ELIAS RP, FRANCO NG. RESIDUAL NEURAL NETWORKS FOR MONOCULAR DEPTH ESTIMATION IN NATURAL ENVIRONMENTS. DYNA NEW TECHNOLOGIES. 2024. doi:10.6036/nt11086
BibTeX
@article{LUGO2024,
author = {LUGO, ALEXANDRA ROMERO and SALAZAR, ANDREA MAGADAN and PACHECO, JORGE FUENTES and ELIAS, RAUL PINTO and FRANCO, NIMROD GONZALEZ},
title = {RESIDUAL NEURAL NETWORKS FOR MONOCULAR DEPTH ESTIMATION IN NATURAL ENVIRONMENTS},
journal = {DYNA NEW TECHNOLOGIES},
year = {2024},
doi = {10.6036/nt11086}
}
EUVIMED