In 2017 the Netherlands had 7146km of railways [Ramaekers et al., 2009], which are owned and managed by ProRail and have to be frequently surveyed, for quality inspection. Surveying is done using a variety of surveying techniques, many of which require surveyors to walk on or near the tracks, which could cause injuries. An alternative surveying technique would be photogrammetry using images acquired with a camera mounted on a drone. In this technique a 3D point cloud is constructed out of images, which is georeferenced using GPS measurements on the drone and Ground Control Points (GCP). The positions of the rail rods can then be found by modelling the rail rod using the point cloud. The quality of the point cloud, defined here as a combination of accuracy, precision, point density, completeness, and the rail rod feature detectability, is an important factor in deciding if photogrammetry is a sufficient surveying technique for this project.

In this research the influence of the distance between the camera and the track, the baseline, and the number and spread of GCPs on the quality of the resulting point cloud. The distance to the track was set to 25, 30 and35m and the baseline was varied between 2 and 10m. The requirement set for the accuracy is 15mm, while the precision has to be below 10mm. For the point density an K-nearest neighbors (K-nn) of at least 10 is required, the completeness requires less than 10% missing cells and finally the feature detectability requires that at least once every 2m the location of the rail can be determined. The features are detected using a 2D model of the rail that is fitted in a flattened slice of the point cloud using a modified version of the iterative closest point algorithm.

It is shown that the accuracy and precision are influenced by the distance and baseline, but no clear relation was found, while the accuracy improves when using GCPs. For the point density it is shown that increasing the distance between the camera and the track linearly decreases the point density, while the baseline has no impact and for the completeness a decreasing trend was found when increasing the baseline, while no relation could be found between the completeness and the distance between the camera and the track. For the rail rod feature detectability it was shown that the percentage of accurately found rail rod positions goes down when increasing the distance to the track and the baseline. Overall it is proven that when using a 100MP camera, 5 GCPs, a distance of 25m, and a baseline of 2.17m the rail rods could be surveyed so that the requirements set for this research were met.

During World War II West Papua was the scene of war between the Axis and the Allies. In this case, it was the Japanese on one side Australian and US forces on the other. After the war a lot of equipment was left in the jungle and because of the low population density on the island some material can still be found to this day. Planes and vehicles that were abandoned far enough from villages were able to withstand the test of time and are still hidden under the trees. In November 2018 an expedition force is heading to the island to find some of these planes. This assignment was meant as a preparation for that expedition and it was my job to find places that could be interesting to investigate closer in the field. The research question that had to be answered was as follows: is it possible to classify and link historical data to modern data. To do this I looked at old aerial photographs of the airports, and at modern Sentinel-2 and Landsat multispectral images of the area. The aerial photographs are stitched into a panorama and geolocated so that the coordinates were known. Next features like the average and gradient of surrounding pixels are computed so the image could be classified. Classifications were then performed on the panoramas and on the Landsat 8 dataset in order to create a map of the region of interest and possibly point out potential war equipment locations. The Landsat data was also used to create a heatmap to show the warmest spots in the region. These spots could potentially point to material that is warmer than its surroundings, e.g. a metal car in a grass field that has been standing in the sun for some time. The classification of the panoramas proved to be a difficult task and the final result leaves much to be desired. The classification of the Landsat 8 dataset went better and the results show a useable map. However the most interesting class in this case was the war equipment class, which cannot be validated. The heatmap could mostly be used to highlight the roads, but there are certain spots that light up and cannot be explained without field data. These spots might be interesting to check out during the expedition.