Indoor localisation methods are an essential part for the management of COVID-19 restrictions, social distancing, and the flow of people in the indoor environment. Moving towards an open work space in this scenario requires effective real-time localisation services and tools, along with a comprehensive understanding of the 3D indoor space. This project’s main objective is to analyse how ArcGIS Indoors can be used with location awareness methods to elaborate and develop space management tools for COVID-19 restrictions in order to reopen the workspace for TU Delft Campus. This was accomplished by using six Arduino micro controllers, which were programmed in C++ to scan all available Wi-Fi fingerprints in the east wing of the Faculty of Architecture and the Built Environment of TU Delft and send over the data to an ArcGIS Indoor Information Model (AIIM). The data stored on the AIIM is then accessed using the app on the user’s Android device using REST Application Programming Interface (API) where a kNN based matching algorithm then identifies the location of the user. The results show that the localisation is not consistent for rooms that are directly above each other or share common access points. However, when functioning to locate different tables inside a room, the system proved to uniquely distinguish between the specific tables. As a result, we can conclude that based on the size of the rooms, more Arduino devices should be installed to achieve an ideal accuracy. Finally, recommendations are made for the continuation of this research.@en

Point cloud data have rich semantic representations and can benefit various applications towards a digital twin. However, they are unordered and anisotropically distributed, thus being unsuitable for a typical Convolutional Neural Networks (CNN) to handle. With the advance of deep learning, several neural networks claim to have solved the point cloud semantic segmentation problem. This paper evaluates three different neural networks for semantic segmentation of point clouds, namely PointNet++, PointCNN and DGCNN. A public indoor scene of the Amersfoort railway station is used as the study area. Unlike the typical indoor scenes and even more from the ubiquitous outdoor ones in currently available datasets, the station consists of objects such as the entrance gates, ticket machines, couches, and garbage cans. For the experiment, we use subsets from the data, remove the noise, evaluate the performance of the selected neural networks. The results indicate an overall accuracy of more than 90% for all the networks but vary in terms of mean class accuracy and mean Intersection over Union (IoU). The misclassification mainly occurs in the classes of couch and garbage can. Several factors that may contribute to the errors are analyzed, such as the quality of the data and the proportion of the number of points per class. The adaptability of the networks is also heavily dependent on the training location: the overall characteristics of the train station make a trained network for one location less suitable for another.

@en