BoundED

BoundED: Neural boundary and edge detection in 3D point clouds via local neighborhood statistics

Bode, Lukas (Universität Bonn)
Weinmann, M. (TU Delft Computer Graphics and Visualisation)
Klein, Reinhard (Universität Bonn)

2023

Extracting high-level structural information from 3D point clouds is challenging but essential for tasks like urban planning or autonomous driving requiring an advanced understanding of the scene at hand. Existing approaches are still not able to produce high-quality results consistently while being fast enough to be deployed in scenarios requiring interactivity. We propose to utilize a novel set of features describing the local neighborhood on a per-point basis via first and second order statistics as input for a simple and compact classification network to distinguish between non-edge, sharp-edge, and boundary points in the given data. Leveraging this feature embedding enables our algorithm to outperform the state-of-the-art technique PCEDNet in terms of quality and processing time while additionally allowing for the detection of boundaries in the processed point clouds.

Boundary detection
Classification
Edge detection
Machine learning
Neural network
Point cloud processing

http://resolver.tudelft.nl/uuid:5c540f8e-3583-47c0-a6c3-ddeeb5db53c2

https://doi.org/10.1016/j.isprsjprs.2023.09.023

0924-2716

ISPRS Journal of Photogrammetry and Remote Sensing, 205, 334-351

Institutional Repository

journal article

© 2023 Lukas Bode, M. Weinmann, Reinhard Klein