Noah Kuntz

Learn More
— This paper presents a set of segmentation methods for various types of 3D point clouds. Segmentation of dense 3D data (e.g. Riegl scans) is optimised via a simple yet efficient voxelisation of the space. Prior ground extraction is empirically shown to significantly improve segmentation performance. Seg-mentation of sparse 3D data (e.g. Velodyne scans) is(More)
Currently, robotic rotorcraft determine landing zones based on visual cues or predetermined GPS waypoints. Missions such as perch-and-stare or cargo delivery demand the ability to detect safe landing zones in unstructured environments. To enable these missions, high fidelity maps can be constructed to assist the robot in locating a place to land. In(More)
  • 1