Unsupervised discovery of object classes in 3D outdoor scenarios

Designing object models for a robot's detection-system can be very time-consuming since many object classes exist. This paper presents an approach that automatically infers object classes from recorded 3D data and collects training examples. A special focus is put on difficult unstructured outdoor scenarios with object classes ranging from cars over trees to buildings. In contrast to many existing works, it is not assumed that perfect segmentation of the scene is possible. Instead, a novel hierarchical segmentation method is proposed that works together with a novel inference strategy to infer object classes.