Ansgar Brunn

Hierarchical Bayesian nets for building extraction using dense digital surface models

Abstract During the last years an increasing demand for 3D data of urban scenes can be recognized. Techniques for automatic acquisition of buildings are needed to satisfy this demand in an economic way. This paper describes an approach for building extraction using digital surface models (DSM) as input data. The first task is the detection of areas within the DSM which describe buildings. The second task is the reconstruction of geometric building descriptions. In this paper we focus on new extensions of our approach. The first extension is the detection of buildings using two alternative classification schemes: a binary or a statistical classification based on Bayesian nets, both using local geometric properties. The second extension is the extraction of roof structures as a first step towards the reconstruction of polyhedral building descriptions.

Statistically Testing Uncertain Geometric Relations

This paper integrates Statistical reasoning and Grassmann-Cayley algebra for making 2D and 3D geometric reasoning practical. The multi-linearity of the forms allows rigorous error propagation and Statistical testing of geometric relations. This is achieved by representing all objects in homogeneous coordinates and expressing all relations using Standard matrix calculus.1

A hybrid concept for 3D building acquisition

This paper presents a hybrid concept of interaction between scene and sensors for image interpretation. We present a strategy for 3D building acquisition which combines different approaches based on different levels of description and different sensors: the detection of regions of interest, and the automatic and semi-automatic reconstruction of object parts and complete buildings.

Model-Based 2D-Shape Recovery

The paper presents a new approach for the reconstruction of polygons using local and global constraints. The MDL-based solution is shown to be useful for analysing range and image data of buildings.

A Procedure for Segmenting Surfaces by Symbolic and Iconic Image Fusion

This paper deals with the derivation of a symbolic surface description exploiting the information of multiple images while using a minimum of domain knowledge. We present a new concept for segmenting surfaces by fusing multiple images both on the iconic and on the symbolic description level. In a first step a local 3D-reconstruction and interpretation is derived based on the result of a polymorphic feature ex-traction. It serves as prior information for a second step which refines the initial segmentation using the radiometric image content. Examples of the proposed procedure are presented for the application of 3D-building reconstruction from aerial images.