Development of an object-oriented classification model using very high resolution satellite imagery for monitoring diamond mining activity

Very high resolution (VHR) Ikonos images were analysed to assess the state of activity of a diamond mine extraction site in Africa. The methodology uses a dynamic approach, based on an object-oriented classification of two sets of satellite remote sensing data that were acquired four months apart. The data was processed according to a supervised maximum likelihood classification system, using fuzzy sets of membership functions. Additionally, field information gathered from experts in the sector of diamond mining was used. The results confirm the usefulness of VHR satellite imagery for the identification of both artisanal and industrial diamond mining. The bi-temporal dataset allows information on the evolution of the activity to be derived during a first period.