The field of computer vision is now opening up possibilities offered by analyzing surface data for object recognition and scene understanding. This volume, which highlights current research, demonstrates that surface information can greatly simplify the image understanding process. The study is as much about a style of model-based three dimensional scene analysis as about a particular example of that style. The style combines surface patches segmented from the three dimensional scene description, surface patch based object models, a hierarchy of representations, models and recognitions, a distributed network-based model invocation process and a knowledge-based model matcher. The aim of the work is to show that these elements fit together well, and make it easy to extend the competence of current vision systems without complications.
An introduction to recognition using surfaces; object recognition from surface information; surface data as input for recognition; making complete surface hypotheses; surface clusters; description of three-dimensional structures; object representation; model invocation; hypothesis construction; hypothesis verification.