Uwe Weidner

Towards automatic building extraction from high-resolution digital elevation models

This paper deals with an approach for extracting the 3D shape of buildings from high-resolution Digital Elevation Models (DEMs), having a grid resolution between 0.5 and 5 m. The steps of the proposed procedure increasingly use explicit domain knowledge, specifically geometric constraints in the form of parametric and prismatic building models. A new MDL-based approach generating a polygonal ground plan from segment boundaries is given. The used knowledge is object-related making adaption to data of different density and resolution simple and transparent.

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.

Digital Surface Models for Building Extraction

This paper describes an approach to building extraction using Digital Surface Models (DSM) as input data. The approach consists of building detection and reconstruction using parametric and prismatic building models. The main focus is on the extraction of roof structures, an extension of the previously published work, as first step towards the extraction of polyhedral building descriptions in order to also allow the extraction of complex buildings.

Classification in High-Dimensional Feature Spaces—Assessment Using SVM, IVM and RVM With Focus on Simulated EnMAP Data

Support Vector Machines (SVM) are increasingly used in methodological as well as application oriented research throughout the remote sensing community. Their classification accuracy and the fact that they can be applied on virtually any kind of remote sensing data set are their key advantages. Especially researchers working with hyperspectral or other high dimensional datasets tend to favor SVMs as they suffer far less from the Hughes phenomenon than classifiers designed for multispectral datasets do. Due to these issues, numerous researchers have published a broad range of enhancements on SVM. Many of these enhancements aim at introducing probability distributions and the Bayes theorem. Within this paper, we present an assessment and comparison of classification results of the SVM and two enhancements-Import Vector Machines (IVM) and Relevance Vector Machines (RVM)-on simulated datasets of the Environmental Mapping and Analysis Program EnMAP.

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.

Segment-based characterization of roof surfaces using hyperspectral and laser scanning data

Using remote sensing for urban applications makes high demands on the resolution of the used data - not only concerning its geometric resolution, in terms of ground sampling distance, but also concerning the spectral resolution, in terms of the number of narrow bands, allowing an almost continuous representation of the spectrum. In order to deal with the vari- ability and number of different surface materials with sometimes quite similiar spectral properties, hyperspectral data with its high spectral resolution seems to be mandatory for applications depending on classification of urban surface materials. A recent project of the Chair of Water Chemistry, Engler-Bunte-Institute (EBI), and the Institute of Photogrammetry and Remote Sensing (IPF) - both University of Karlsruhe - aims at the quantitative assessment of pollutants on urban surfaces by chemical analysis and image processing methods. Our research focus at IPF is the characterization of roof surfaces by combined use of hyperspectral and laser scanning data using a segment-based approach. The laser scanning data is primarily used for geometric characterization of the roof patches, but also in combination with the hyperspectral data for material classification. The hyperspectral data already gives rich information about the material, nevertheless the geometry of the roof surface restricts the possible material classes and therefore eases discrimination of materials with almost similar spectra. I. INTRODUCTION The assessment of pollutants on urban surfaces and their impact on the pollution load in rain runoffs is a small, but nevertheless important topic in the assessment of the influence of human activity on the status of surface waters and groundwater. Thus, the aim of our research project is not only to derive information on the amount of sealed surfaces in an urban area, but to derive a detailed surface material map. The necessary classes for our application are identified based on chemical measurements on reference roof surfaces, observing that different roof constructions/materials may have similar polluting behaviour. This allows merging of classes with respect to the resulting pollution, although they may have different spectral properties. One example are those material combinations including a bitumen layer and a covering layer from stone materials. The pure material-spectra-oriented clas- sification (cf. (1)) is in our approach supported by geometric clues of surface patches, thus combining geometric data from laser scanning and hyperspectral data for the characterization of roof segments. In the following, we give a short overview on related work. Section III introduces the input data. Our approach for the characterization of roof surfaces in urban areas is presented in Section IV. Recent results as well as a quantitative evaluation follow in Section V, finalized by the conclusions. II. RELATED WORK Laser scanning and hyperspectral data are often used exclu- sively, either to derive the geometry based on laser scanning data (cf. (2)) or to derive material maps based on hyperspectral data (cf. (1)). (3) use hyperspectral data (AVIRIS) in order to improve reconstruction results based on IFSAR, namely to mask vegetation areas, but the used data has only limited geo- metric resolution. In (4), they present results of hyperspectral data analysis for urban areas based on ROSIS and DAIS data, also discussing the impact of spectral and geometric resolution. (5) integrate Digital Surface Model (DSM) information in or- der to improve the results of hyperspectral classification based on HYDICE data. In their research the DSM, derived from aerial imagery, is applied for the discrimination of roofs and ground surfaces. The materials may have a similar spectrum, but they can be discriminated based on the height information. (6) show material mapping techniques based on deterministic similarity measures for spectral matching to separate target from non-target pixels in urban areas.

Support vector machines, import vector machines and relevance vector machines for hyperspectral classification — A comparison

Support Vector Machines (SVM) have gained increasing attention due to their classification accuracy, robustness and indifference towards the input data type. Thus, they are widely used in the remote sensing community — and especially among researchers working on hyperspectral datasets. However, since their first publication a lot of enhancements and adaptations have been proposed, many of which aim at introducing probability distributions and the Bayes theorem to SVM. Within this paper, we present a classification result of a HyMap dataset using two of the proposed enhancements — Import Vector Machines and Relevance Vector Machines — and compare them to the Support Vector Machine.

Design of a Spectral–Spatial Pattern Recognition Framework for Risk Assessments Using Landsat Data—A Case Study in Chile

For many ecological applications of remote sensing, traditional multispectral data with moderate spatial and spectral resolution have to be used. Typical examples are land-use change or deforestation assessments. The study sites are frequently too large and the timespan covered too long assumes the availability of modern datasets such as very high resolution or hyperspectral data. However, in traditional datasets such as Landsat data, separability of the relevant classes is limited. A promising approach is to describe the landscape context pixels that are integrated. For this purpose, multiscale context features are computed. Then, spectral-spatial classification is employed. However, such approaches require sophisticated processing techniques. This study exemplifies these issues by designing an entire framework for exploiting context features. The framework uses kernel-based classifiers which are unified by a multiple classifier system and further improved by conditional random fields. Accuracy on three scenarios is raised between 19.0%pts and 26.6%pts. Although the framework is designed, focusing an application in Chile, it is generally enough to be applied to similar scenarios.

Parameterfree information-preserving surface restoration

In this paper we present an algorithm for parameterfree information-preserving surface restoration. The algorithm is designed for 2.5D and 3D surfaces. The basic idea is to extract noise and signal properties of the data simultaneously by variance-component estimation and use this information for filtering. The variance-component estimation delivers information on how to weigh the influence of the data dependent term and the stabilizing term in regularization techniques, and therefore no parameter which controls this relation has to be set by the user.

Information-preserving surface restoration and feature extraction for digital elevation models

Preprocessing such as filtering data in order to remove or at least reduce noise is a crucial step because information which is lost during this filtering cannot be recovered in subsequent steps. It is a well-known fact, that linear filtering does not only reduce noise, but may also lead to a loss of information due to the global smoothing, regardless of structures in the data. In order to overcome these drawbacks, we propose using an algorithm for parameter free information- preserving surface restoration. As we do not want to evaluate the results of the filtering only qualitatively by visual inspection, we examine the influence of pre-processing on feature extraction for digital elevation models and discuss quantities for the evaluation of these influences.