Event Details
A Sim-to-Real Deformation Classification Pipeline using Data Augmentation and Domain Adaptation
Presenter: Joel Sol
Supervisor:
Date: Thu, May 9, 2024
Time: 09:00:00 - 00:00:00
Place: ZOOM - Please see below.
ABSTRACT
Location: Remote via Zoom
Join Zoom Meeting
https://uvic.zoom.us/j/89091211412?pwd=L1ZrMEVoc2Z0T1pjUG9KbkVFcURMQT09
Meeting ID: 890 9121 1412
Password: 432774
One tap mobile
+16475580588,,89091211412# Canada
+17789072071,,89091211412# Canada
Dial by your location
+1 647 558 0588 Canada
+1 778 907 2071 Canada
Meeting ID: 890 9121 1412
Find your local number: https://uvic.zoom.us/u/kbDhuvlmWD
Abstract:
Geometrical quality assurance is critical for improving manufacturing time and cost.
This is more inhibiting when the visual or haptic assessment of human operators is
necessary. Modern machine learning (ML) methods can solve this problem but require
large datasets including diverse deformations. However, preparing those deformations
using physical objects can be difficult and costly. This thesis proposes to use Blender,
an open-source simulation tool, to imitate object deformities and automate the preparation of synthetic datasets. The utility of these datasets can be further improved
using data augmentation techniques such as background randomization or domain
adaptation networks. The background randomization approach provides a way to
generalize the image distribution to a variety of environments, whereas the domain
adapted approach provides a better targeted distribution. This thesis showcases that
discrepancies between real and simulated environments can be mitigated to create
models effective at sim-to-real deformation classification.