Embodiments relate to systems, devices, and computer-implemented methods for performing automated visual surveillance by obtaining video camera coordinates determined using video data, video camera metadata, and/or digital elevation models, obtaining a surveillance rule associated with rule coordinates, identifying a video camera that is associated with video camera coordinates that include at least part of the rule coordinates, and transmitting the surveillance rule to a computing device associated with the video camera. The rule coordinates can be automatically determined based on received coordinates of an object. Additionally, the surveillance rule can be generated based on instructions from a user in a natural language syntax.