Robustifying semantic perception of traversability across wearable RGB-depth cameras
Identifiers
Permanent link (URI): http://hdl.handle.net/10017/43167DOI: 10.1364/AO.58.003141
ISSN: 1559-128X
Publisher
OSA
Date
2019-04Funders
Ministerio de Economía y Competitividad
Comunidad de Madrid
Dirección General de Tráfico
Bibliographic citation
Yang, K., Bergasa, L. M., Romera, E. & Wang, K. 2019, "Robustifying semantic cognition of traversability across wearable RGB-depth cameras", Applied Optics, vol. 58, no. 12, pp. 3141-3155
Project
info:eu-repo/grantAgreement/MINECO//TRA2015-70501-C2-1-R/ES/VEHICULO INTELIGENTE PARA PERSONAS MAYORES/
info:eu-repo/grantAgreement/DGT//SPIP2017-02305
info:eu-repo/grantAgreement/CAM//S2013%2FMIT-2748/ES/ROBOTICA APLICADA A LA MEJORA DE LA CALIDAD DE VIDA DE LOS CIUDADANOS, FASE III/RoboCity2030-III-CM
Document type
info:eu-repo/semantics/article
Version
info:eu-repo/semantics/acceptedVersion
Publisher's version
https://doi.org/10.1364/AO.58.003141Rights
Attribution-NonCommercial-NoDerivatives 4.0 Internacional
© 2019 Optical Society of America
Access rights
info:eu-repo/semantics/openAccess
Abstract
Semantic segmentation represents a promising means to unify different detection tasks, especially pixelwise traversability perception as the fundamental enabler in robotic vision systems aiding upper-level
navigational applications. However, major research efforts are being put into earning marginal accuracy increments on semantic segmentation benchmarks, without assuring the robustness of real-time
segmenters to be deployed in assistive cognition systems for the visually impaired. In this paper, we
explore in a comparative study across four perception systems, including a pair of commercial smart
glasses, a customized wearable prototype and two portable RGB-Depth (RGB-D) cameras that are being
integrated in the next generation of navigation assistance devices. More concretely, we analyze the gap
between the concepts of “accuracy” and “robustness” on the critical traversability-related semantic scene
understanding. A cluster of efficient deep architectures is proposed, which are built using spatial factorizations, hierarchical dilations and pyramidal representations. Based on these architectures, this research
demonstrates the augmented robustness of semantically traversable area parsing against the variations
of environmental conditions in diverse RGB-D observations, and sensorial factors such as illumination,
imaging quality, field of view and detectable depth range.
Files in this item
Files | Size | Format |
|
---|---|---|---|
Robustifying_Yang_Appl_Optics_ ... | 3.877Mb |
|
Files | Size | Format |
|
---|---|---|---|
Robustifying_Yang_Appl_Optics_ ... | 3.877Mb |
|
Collections
- ELECTRON - Artículos [242]
- ROBESAFE - Artículos [37]