The seismic building structural type (SBST) reflects the main load-bearing structure of a building and therefore its behaviour under seismic load. For numerous areas in earthquake prone regions this information is outdated, unavailable, or simply not existent. Traditional methods to gather this information, such as building-by-building inspections, are costly and highly time-consuming, making them unfeasible for assessing large building inventory. For this reason, the use of remote sensing data has been proposed to allow a fast acquisition of relevant building information on urban and regional scale. Subsequently, machine learning algorithms may be used to analyse the gathered data, e.g. to classify a building stock into groups with similar seismic behaviour. This thesis investigates into such an approach for the building stock of Groningen in the Netherlands. Our focus lies on the extraction of detailed geometric information from a point cloud gained by aerial laser scanning. We thereby follow the assumption that similar structural systems and materials can be inferred from geometric similarities. To describe the geometric shape of a building we apply Shape DNA, a spectral shape descriptor based on the eigenvalues of the Laplace-Beltrami operator. In a first experiment on a synthetically generated building stock we succeed in predicting the roof type of different buildings with accuracies above 80%, only relying on the Shape DNA. The experiment shows promising results, however, further research is necessary in order to explore the usability on real building data. In a second experiment we use a sample of buildings from the Groningen building stock. Here we can automatically predict detailed SBST information, such as the type of lateral load resisting system, with accuracies above 80% only by taking a buildings footprint area and year of construction into account. (see thesis document for extended abstract)

With fast development of both hardware and software, 3D real-world scene
data, for example multi view stereo mesh, can be acquired efficiently. And
since 3D city data are more realistic and more useful in some applications,
they begin to appear in the market.
Although the generation of 3D city data like multi view stereo mesh
can be fast, the data might contain many measurement errors. Because
of these measurement errors, some regular objects such as building, ground
etc sometimes are not exactly flat. Points which should be on the same
plane have small deviations from the plane they belong to, which makes the
flat surface bumpy. One way to solve this problem is to control the quality
of data acquisition and data processing. Unfortunately, even the data error
sources are known, it is not possible to eliminate all the errors, and accurate
but expensive data acquisition equipment sometimes are not affordable. In
that case, processing existing data is much more economic and time saving
compared with collecting data again.
This MSc thesis aims at solving above problem. It provides a methodology
on straightening planar parts of multi view stereo mesh of the city. After
straightening the mesh, this thesis also tries to simply the mesh by removing
redundant vertices and faces in the mesh, so that the data will be clean and
the data storage can be reduced.