Solid waste on the streets and socieconomic class using remote sensing

Abstract

Solid waste dumped on the streets affects human hygiene, well-being, and increases deprivation. This happens as result of a failure in the solid waste management of a city. This is especially observed in informal poorer areas. With the current increase of population in urban settlements, and especially in informal areas, new techniques are in demand to identify litter dumped on the streets in a rapid manner. In this study, aerial imagery of the city of Medellín were segmented with a k-means based algorithm and classified with a Random Forest decision tree ensemble. The results show, that with this approach garbage detection is possible with an Overall Accuracy of 82 %. Comparison with socioeconomic data from a national census on housing shows that solid waste was identified with higher shares in poorer districts. This method can be implemented at city scale and therefore might be useful for decision makers.