Increasing the precision of reconstructed 3D model of indoor robot environment by elimination of problematic points1

In the process of reconstructing the 3D environment from the point cloud acquired from 3D laser the main objective is to obtain the model that is as precise as possible. Reconstruction algorithms greatly rely on the input data precision. Unfortunately, the point clouds regularly contains points that are problematic for the reconstruction. They are mostly associated with the reflection of laser beams off the semi–transparent surfaces, e.g. windows. This paper proposes the method for eliminating such points based on K–means clustering in order to increase the accuracy of the reconstructed 3D model.