A method to insert physically measured 3D point clouds of humanoid targets into real LiDAR scenes, using registered meshes to model occlusion, is shown to produce scenes geometrically close to real sensor scans.
The machine vision iceberg explained: Advancing dynamic testing by consid- ering holistic environmental relations,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Point Cloud Recombination: Systematic Real Data Augmentation Using Robotic Targets for LiDAR Perception Validation
A method to insert physically measured 3D point clouds of humanoid targets into real LiDAR scenes, using registered meshes to model occlusion, is shown to produce scenes geometrically close to real sensor scans.