Segmentation of 3D lidar data in non-flat urban environments using a local convexity criterion

Present object detection methods working on 3D range data are so far either optimized for unstructured offroad environments or flat urban environments. We present a fast algorithm able to deal with tremendous amounts of 3D lidar measurements. It uses a graph-based approach to segment ground and objects from 3D lidar scans using a novel unified, generic criterion based on local convexity measures. Experiments show good results in urban environments including smoothly bended road surfaces.