Politz - Research Projects

Laser Scanning

  • 3D object extraction of high-resolution 3D point clouds
    National Survey Departments acquire area-wide, controlled airborne laser scanning (ALS) datasets with different point densities, which are at least classified into ground and non-ground points. The Working Committee of the Surveying Authorities of the Laender of the Federal Republic of Germany (AdV) is discussing about an update cycle of 10 years for ALS point clouds. The national survey departments also acquire 3D point clouds from aerial images every 2-3 years with high overlapping ratios using a method called Dense Image Matching (DIM). Those DIM point clouds have a high point density, which is equal to the original aerial image resolution. In addition, those DIM point clouds also contain radiometric information from the aerial images, but only reconstruct the surface due to image correlation. This project is split into four distinctive topics.
    Team: Politz, Sester
    Year: 2017
    Sponsors: Forschungs- und Entwicklungsvorhaben zwischen den Landesvermessungsämtern Niedersachsen, Schleswig-Holstein und Mecklenburg-Vorpommern

Bachelor Theses

  • Transformation of point clouds using Generative Adversarial Networks
    The goal of this thesis is to transform a DIM point cloud this way that it behaves like an ALS point cloud for the following processing steps. Firstly, both point clouds are rasterized, where each raster cell describes the distribution in height for all points within a raster cell. These rasterized images from both point clouds are then used to train a Generative Adversarial Network (GAN) such as the pix2pix network. The network outputs transformed height distributions, which can be back-projected to the original point clouds. Finally, those transformed point clouds can then be tested on different processing steps such as registration, change detection or classification.
    Team: Politz, Sester
    Year: 2019
  • Registration of point clouds using Least Squares Adjustment
    The goal of this thesis is to determine global transformation parameter for point cloud tiles or individual flight stripes using the information of local transformation parameters. The local transformation parameters should be derived using least square adjustment considering the different attributes of ALS and DIM point clouds. The quality of those local transformations should be used to weight the observations in a global alignment over a region, which will consequently return stable and uniform global registration parameters and thus will be able to support tiles with weak local transformation results.
    Team: Politz, Brenner
    Year: 2019
  • Registration of point clouds using segments
    The goal of this thesis is to develop different methods, which should register point clouds using segments. The registration on 2D- as well as on 3D-level should be investigated.
    Team: Politz, Brenner
    Year: 2019

Master Theses

  • Robust registration of airborne point clouds
    Goal of this thesis is the robust registration of airborne point clouds, which are derived from Airborne Laser Scanning (ALS) and Dense Image Matching (DIM). We implemented a coarse, translative registration method using a Maximum Consensus Estimator and compared our results with a standard ICP. In addition, we tested several methods to prune object points from point clouds, which are represented differently in both point cloud types.
    Leaders: Politz, Brenner
    Team: Jannik Busse
    Year: 2019
  • Optimal assignment of point clouds using deep learning
    The main goal of this master thesis was to register airborne 3D point clouds from different sensor systems. These point clouds are derived from airborne laser scanning (ALS) and dense image matching (DIM) of aerial images. Those point clouds may cover the same surface, but do contain different attributes and characteristics. One major problem when dealing with those two point clouds is vegetation. The laser beam in ALS is able to penetrate vegetation leading to ground and vegetation points in the final point cloud. Since they are derived from aerial images, DIM point clouds only contain the surfaces and thus describes the treetops. This major difference between ALS and DIM causes problems for the registration of point clouds and established algorithms such as the iterative closest points (ICP) algorithm are facing issues when dealing with both point cloud types at the same time, because they assume that similar points are close to each other.
    Leaders: Brenner, Politz
    Team: Stephan Niehaus
    Year: 2019
  • Transformation of point clouds using Generative Adversarial Networks
    The goal of this thesis is to transform a DIM point cloud this way that it behaves like an ALS point cloud for the following processing steps. Firstly, both point clouds are rasterized, where each raster cell describes the distribution in height for all points within a raster cell. These rasterized images from both point clouds are then used to train a Generative Adversarial Network (GAN) such as the pix2pix network. The network outputs transformed height distributions, which can be back-projected to the original point clouds. Finally, those transformed point clouds can then be tested on different processing steps such as registration, change detection or classification.
    Team: Politz, Sester
    Year: 2019
  • Registration of point clouds using Least Squares Adjustment
    The goal of this thesis is to determine global transformation parameter for point cloud tiles or individual flight stripes using the information of local transformation parameters. The local transformation parameters should be derived using least square adjustment considering the different attributes of ALS and DIM point clouds. The quality of those local transformations should be used to weight the observations in a global alignment over a region, which will consequently return stable and uniform global registration parameters and thus will be able to support tiles with weak local transformation results.
    Team: Politz, Brenner
    Year: 2019
  • Registration of point clouds using segments
    The goal of this thesis is to develop different methods, which should register point clouds using segments. The registration on 2D- as well as on 3D-level should be investigated.
    Team: Politz, Brenner
    Year: 2019