Skip to content

TDA feature extraction on low point cloud densities #3

Description

@bhuppenthal

Before calculating the TDA features, a voxel downsampling step is performed on the input point cloud. The default voxel size for downsampling is 0.09 m. Thus, for every 9 cm x 9 cm x 9 cm cube in space, all points are replaced by a single representative point. On May 14th, 2026 I noticed while processing scan date 2/4/2022 that this resulted in downsampled point clouds containing between 3-30 points. I suspect this is insufficient to accurately estimate TDA features.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions