Unequal deformation of the soil can cause deformation or damage to buildings, like tilted facades or cracks in walls. This research investigates how deformation of a building can be analyzed using Light Detection And Ranging (LiDAR) data. Cyclomedia captures LiDAR data yearly in the Netherlands making it possible to analyze either one or multiple epochs of data. If deformation is monitored, failure can be predicted, and repairs can be performed in time.

A subsiding area is found using the Dutch surface motion map. The data points of a single building are fetched from the LiDAR point cloud to analyze the following types of deformation: a difference in the torsion and tilt angle of the facade between two epochs of data; the tilt angle of the facade for a single epoch of data; and local deformation patterns on the facade. The data is segmented before computing the angles and analyzing the local deformation patterns. During segmentation, points that do not correspond to the façade (like a sunshade or windows) are removed. After segmentation, the facade is modeled by fitting a plane using Principal Component Analysis (PCA). The plane parameters (A, B, C, D) are used to determine the torsion and tilt angles. If the torsion or tilt angles are large (above a degree), it is expected the facade has deformed. Local deformation patterns can be analyzed by using a raster containing the distance of the segmented points with an accuracy of 8 centimeters. Besides the point clouds, Cyclomedia also captures 360° panoramic images (Cycloramas). These Cycloramas can be used to explain patterns that are visible in the rasters. For example, objects in front of the building like a bench or a sunshade.

This research uses Random Sample Consensus (RANSAC) to segment the data. From the results, it can be concluded RANSAC is not very predictable because random points are taken as input. So, points corresponding to the facade can be removed instead of points corresponding to windows or doors. Therefore, it is recommended to use another segmentation method for future research instead of RANSAC. Machine learning could be a good alternative to remove objects like windows and other unwanted points from the data.

Over the last decades, laser scanners are becoming more and more established for the acquisition of geo-information. Depending on the sensor platform where the laser scanners are mounted, there are MLS, ALS and TLS techniques for both indoor and outdoor environments. The high-quality 3D point clouds produced from laser scanners is an important source of 3D spatial information and it is increasingly used in a wide field of applications from engineering to medical modeling, gaming and agriculture. Although laser scanners provide dense and accurate point clouds, a scene coverage and the creation of a complete 3D representation requires multiple scans of the same area. The procedure integrating multiple scans does not always result to a perfect match. Errors that exist in the datasets or errors in the transformation of datasets create difficulties during the matching procedure. Matching data-sets with the best alignment is a topic that has been researched in many fields and a variety of methods have been analyzed for registering point clouds. A co-registration can be compared to a mathematical model and hence it is important to present not only the functional model and the set of functional relationships between the variables but also the stochastic model that describes the variability among the values and gives insights about the level of satisfying predefined demands. As a result, it becomes necessary to establish an evaluation of the output of a procedure and each result to be accompanied by its quality description. The aim of this graduation thesis is about presenting the stochastic model of a co-registration with a quality description of the result of co-registration between point clouds. The approach will be applicable to results acquired from an image-based registration and the goal is to implement a method in order to quantify the quality of the co-registered result of two different point clouds. A probabilistic analysis of the results of an image-based method results to a quantification of the quality of the output. Response images acquired from an image-based co-registration are tested and the quality indicators of precision and reliability are determined. Moreover, the shift parameter is also defined, fact that enhances the applicability of this research to co-registrations referring to big areas where multiple local registrations have to be combined in a globally consistent manner and each local result contributes to the global registration according to its quality indicators. Particularly, response images that have clearly defined peak areas and pass the tested criteria, are considered more reliable and contribute to the global registration with a greater weight. On the contrary, blurry response images, fail to satisfy the tests, are considered less reliable results and contribute with a smaller weight. The analysis of the images performed by testing the distribution of pixel values in both directions of the images. The implemented approach provides information about the precision and reliability of the images that have normally distributed values. Furthermore, by fitting a Gaussian line to the discrete pixel values, a sub-pixel accuracy of the result is achieved as values are generated in between the discrete pixels. The developed method quantifies the quality of an image-based registration but further improvements and investigation of the recommendations can also attach additional value.

In this thesis, an image-based method is proposed for solving the relative translation errors of 3D point clouds collected by Mobile Laser Scanning (MLS) techniques. The process of matching 3D point clouds is known as registration. Due to environment-depending limitations of the positioning component of MLS systems, when recording a certain scene more than once, point clouds recorded at different times tend to have mainly positioning distortions. Additionally, due to yaw-angle errors of the recording platform it is possible that the point clouds have small distortions around their Z axis or the point clouds are scanned with fuzziness. This project deals only with the translation errors. Various methods can be found in the literature to perform pair-wise registration of point clouds. Commonly, the challenge of aligning 3D features is tackled in 3D. Only a few techniques for registering point clouds in 2D have being explored. However, the approach presented in this thesis uses the attributes of the 3D points to generate and match 2D-projections, by employing a simple correlation technique instead of matching in 3D. As a result, the developed method depends more on the
number of pixels in the 2D-projections and less on the number of points in the point clouds. This leads to a more cost-efficient method in contrast to 3D registration techniques. The method uses this benefit to provide redundant translation parameters for each point cloud pair. Particularly, several images are created from each point cloud tile. The constructed images illustrate the density of the points, the intensity, the gradient of intensity, the depth, the gradient of the depth and the normal vectors of the points. As a result, the translation parameters are retrieved from the matching of various image-techniques and that is how redundant solutions are provided. Next, with the utilization of image-based evaluation criteria the reliable translation parameters are detected and only those are used to compute the final solutions. The reliable estimations are taken into account for the estimation of the final solutions. Since redundant solutions are provided, the confidence levels of each final estimation can be computed. In addition, an indication of robustness showing how many estimations where included for the computation of the final solution is included. As a result, the developed approach is capable of providing information about the precision and reliability of each pairwise registration. In such a way it is known which of the results can be used in a following step, such as a global registration. Furthermore, a 2D Gaussian elliptical fitting is used to obtain sub-pixel accuracy registration results, as the accuracy of the estimations is restricted to the pixel size of the generated images. It is proven that the developed image-based registration method has the capability to produce reliable matches when there is at least some overlap between two overlapping point clouds and corresponding objects between the point clouds are distinct in pairs of 2D projections. The technique developed for the computation of sub-pixel accuracy results seems to have potential, but further improvement is required.