Towards Object Classification Using 3D Sensor Data

This paper presents an approach to classify objects using 3D sensor data and an evolutionary algorithm. An important by-product of this classification is, that additionally certain properties and the pose in space of this object are determined. The reproductive perception paradigm is used utilizing an evolutionary strategy. Two sub-approaches are discussed using different representations of the 3D data. The first one uses depth images while the second one uses point clouds stored in a special octree. The approaches will be demonstrated in experiments with simulated and real data.