Unsupervised Discovery of Object Classes in 3D Outdoor Scenarios
IEEE International Conference on Computer Vision Workshops Proceedings, 2011.
13th International Conference on Computer Vision (ICCV), 1st IEEE Workshop on Challenges and Opportunities in Robot Perception, Barcelona, November 12, 2011
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.