3D data classification based on mid-level geometric features

This paper introduces an approach to classify robot environments based on planar segments extracted from 3D data. In a preprocessing step, point data from a 3D range sensor is transformed to planar patches, i.e. raw data is transformed to a mid level geometric representation. This step allows for a robust, simple and straightforward feature extraction. The features are fed into a learning algorithm, resulting in binary classification into two different types of indoor environments, hallways and office spaces. The main contribution of this paper is to demonstrate the robustness of using mid-level geometric features. Tested on multiple learning algorithms with standard parameters, this approach achieves promising results.