Computer Science Department
School of Computer Science, Carnegie Mellon University
Representation and Incremental Construction of a Three-Dimensional Scene Model
The representation, construction, and updating of the 3D scene model derived by the 3D Mosaic scene understanding system is described. The scene model is a surface-based description of an urban scene, and is incrementally acquired from a sequence of images obtained from multiple viewpoints. Each view of the scene undergoes analysis which results in a 3D wire-frame description that represents portions of edges and vertices of buildings. The initial model, constructed from the wire frames obtained from the first view, represents an initial approximation of the scene. As each successive view is processed, the model is incrementally updated and gradually becomes more accurate and complete. Task-specific knowledge is used to construct and update the model from the wire frames. At any point along its development, the model represents the current understanding of the scene and may be used for tasks such as matching, display generation, planning paths through the scene, and making other decisions dealing with the scene environment.
The model is represented as a graph in terms of symbolic primitives such as faces, edges, vertices, and their topology and geometry. This permits the representation of partially complete, planar-faced objects. Because incremental modifications to the model must be easy to perform, the model contains mechanisms to 1 add primitives in a manner such that constraints on geometry imposed by these additions are propagated throughout the model, and 2 modify and delete primitives if discrepancies arise between newly derived and current information. The model also contains mechanisms that permit the generation, addition, and deletion of hypotheses for parts of the scene for which there is little data.
We describe an experiment in which the model is generated and updated from two views.