No abstract

Reconstruction of 3D scene geometry is an important element for scene understanding, autonomous vehicle and robot navigation, image retrieval, and 3D television. We propose accounting for the inherent structure of the visual world when trying to solve the scene reconstruction problem. Consequently, we identify geometric scene categorization as the first step toward robust and efficient depth estimation from single images. We introduce 15 typical 3D scene geometries called stages, each with a unique depth profile, which roughly correspond to a large majority of broadcast video frames. Stage information serves as a first approximation of global depth, narrowing down the search space in depth estimation and object localization. We propose different sets of low-level features for depth estimation, and perform stage classification on two diverse data sets of television broadcasts. Classification results demonstrate that stages can often be efficiently learned from low-dimensional image representations.

We will briefly discuss the classic approaches to correspondence estimation including: feature detection and matching, block matching, pel-recursive, and optical-flow techniques. For more details we refer the reader to the excellent overview in [ 531. Feature-Based Algorithms Feature-based algorithms [3], [28] first extract predefined features, and then match these (Fig. 11). The separation of detection and matching is a restriction on the MAY 1999 IEEE SIGNAL PROCESSING MAGAZINE