Hans-Peter Bähr

Automatic building extraction from laser scanning data: an input tool for disaster management

Estimation of damages caused by a disaster is a major task in the post disaster mitigation process. To enhance the relief and rescue operation in the affected area it is required to get a near real time damage model. For this purpose a fast method of data acquisition with suitable methods for extracting the man-made objects is required. Laser scanning data provide the height of the ground objects, which can be used for developing models to extract the man-made features in a complex urban environment. Using the height variation along the periphery of objects present in the data, a method based on standard deviation was developed to distinguish between tree and building.

Wavelet Compression and the Automatic Classification of Urban Environments Using High Resolution Multispectral Imagery and Laser Scanning Data

The field of wavelets has opened up new opportunities for the compression of satellite data. This paper examines the influence of data compression on the automatic classification of urban environments. Data from Daedalus airborne scanner imagery is used. Laser scanning altitude data is introduced as an additional channel alongside the spectral channels thus effectively integrating the local height and multispectral information sources. In order to incorporate context information, the feature base is expanded to include both spectral and non-spectral features. A maximum likelihood classification is then applied. It is demonstrated that the classification of urban scenes is considerably improved by fusing multispectral and geometric data sets. The fused imagery is then systematically compressed (channel by channel) at compression rates ranging from 5 to 100 using a wavelet-based compression algorithm. The compressed imagery is then classified using the approach described hereabove. Analysis of the results obtained indicates that a compression rate of up to 20 can conveniently be employed without adversely affecting the segmentation results.

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.

An Approach for the Detection of Damages in Buildings from Digital Aerial Information

Management procedures in general, and disaster management in particular, depend on information. The central questions are however, which information is necessary in order to draw for a particular decision, when is this information needed and at which resolution it is required. “Resolution” in this context is defined as the “level of detail”. Quality of management is thus directly related to the quality of information.