Mine sites are routinely required to rehabilitate their post-mining landforms with a safe, stable and sustainable land-cover. To assess these post-mining landforms, traditional on-ground field monitoring is generally undertaken. However, these labour intensive and time-consuming measurements are generally insufficient to catalogue land rehabilitation efforts across the large scales typical of mining sites (>100 ha). As an alternative, information derived from Unmanned Aerial Vehicles (UAV) can be used to map rehabilitation success and provide evidence of achieving rehabilitation site requirements across a range of scales. UAV based sensors have the capacity to collect information on rehabilitation sites with extensive spatial coverage in a repeatable, flexible and cost-effective manner. Here, we present an approach to automatically map indicators of safety, stability and sustainability of rehabilitation efforts, and demonstrate this framework across three coalmine sites. Using multi-spectral UAV imagery together with geographic object-based image analysis, an empirical classification system is proposed to convert these indicators into a status category based on a number of criteria related to land-cover, landform, erosion, and vegetation structure. For this study, these criteria include: mapping tall trees (Eucalyptus species); vegetation extent; senescent vegetation; extent of bare ground; and steep slopes. Converting these land-cover indicators into appropriate mapping categories on a polygon basis indicated the level of rehabilitation success and how these varied across sites and age of the rehabilitation activity. This work presents a framework and workflow for undertaking a UAV based assessment of safety, stability and sustainability of mine rehabilitation and also provides a set of recommendations for future rehabilitation assessment efforts.