Georges Chahine presents Multi-Sensor Mapping in Natural Environments: 3D Reconstruction and Temporal Alignment

On 2022-03-22 11:00:00 at G205, Karlovo náměstí 13, Praha 2
Hybrid seminar:
- Physical presence at G205, KN
- Online at meet.google.com/npz-satd-eiz

Using semantic knowledge, we constrain the Iterative Closest
Point (ICP) in order to build semantic keyframes as well as to align
them both spatially and temporally. Hierarchical clustering of
ICP-generated transformations is then used to both eliminate outliers
and find alignment consensus, followed by an optimization scheme based
on a factor graph that includes loop closure. Data was captured using
a portable robotic sensor suite consisting of three cameras, three
dimensional lidar, and an inertial navigation system. The data was
acquired in monthly intervals over 12 months, by revisiting the same
trajectory between August 2020 and July 2021. Finally, it has been
shown that it is possible to align monthly surveys, taken over a year
using the conceived sensor suite, and to provide insightful metrics
for change evaluation in natural environments.

About Georges: He has recently graduated with his Ph.D. at the Georgia
Institute of Technology on 3D reconstruction and long term temporal
alignment on scenes dominated by vegetation.

He will stay for 2 weeks until 29/03 to collaborate on a data
collection project for retrieval and localization.
Feel free to reach out to him if you are interested in his work.

In the meantime, here are videos of his impressive reconstructions:
- Year long In-depth navigation inside point clouds:
https://youtu.be/iB0Qn1Xeuog
- Timelapse of aligned 3D point clouds showing natural changes:
https://youtu.be/2tmxL0rMDqg


Locations:
- Physical: G205
- Online: meet.google.com/npz-satd-eiz
Za obsah zodpovídá: Petr Pošík