Alignment and 3D scene change detection for segmentation in autonomous earth moving

The tasks of region or object segmentation and environment change detection in a 3D context are investigated and tested on an autonomous skid steer loader. This is achieved through a technique analogous to background subtraction utilising 3D scan data which is first aligned before a voxel subtraction operation against a prior map. We highlight the close relationships between the scan-to-map alignment, background subtraction and 3D scan-to-map matching problems.