caa a22 4500 467914834 CHVBK 20180406152859.0 cr unu---uuuuu 170328e20060301xx s 000 0 eng 10.1007/s11263-005-3674-1 doi (NATIONALLICENCE)springer-10.1007/s11263-005-3674-1 3D Object Modeling and Recognition Using Local Affine-Invariant Image Descriptors and Multi-View Spatial Constraints [Elektronische Daten] [Fred Rothganger, Svetlana Lazebnik, Cordelia Schmid, Jean Ponce] Abstract.: This article introduces a novel representation for three-dimensional (3D) objects in terms of local affine-invariant descriptors of their images and the spatial relationships between the corresponding surface patches. Geometric constraints associated with different views of the same patches under affine projection are combined with a normalized representation of their appearance to guide matching and reconstruction, allowing the acquisition of true 3D affine and Euclidean models from multiple unregistered images, as well as their recognition in photographs taken from arbitrary viewpoints. The proposed approach does not require a separate segmentation stage, and it is applicable to highly cluttered scenes. Modeling and recognition results are presented. Springer Science + Business Media, Inc., 2006 three-dimensional object recognition nationallicence image-based modeling nationallicence affine-invariant image descriptors nationallicence multi-view geometry nationallicence Rothganger Fred Department of Computer Science and Beckman Institute, University of Illinois at Urbana-Champaign, 61801, Urbana, IL, USA aut Lazebnik Svetlana Department of Computer Science and Beckman Institute, University of Illinois at Urbana-Champaign, 61801, Urbana, IL, USA aut Schmid Cordelia INRIA, Rhône-Alpes, 665, Avenue de l'Europe, 38330, Montbonnot, France aut Ponce Jean Department of Computer Science and Beckman Institute, University of Illinois at Urbana-Champaign, 61801, Urbana, IL, USA aut International Journal of Computer Vision Kluwer Academic Publishers 66/3(2006-03-01), 231-259 0920-5691 66:3<231 2006 66 11263 https://doi.org/10.1007/s11263-005-3674-1 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11263-005-3674-1 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Rothganger Fred Department of Computer Science and Beckman Institute, University of Illinois at Urbana-Champaign, 61801, Urbana, IL, USA aut NATIONALLICENCE 700 1- Lazebnik Svetlana Department of Computer Science and Beckman Institute, University of Illinois at Urbana-Champaign, 61801, Urbana, IL, USA aut NATIONALLICENCE 700 1- Schmid Cordelia INRIA, Rhône-Alpes, 665, Avenue de l'Europe, 38330, Montbonnot, France aut NATIONALLICENCE 700 1- Ponce Jean Department of Computer Science and Beckman Institute, University of Illinois at Urbana-Champaign, 61801, Urbana, IL, USA aut NATIONALLICENCE 773 0- International Journal of Computer Vision Kluwer Academic Publishers 66/3(2006-03-01), 231-259 0920-5691 66:3<231 2006 66 11263 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer