From surfaces to objects: computer vision and three dimensional scene analysis
A unified approach to the theory and practice of computer vision. Presents a model-based, 3-dimensional scene analysis that combines surface patches segmented from the 3-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. Describes the model-independent scene analysis, and how objects are represented and selected, and shows how to locate, verify, and understand a known object given its geometric model.
What people are saying - Write a review
We haven't found any reviews in the usual places.
An Introduction to Recognition Using Surfaces
Object Recognition from Surface Information
Surface Data as Input for Recognition 89
9 other sections not shown
Other editions - View all
analysis angle armasm ASSEMBLY B0/LINE boundary segments Chapter Complete Robot computation computer vision connected context corresponding curvature axis cylinder deﬁned deﬁnition described DESCRIPTION DESCRIPTION DESCRIPTION error estimates evidence types Figure ﬁnal ﬁnding ﬁrst global graph harmonic mean Hence hypothesis construction identiﬁcation identity image features image regions invoked labeled linked lowerarm lsideb matching model features model instance model invocation model SURFACEs model-to-data nodes object model object recognition object surface obscured surface obscuring boundaries occlusion orientation discontinuity paired parameter planar plane plausibility position predicted principal curvatures problem property evidence raycasting reconstruction reference frame relationships representation robbody robbodyside robot robshldbd robshldend robshould rotation signiﬁcant speciﬁed SRFTYPE structure superclass supercomponent surface clusters surface data surface hypotheses surface image surface normals surface orientation surface patches surface reconstruction surface regions surface shape Test Scene three dimensional scene transformation trash UNARYEVID UNARYEVID UNARYEVID upperarm uside vector veriﬁcation visible WEIGHT wire frame models