Depth-Camera-Based In-line Evaluation of Surface Geometry and Material Classification For Robotic Spraying

Open access
Date
2020-10Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
Abstract
This paper presents a feasibility study of surface geometry (SG) evaluation and material classification (MC) for robotic spraying. We propose two complementary approaches using point clouds and intensity data provided by a state-of-the-art industrial time-of-flight (ToF) depth camera. The SG evaluation is based on geometric feature computation within local neighbourhoods, which are then used within a supervised classification. The results of this approach are SG classes according to the level of geometric variability of the surface, displayed as SG maps. For MC, active reflectance estimation is investigated and exploited to derive features related to the reflectance and diffusive properties of each material for classification. The result of both approaches can be prospectively used as feedback in digital fabrication for in-line adaptation of the process to improve control of relevant geometrical and material properties. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000446406Publication status
publishedExternal links
Book title
2020 Proceedings of the 37th ISARC (online)Pages / Article No.
Publisher
International Association for Automation and Robotics in ConstructionEvent
Subject
Surface Geometry; Material Classification; Digital Fabrication; Depth Camera; Machine LearningOrganisational unit
03964 - Wieser, Andreas / Wieser, Andreas
02284 - NFS Digitale Fabrikation / NCCR Digital Fabrication
Notes
Additional Notes": Due to the Coronavirus (COVID-19) the conference was conducted virtually.More
Show all metadata
ETH Bibliography
yes
Altmetrics