In the second half of the 20th and beginning of the 21st century the amount of natural disasters has increased rapidly. Due to this rise in occurrences, more people are affected. An important indicator for people affected is the amount of damage to buildings. To gather this information aid workers now have to go into the field to gather data on the amount of destruction. In response to the possible dangers these people encounter in the field, remote sensing and analysis techniques have been developed for automated damage detection. However, due to various limitations on the implementation, these techniques are not yet widely adopted in emergency response and humanitarian aid. This work compares two methods and two data sources for the detection of building damage. The methods are evaluated on their accuracy and implementability within humanitarian aid in disaster situations. The main methods considered are equalisation of histograms of pre-event and post-event imagery, followed by Univariate Image Differencing; and a convolutional neural network on features withdrawn from post-event imagery, using OpenStreetMap data. Remotely sensed data sources considered are synthetic aperture radar and very high resolution optical imagery. All results are analysed and compared to current standards in damage detection. From the results it can be concluded that more research is required for a practical implementation of deep learning techniques. The constraint posed by the requirement of large datasets, make these methods impracticable without sufficient preparation and resources. More simpler methods, like Univariate Image Differencing, can be validated on smaller ground-truth datasets, and are therefore easier in implementation when resources are limited. The possible accuracy increase of deep learning methods does, at this moment, not outweigh the ease of an elementary differencing approach.

Along with the rise of the smart city movement, Internet of Things is an upcoming phenomenon. Objects and devices are becoming more and more wirelessly interconnected, communicating information between themselves and to human beings. As an extension on static sensor networks that gather real-time environmental data, the feasibility of implementing a dynamic sensor network based on LoRa communication is researched. To achieve such a dynamic system, a self-developed sensor platform was constructed, based on the microcontroller LoPy. Sensors attached to it include a hygrometer, thermometer and microphone. The emphasis of the research was on localisation of the sensors, to put the gathered sensor data into geographical context. A WiFi fingerprinting radiomap was constructed based on available MAC-addresses, their signal strengths, and GPS coordinates. The GPS module was only used for composing the radiomap. When the radiomap is completed, the module can be switched off, only to be switched on for periodical updates of the radiomap. The quality of the radiomap methodology was evaluated by constructing it of measurements gathered in four days, and testing it for the remaining three days. This test gave a correctness of 50% while another 38% of measurements were localised in a neighbouring cell. The correctness can be improved by having a longer training period. The quality of the collected sensor data turned out to be dependent on the weather conditions and the placement location on the carrier vehicle. Vehicle requirements were specified as driving through the city centre and having a schedule and route producing as little noise, heat and air pollution as possible. Another topic of research was LoRa communication, which was deemed as very limited for dynamic implementations, as the sending of location-related data takes up a large part of the already limited message size. To decrypt the sent message and store it in a meaningful database, Node-RED was used. Despite visualisation of measurements showed promising results, there is margin for improvement as far as data capturing is concerned.