caa a22 4500 467914567 CHVBK 20180406152858.0 cr unu---uuuuu 170328e20060401xx s 000 0 eng 10.1007/s11263-005-4264-y doi (NATIONALLICENCE)springer-10.1007/s11263-005-4264-y Object Level Grouping for Video Shots [Elektronische Daten] [Josef Sivic, Frederik Schaffalitzky, Andrew Zisserman] We describe a method for automatically obtaining object representations suitable for retrieval from generic video shots. The object representation consists of an association of frame regions. These regions provide exemplars of the object's possible visual appearances. Two ideas are developed: (i) associating regions within a single shot to represent a deforming object; (ii) associating regions from the multiple visual aspects of a 3D object, thereby implicitly representing 3D structure. For the association we exploit temporal continuity (tracking) and wide baseline matching of affine covariant regions. In the implementation there are three areas of novelty: First, we describe a method to repair short gaps in tracks. Second, we show how to join tracks across occlusions (where many tracks terminate simultaneously). Third, we develop an affine factorization method that copes with motion degeneracy. We obtain tracks that last throughout the shot, without requiring a 3D reconstruction. The factorization method is used to associate tracks into object-level groups, with common motion. The outcome is that separate parts of an object that are not simultaneously visible (such as the front and back of a car, or the front and side of a face) are associated together. In turn this enables object-level matching and recognition throughout a video. We illustrate the method on the feature film "Groundhog Day.” Examples are given for the retrieval of deforming objects (heads, walking people) and rigid objects (vehicles, locations). Springer Science + Business Media, Inc., 2006 3D object retrieval in videos nationallicence tracking affine covariant regions nationallicence independent motion segmentation nationallicence robust affine factorization nationallicence Sivic Josef Department of Engineering Science, University of Oxford, OX1 3PJ, Oxford, UK aut Schaffalitzky Frederik Department of Engineering Science, University of Oxford, OX1 3PJ, Oxford, UK aut Zisserman Andrew Department of Engineering Science, University of Oxford, OX1 3PJ, Oxford, UK aut International Journal of Computer Vision Kluwer Academic Publishers 67/2(2006-04-01), 189-210 0920-5691 67:2<189 2006 67 11263 https://doi.org/10.1007/s11263-005-4264-y text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11263-005-4264-y text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Sivic Josef Department of Engineering Science, University of Oxford, OX1 3PJ, Oxford, UK aut NATIONALLICENCE 700 1- Schaffalitzky Frederik Department of Engineering Science, University of Oxford, OX1 3PJ, Oxford, UK aut NATIONALLICENCE 700 1- Zisserman Andrew Department of Engineering Science, University of Oxford, OX1 3PJ, Oxford, UK aut NATIONALLICENCE 773 0- International Journal of Computer Vision Kluwer Academic Publishers 67/2(2006-04-01), 189-210 0920-5691 67:2<189 2006 67 11263 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer