▼ 

This project develop a new method to generate breakline from the point cloud directly with the MAT. The breakline is a structured line of the object surface which has high curvature. Meanwhile, the reciprocal of the medial edge ball's radius can represent the point with high curvature, which is the fundamental idea of this project. The key parts of the method are: (a) with the help of MAT detecting candidate points having high curvature; (b) connect the candidate points to get breaklines with graph theory or polynomial fitting. The topology of the breakline is considered. In addition, this project also provides the polyline simplification and smoothing. In the resulting breakline, 27/32 are true positive. In general, the average correctness is 97% and 96%, the average quality is 90.67% and 91.19%, and the average completeness is 93.84% and 93.92% for valley and ridge. Most of accuracy parameters are above 80%. The accuracy is high. As to the precision, the average polyline precision is 0.3 and 0.23, and the average vertex precision is 1.14 meter and 1.12 meter. Comparing with the point density 2 pts/m². 25 of 27 breaklines' polyline precision is better than 0.5. 16 of 27 breakline's vertex precision is better than 1.0; and 23 of 26 is better than 1.5. The precision is also good. The source code is on Github: https://github.com/qq2012/geoflow-nodes.

Architecture, Urbanism and Building Sciences | Management in the Built Environment

Advisors/Committee Members: Peters, Ravi (mentor), Ledoux, Hugo (graduation committee), Delft University of Technology (degree granting institution).

▼ 

In recent years, there is an ever-increasing demand — both by industry and academia — for 3D spatial information and especially, for 3D building models. One of the ways to acquire such models derives from the combination of massive point clouds with reconstruction techniques, such as Ball Pivoting and Poisson Reconstruction. The result of these techniques is the representation of individual buildings or entire urban scenes in the form of surface meshes — data structures consisting of vertices, edges and faces. Despite their usefulness for visualization purposes, the high complexity of these meshes, along with various geometric and topological flaws, stands as an obstacle to their usage in further applications, such as simulations and urban planning. To address the issue of complexity, the production of lightweight building meshes can be achieved through mesh simplification, which reduces the amount of faces used in the original representations. Moreover, simplification methods focus on conforming the resulting mesh to the original one, in order to minimize the differences between the two of them. As a consequence, simple and accurate building models are possible to be acquired, whose geometric and topological validity is yet questionable. In this thesis, we introduce a novel approach for the simplification of building models, which results into a more compact representation, free of topological defects. The main characteristic of our method is structure awareness — namely, the recovery and preservation, for the input mesh, of both its primitives and the interrelationships between them (their configuration in 3D space). This awareness asserts that the resulting mesh closely follows the original and at the same time, dictates the geometric operations needed for its construction in the first place — thus providing accuracy, along with computational efficiency. Our proposed methodology is divided into three main stages: (a) primitive detection via mesh segmentation, (b) storage of primitive interrelationships in a structure graph and (c) simplification. In particular, simplification is accomplished here by approximating the primitive borders with a building scaffold, out of which a set of candidate faces is defined. The selection of faces from the candidate set to form the simplified mesh is achieved through the formulation of a linear binary programming problem, along with certain hard constraints to ensure that this mesh is both manifold and watertight. Experimentation reveals that our simplification method is able to produce simpler representations for both closed and open building meshes, which highly conform to the initial structure and are ready to be used for spatial analysis. Additionally, a fairly good approximation of a given mesh is possible to be obtained within reasonable execution times, regardless of the initial noise level or topological invalidity. Finally, a comparative analysis shows that the accuracy of our method stands in parallel with that of other available simplification techniques.

Geomatics

Advisors/Committee Members: Nan, Liangliang (mentor), Ledoux, Hugo (graduation committee), Delft University of Technology (degree granting institution).

▼ 

The use of 3D models has been rapidly expanding, finding applications in both scientific and commercial fields. One common requirement for these various applications is the geometrical and topological validity of these models. However, many models available online contain deficiencies in various forms, such as duplicated geometry, gaps in the surface, etc.. To cope with those deficiencies, a standard solution is the clean extraction of the model’s boundary, and simultaneously the model’s reconstruction in a way that its structure is valid. This thesis tackles a more generalized problem, the inside-outside classification for these models. Where many approaches might have requirements for running analysis, the methodology presented strives to robustly handle all cases. These last decades, there have been various approaches in solving the ”inside - outside classification problem”. A major attempt utilizes the winding number algorithm, in order to assign values to elements whose position is relevant to the input model. By assessing that value, a decision on whether the element in question is interior or exterior is taken. Other approaches work with casting rays, or other geometric analysis to also identify the borders of a model and segment the interior from the exterior. Also, since deficiencies inhibit the kick-starting of the necessary analysis, there are methods that try to restructure said models in order to clear any existing deficiencies. The methodology within this thesis will attempt a different approach from those that have been presented until now, which is transferring the problem from three into two dimensions. The first step is introducing a planar cross section on the area of interest. From there, through some graph reconstruction, geometric and optimization applications, a valid 1-manifold boundary of the cross-section is created. On that, the application of inside-outside classification through ray casting is possible. Assessing the results of the pipeline proves that the automated process can produce valid results, for a particular point of interest, related to an input model. The pipeline has been proven to function regardless of the cutting plane’s orientation, and can handle robustly a multitude of geometrically and topologically defective models. The results from this thesis can inspire further applications, and improvements on the pipeline can further evolve the quality of its outcome.

Geomatics

Advisors/Committee Members: Nan, Liangliang (mentor), Ledoux, Hugo (graduation committee), Delft University of Technology (degree granting institution).

▼ 

This thesis proposes a novel medial axis transform (MAT) based method to achieve visibility analysis in a point cloud. There are several advantages of this MAT based method. This method avoids surface reconstruction from a point cloud. It also works for the situation when there is surface missing in the input point cloud. For different point cloud datasets such as point cloud generated from meshes, AHN3 point cloud and point cloud generated from dense image matching, this method successfully deliver decent visibility result for all of them. The main challenge overcome in this thesis is the interior and exterior MAT separation. Two approaches, normal reorientation approach and bisector based approach are experimented in the thesis to separate MAT. The normal reorientation approach only works for point cloud generated from meshes. The bisector based approaches works for all the datasets testes. It successfully separates the interior and exterior MAT when there is surfacing missing. To speed up of the query process, spatial index is generated for interior MAT. In this thesis, two spatial indices are implemented, KD-Tree and R-Tree. Due to the limitation of my KD-Tree implementation, the KD-Tree does not improve the running speed obvious. There is a room to improve the KD-Tree implementation. The R-Tree achieves sharply improvement on running time of the queries. For 51567 points, the query based on R-Tree finished in 1880 ms. In a word, this thesis proposed an efficient MAT based method of visibility analysis in a point cloud.

Geomatics

Advisors/Committee Members: Peters, Ravi (mentor), Ledoux, Hugo (graduation committee), Delft University of Technology (degree granting institution).

▼ 

In recent years, the demand for 3D spatial information and 3D city models has increased, as they support and allow many different applications, e.g. noise simulations, energy demand estimations, and shadow analysis. Constructing a city model with 3D buildings requires elevation data (such as LiDAR or Digital Terrain Models), but unfortunately, data of sufficient quality is often unavailable. This thesis focuses on the use of machine learning methods to estimate the height of building footprints and thus bypassing the use of elevation data completely. Three different methods are tested and compared: Random Forest Regression (RFR), Multiple Linear Regression (MLR), and Support Vector Regression (SVR). A case study is performed for the conterminous United States of America (USA) because of its availability of a nation-wide building dataset, containing roughly 125 million building footprints. The high diversity in urban layouts is considered, where a distinction is made between Central Business Districts (CBDs) in cities and all other regions (e.g. suburbs and rural areas). All building footprints are characterised by nine features derived from their geometry, which are then used (in several combinations) in the model training and predicting stages. Furthermore, the influence of additional features – including census and cadastral data – on the results of the building height predictions is analysed for the city of Denver, Colorado. The experiments show that it is feasible to predict the height for all buildings in the conterminous USA in under 6 minutes. Both the MLR and SVR method even accomplish it in under 30 seconds. The height prediction results show that the different prediction models struggle to accurately estimate the height for buildings in CBDs. The lowest achieved Mean Absolute Error (MAE) is 31.81m, whereas for the suburban and rural areas it is 1.41m. Adding additional, non-geometric features (e.g. census data) to the prediction models for one city (Denver) proved to be successful; the RFR method reduced its MAE from 1.35m to 0.96m for the suburbs, achieving sub-metre accuracy. The CBDs, however, are still problematic with an MAE of 16.87m. These results show that for the suburban and rural areas, the accuracy recommendations from the CityGML specifications for LOD1 models can be met (5m limit). For the CBDs, improvement is required. The experiments also proved that the proposed methodology can be used to generate 3D city models of very large datasets if no elevation data is available. Moreover, the method is, in theory, generic enough to be applied outside the USA.

Geomatics

Advisors/Committee Members: Ledoux, Hugo (mentor), Dukai, Balázs (graduation committee), Delft University of Technology (degree granting institution).

▼ The use of 3D city models has increased the last decades due to the evolution of technology. Their use is related to the need for solutions on issues that correspond to the building environment. Modelling aspects, like geometric, semantic information and topology are necessary, in order to provide an integrated result of spatial analysis. The creation of a complete 3D city model that contains all the needed information for an application, is a time consuming and complex process. Furthermore, different 3D city model formats can contain different aspects of the same features. For example, a CityGML model can have the semantic information of a 3D object, while a Multi-View Stereo Mesh model can contain all the geometric and appearance information of the same 3D object. This thesis is documenting the possible enrichments that can be done bidirectionally between these two different 3D city model formats, when both exist for the same entities. Moreover, it presents the exploration of possible automated enrichment methodologies that can enrich each 3D city model automatically with information from the other one. Finally, an automatic bidirectional enrichment methodology is proposed and is implemented on a testing area, provided in the two different 3D city model formats. This method is based on distance computations between the meshes of the two 3D city models, used to match corresponding features, or part of features, in order to segment semantically the Multi-View Stereo Mesh model (roof, wall, road, terrain, uncertain) and transfer texture to the surfaces of the CityGML model that correspond with the surfaces of the Multi-View Stereo Mesh model. In addition, distance computations are performed for the validation of the absence of buildings and the shapes of the roofs in the CityGML model, with respect to the information given from the Multi-View Stereo Mesh model. After the implementation of the proposed methodology, it is found that both 3D city model formats can be used for the proposed enrichments of either 3D city model format. Future improvements are presented for the achievement of using existing information of different formats of 3D city models of the same entities, in order to supplement each 3D city model format with useful information, enhance the performance of spatial analysis and boost the evolution on the use of such models on real life applications. Advisors/Committee Members: Ledoux, Hugo (mentor), Peters, Ravi (graduation committee), Delft University of Technology (degree granting institution).

▼ 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. Advisors/Committee Members: Ledoux, Hugo (mentor), Diakite, Abdoulaye (mentor), Meijers, Martijn (graduation committee), Delft University of Technology (degree granting institution).

▼ 

There are several 3D city models available openly, worldwide. These models are used in various applications, from which many expects a homogeneous Level of Detail (LoD). Validating the accuracy of the LoD of a model requires the inference its LoD class and its conformance to the real-world object. This process quickly becomes infeasible for large models when done manually. Yet there is no automatic method for LoD inference and validation. Therefore the thesis proposes a method to automatically infer the geometric LoD (LoD0-2.3) in 3D city models. A central aspect of this work is the use of machine-learning to classify building models based on their LoD. It follows the assumption that a process is possible where a classifier trained in a synthetic 3D city model containing all LoD classes, and applied in real city model. Therefore ten geometry measures (features) are computed from the objects and tested with six classification algorithms. The six experiments the transferability of a classifier from the synthetic city model to the real one, multi-class (LoD0-2.3) and binary (LoD2 or not) classification, and the effect of LoD class imbalance by introducing various amounts of LoD1 objects into the LoD2 model. Furthermore, by using a point cloud as ground truth, this explored the possibility of validating the inferred LoD classes. The results indicate that the classifier is not transferable to the real data set when trained on the synthetic city model, which is probably due to the significant difference in object shapes between the two models. Binary classification outperforms the multi-class case and it is favourable for LoD validation where the main question is whether the model conforms the stated LoD or not. Finally, class-imbalance can reduce the classification with as much as 20%.

Geomatics

Advisors/Committee Members: Biljecki, Filip (mentor), Ledoux, Hugo (graduation committee), Labetski, Anna (graduation committee), Lopes Gil, Jorge (graduation committee), Delft University of Technology (degree granting institution).

▼ 

3D reconstruction of the built environment is a widely studied Geomatics topic. Resulting city models are used for a great variety of purposes. The reconstruction of roofs remains challenging. These roofs are not only building blocks for the city models but are of direct interest as well. The company READAAR uses roof segments for the detection of asbestos and PV potential analysis. Typical clients for such analysis are muncipalities and provinces. Currently, READAAR extracts roof segments from the gridded LiDAR dataset: algemeen hoogtebestand nederland 2 (AHN2). The use of LiDAR data however comes with some limitations. Most importantly, outside the Netherlands, LiDAR data is not always available as it is relatively expensive to gather. Furthermore, the point density of the AHN is 6-10 points/m², which limits the amount of detail that can be extracted. In the Netherlands countrywide aerial stereo imagery is available at a resolution of 10cm, this potentially gives a point density of 100 points/m² after image matching. This research explores the possibilities of using aerial stereo imagery instead of LiDAR data for the efficient large-scale extraction of 3D roof segments. A workflow is designed in which stereo matching and extraction of segments are integrated. This makes the workflow both efficient and easily scalable. Roof segments are extracted in two steps. First, a watershed segmentation is applied to retrieved color segments. Second, these color segments are clustered based on their orientation. The resulting roof segments generally have a higher quality than the segments retrieved with READAARs LiDAR-based approach. However, problems do occur, especially in shaded areas. This could possibly be solved by integrating LiDAR data when available. Another recommendation for future research is improving the matching by using multi-view matching or possibly neural networks. Furthermore, the segmentation could potentially be improved by using multiple images from different years and processing building blocks.

Geomatics

Advisors/Committee Members: Ledoux, Hugo (mentor), Commandeur, Tom (mentor), Nourian, Pirouz (graduation committee), Delft University of Technology (degree granting institution).

▼ 

To obtain 3D information of the Earth’s surface, airborne LiDAR technology is used to quickly capture high-precision measurements of the terrain. Unfortunately, laser scanning techniques are prone to producing outliers and noise (i.e. wrong measurements). Therefore, a pre-process of the point cloud is required to detect and remove spurious measurements. While outlier detection in datasets has been extensively researched, in 3D point cloud data it is still an ongoing problem. Especially, clustered outliers are hard to detect with previous local-neighborhood based algorithms. This research explores the possibilities of using a voxel-based approach to automatically remove outliers from aerial point clouds. A workflow is designed in which a series of voxel-based operations are integrated, with the aim to detect all types of outliers and minimize false positives. Voxels can be processed more efficiently than 3D points for two reasons: (1) A voxelgrid can be analyzed using efficient image processing techniques; (2) Voxels group inner points before feature extraction using neighborhood operators. Outliers are detected in two steps. First, the source point cloud is voxelized. Secondly, outliers are detected by computing connected components and labeling voxels not connected to the largest region as outliers. Simultaneously, analysis of the point’s local density, shape (planar) and intensity minimize classification of false positives. The presented algorithm generally detects outliers with a higher accuracy than previous local neighborhood-based methods. A comparison with an existing approach shows that more outliers are detected. Above all, clustered outliers are removed. However, some issues can still be improved. First, more research is necessary to classify outliers based on non-arbitrary decisions. This could potentially be improved by introducing supervised learning algorithms. Secondly, more attention is required to process massive point clouds that do not fit in internal memory. This study proposes a possible streaming solution.

Geomatics

Advisors/Committee Members: Peters, Ravi (mentor), Ledoux, Hugo (mentor), Meijers, Martijn (graduation committee), Delft University of Technology (degree granting institution).

▼ 

Automatically generated 3D city models are becoming less of a futuristic, demanding or even impossible to attain goal, and more of a necessary, or vastly sought after, means for a multitude of applications. The current prevalence of open geographic information, such as nationwide-covering LiDAR datasets in the Netherlands, opens up opportunities for different parties to experiment in a search for solutions based on LiDAR data. A current approach in answering this demand for 3D city models is 3dfier, which is an ongoing project to automatically generate, disseminate and maintain a 3D city model based on open source airborne LiDAR datasets as a main source. Trees are currently not included in the 3D city models generated by 3dfier, while trees are an integral part of any city landscape. In this thesis, an implementation is developed that goes through multiple stages of the construction of 3D tree models. First, an initial classification method of the available LiDAR point cloud data is done. This results in a new intermediate point cloud that consists of mostly points belonging to trees. These classified tree points need to be segmented, such that each segment consists of a group of points that represent a single tree. A second classification is constructed after the segmentation, which is called data cleaning. This step ensures that every segment that consists of tree points, is checked for misclassifications and outliers and that these are removed. After cleaning every segment, tree models can be constructed in various LODs and additionally, the types of trees are classified based on identifying features of these trees. The conclusions of this research are that it is possible to construct 3D tree models based on airborne LiDAR point cloud data and that these can be made to fit in an existing 3D city model. This is demonstrated by creating a 3D city tree model for an existing 3D city model and merging them into one dataset. While further work is required to achieve a seamless fit, the integrated results show that the datasets complement each other well.

Geomatics

Advisors/Committee Members: Ledoux, Hugo (mentor), Stoter, Jantien (graduation committee), Commandeur, Tom (graduation committee), Delft University of Technology (degree granting institution).