Abstract

There exists great demands to map out Earth’s environmental changes. The initiative Global Watch Center was initiated with the purpose of giving a global situational awareness of the premises for all life on Earth. The vast majority of Earth Observations are today collected by using satellites. By collecting, studying and analyzing vast amounts of data in an automatic, scalable and transparent way, the aims are to work towards reaching the UNs’ SDG. The initiative’s vision is to make use of qualified accessible data together with worlds’ leading organizations in order to lay the foundations of the important decisions that have the biggest potential to make an actual difference for the awaited future. As a show-case for the initiative has UN’s strategic department recommended a specific use-case, involving mapping large accumulation of waste in areas greatly affected, which they believe will profit the initiative the most. Many are today affected greatly both directly and indirectly from the consequences of large accumulations of solid-waste. Therefore does this Master Thesis aim to in an automatic and scalable way to detect and classify dumpsites in Kampala, the capital of Uganda, by using available satellite imagery. The hopes are that showing technical feasibility and presenting interesting remarks will aid in spurring further interest for coming closer to a realization of the initiative, by using existing techniques and available tools in a non-commercial fashion. The technical approach is to use a lightweight version of Automatic Target Recognition, which conventionally is used for military applications, to detect and classify features of large accumulations of solid-waste which uses techniques from the field of Image Analysis and Data Mining. Choice of data source, this study’s area of interest as well as choice of methodology for Feature Extraction and choice of the Machine Learning algorithm Support Vector Machine will all be accounted for and implemented. Since the objective is to show feasibility for the initiatives realization, will technical results will both be presented in depth and in an easily comprehensible way – regardless of technical background. Interesting remarks will have as the ambition to promote further work and contribute the initiative with valuable information for realization.