Integrating sensor models in deep learning boosts performance: application to monocular depth estimation in warehouse automation
![Thumbnail](/xmlui/bitstream/handle/10234/193057/sensors-21-01437.pdf.jpg?sequence=5&isAllowed=y)
Ver/ Abrir
Impacto
![Google Scholar](/xmlui/themes/Mirage2/images/uji/logo_google.png)
![Microsoft Academico](/xmlui/themes/Mirage2/images/uji/logo_microsoft.png)
Metadatos
Mostrar el registro completo del ítemcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/8620
comunitat-uji-handle4:
INVESTIGACIONMetadatos
Título
Integrating sensor models in deep learning boosts performance: application to monocular depth estimation in warehouse automationFecha de publicación
2021-02-19Editor
MDPIISSN
1424-8220Cita bibliográfica
Yoneyama, Ryota; Duran, Angel J.; del Pobil, Angel P. 2021. "Integrating Sensor Models in Deep Learning Boosts Performance: Application to Monocular Depth Estimation in Warehouse Automation" Sensors 21, no. 4: 1437. https://doi.org/10.3390/s21041437Tipo de documento
info:eu-repo/semantics/articleVersión de la editorial
https://www.mdpi.com/1424-8220/21/4/1437Versión
info:eu-repo/semantics/publishedVersionPalabras clave / Materias
Resumen
Deep learning is the mainstream paradigm in computer vision and machine learning,
but performance is usually not as good as expected when used for applications in robot vision.
The problem is that robot sensing is ... [+]
Deep learning is the mainstream paradigm in computer vision and machine learning,
but performance is usually not as good as expected when used for applications in robot vision.
The problem is that robot sensing is inherently active, and often, relevant data is scarce for many
application domains. This calls for novel deep learning approaches that can offer a good performance
at a lower data consumption cost. We address here monocular depth estimation in warehouse
automation with new methods and three different deep architectures. Our results suggest that the
incorporation of sensor models and prior knowledge relative to robotic active vision, can consistently
improve the results and learning performance from fewer than usual training samples, as compared
to standard data-driven deep learning. [-]
Publicado en
Sensors, Volume 21, Issue 4 (February-2 2021)Entidad financiadora
Ministerio de Ciencia e Innnovación | Universitat Jaume I | Generalitat Valenciana
Código del proyecto o subvención
DPI2015-69041-R | UJI-B2018-74 | PROMETEO / 2020/034
Título del proyecto o subvención
UJI Robotic Intelligence Laboratory
Derechos de acceso
info:eu-repo/semantics/openAccess
Aparece en las colecciones
- ICC_Articles [424]
El ítem tiene asociados los siguientes ficheros de licencia: