On-line data registration in OUTDOOR environment

Abstract

In the paper an algorithm of 3D data registration based on CUDA implementation is shown. The research is related to the problem of collecting 3D data with laser measurement system mounted on rotated head, to be used in mobile robot applications. Assumed performance of data registration algorithm is achieved, therefore it can used as On-line. The ICP (Iterative Closest Point) approach is chosen as registration method. Computation is based on massively parallel architecture of NVIDIA CUDA. The presented concept of 3D data matching is based on parallel computation used for fast nearest neighbor search. Nearest neighbor search procedure is using 3D space decomposition into cubic buckets, therefore the time of matching is deterministic.