D. Paulus, U. Ahlrichs, B. Heigl, J. Denzler, J. Hornegger, M. Zobel,
and H. Neimann
Lehrstuhl für Mustererkennung (LME, Informatik 5)
AbstractWe present a modular architecture for image understanding and active computer vision that consists of three major components: sensor and actor interfaces required for data-driven active vision are encapsulated to hide machine-dependent parts; image segmentation is implemented in object-oriented programming as a hierarchy of image operator classes, guaranteeing simple and uniform interfaces; knowledge about the environment is represented either as a semantic network or as statistical object models or as a combination of both; and the semantic network formalism is used to represent camera actions that are needed in explorative vision.
We use these modules to create two application systems. The emphasis here is object localization and recognition in an office room: An active purposive camera control is applied to recover depth information and to focus on interesting objects, and color segmentation is used to compute object features which are relatively insensitive to small aspect changes.
Keywords: Computer vision system, object-oriented design, object recognition, scene analysis, mobile systems, knowledge-based analysis.