Hiroaki Uchiyama

Picture Context Capturing for Mobile Databases

A sensor-based camera system associates picture contents with the captured environment to enable semantic content retrieval, interaction, and visualization.

Semantic maps and mobile context capturing for picture content visualization and management of picture databases

Modern cameras are powerful devices that can interoperate using international standards with other sensors that can capture the context of each picture taken. Future cameras are expected to integrate such sensors within them. The contextual parameters captured can be interpreted with the help of semantic maps which are maps that integrate semantic information on them. Semantic maps can be used for understanding and visualization of the picture contents as well as for the management of context and content in picture databases. In this paper, we present a model for the management of semantic image information and the contextual knowledge related to the image capture along with a system implementation that manages and exploits this knowledge. Digital picture contents in the database can be interrelated with, and understood based on, contextual semantic geospatial information that the system manages. We describe the integrated camera system, the calculation and visualization of the contextual parameters, and the management of the semantics of the spatial objects. Finally, we present the implementation of SPIM, a SPatial Image Management system that exploits semantic contextual knowledge, its retrieval functionality and the visual user interfaces.