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)
View/ Open
Impact
![Google Scholar](/xmlui/themes/Mirage2/images/uji/logo_google.png)
![Microsoft Academico](/xmlui/themes/Mirage2/images/uji/logo_microsoft.png)
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/7036
comunitat-uji-handle3:10234/8620
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
Integrating sensor models in deep learning boosts performance: application to monocular depth estimation in warehouse automationDate
2021-02-19Publisher
MDPIISSN
1424-8220Bibliographic citation
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/s21041437Type
info:eu-repo/semantics/articlePublisher version
https://www.mdpi.com/1424-8220/21/4/1437Version
info:eu-repo/semantics/publishedVersionSubject
Abstract
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. [-]
Is part of
Sensors, Volume 21, Issue 4 (February-2 2021)Funder Name
Ministerio de Ciencia e Innnovación | Universitat Jaume I | Generalitat Valenciana
Project code
DPI2015-69041-R | UJI-B2018-74 | PROMETEO / 2020/034
Project title or grant
UJI Robotic Intelligence Laboratory
Rights
info:eu-repo/semantics/openAccess
This item appears in the folowing collection(s)
- ICC_Articles [424]
The following license files are associated with this item: