In recent years, the technological improvements of low-cost small-scaleUnmanned Aerial Vehicles (UAVs) are promoting an ever-increasing use of them indifferent tasks. In particular, the use of small-scale UAVs is useful in allthese low-altitude tasks in which common UAVs cannot be adopted, such asrecurrent comprehensive view of wide environments, frequent monitoring ofmilitary areas, real-time classification of static and moving entities (e.g.,people, cars, etc.). These tasks can be supported by mosaicking and changedetection algorithms achieved at low-altitude. Currently, public datasets fortesting these algorithms are not available. This paper presents the UMCDdataset, the first collection of geo-referenced video sequences acquired atlow-altitude for mosaicking and change detection purposes. Five referencescenarios are also reported.
展开▼
