Spatio-Temporal Modeling in Video and Multimedia Geographic Information Systems

The geographic application domain includes important information such as design plans, record drawings, photographs, and video data records. The corresponding geographic information systems (GISs) should maintain a specific model for each geographic data modality such as geographic video model for video records. Real-time 3-D geographic information systems provide comprehensive interface to complex and dynamic databases and truly immersive capability for visualizing geographic data. In cases, where information about location of geographic objects is needed at different moments of time, a GIS should process video data that is directly manipulated and retrieved through representation of its spatio-temporal characteristics. In this context, the most advanced multimedia form—digital video, finds an efficient application in GIS for versatile specification of geographic data. In this paper, a model for spatial data evolving with time is introduced in the context of video data manipulation. We designed a model that represents the spatio-temporal continuum among geographic objects in geographic video sequences, or digital video. The model developed here was motivated by the requirements for manipulating, managing, and analyzing geographic data for the necessities of infrastructure management, urban and regional planning, hazard prevention and management, transportation networks, vehicles routing, etc. This model allows the important issues for GIS such as conditions of adjacency (what is next to what), containment (what is enclosed by what), and proximity (how close one geographic object is to another) to be determined. Our model describes the spatial relationships among objects for each key frame in a given video scene, and the temporal relationships of the temporal intervals measuring the validity duration of the spatial relationships spanning over the given key frame. One of the main GIS issues—distance estimation, is solved as quantitative metrics of geographic objects in digital video are easily and precisely specified. This model is a basis for annotation of raw video for subsequent use in geographic video databases and digital libraries that provide access to and efficient storage of large volume of geographic data.