Digital media assets depicting or otherwise representing portions of a property are captured via a media capture device, such as an unmanned vehicle, at various locations about a property. A positioning receiver tracks the location of the media capture device when each digital media asset is captured. A computing device associated with either the media capture device itself or a network-connected server automatically generates location-based categories—such as “front side” or “rear side” or “living room”—automatically based on the plurality of locations so that each location-based category is associated with multiple digital media assets and their corresponding locations.