lecture21 - EECS 442 Computer vision Object Recognition...

Info iconThis preview shows pages 1–18. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: EECS 442 Computer vision Object Recognition Intro Recognition of 3D objects Recognition of object categories: Bag of world models Part based models 3D object categorization Faces Segments of this lectures are courtesy of Prof A. Torralba, R. Fergus and F. Li Recognizing and Learning Object Categories: Year 2007 Challenges: intra-class variation Usual Challenges: Variability due to: View point Illumination Occlusions Problem with bag-of-words All have equal probability for bag-of-words methods Location information is important Part Based Representation Object as set of parts Model: Relative locations between parts Appearance of part Figure from [Fischler & Elschlager 73] History of Parts and Structure approaches Fischler & Elschlager 1973 Yuille 91 Brunelli & Poggio 93 Lades, v.d. Malsburg et al. 93 Cootes, Lanitis, Taylor et al. 95 Amit & Geman 95, 99 Perona et al. 95, 96, 98, 00, 03, 04, 05 Ullman et al. 02 Felzenszwalb & Huttenlocher 00, 04 Crandall & Huttenlocher 05, 06 Leibe & Schiele 03, 04 Many papers since 2000 A B D C Deformations Presence / Absence of Features occlusion Background clutter Sparse representation + Computationally tractable (10 5 pixels 10 1 -- 10 2 parts) + Generative representation of class + Avoid modeling global variability - Throw away most image information- Parts need to be distinctive to separate from other classes from Sparse Flexible Models of Local Features Gustavo Carneiro and David Lowe, ECCV 2006 Different connectivity structures O(N 6 ) O(N 2 ) O(N 3 ) O(N 2 ) Fergus et al. 03 Fei-Fei et al. 03 Crandall et al. 05 Fergus et al. 05 Crandall et al. 05 Felzenszwalb & Huttenlocher 00 Bouchard & Triggs 05 Carneiro & Lowe 06 Csurka 04 Vasconcelos 00 Hierarchical representations Pixels Pixel groupings Parts Object Images from [Amit98,Bouchard05] Multi-scale approach increases number of low-level features Amit and Geman 98 Bouchard & Triggs 05 Hierarchical representations Pixels Pixel groupings Parts Object Images from [Amit98,Bouchard05] Multi-scale approach increases number of low-level features Amit and Geman 98 Bouchard & Triggs 05 Hierarchical representations Pixels Pixel groupings Parts Object Images from [Amit98,Bouchard05] Multi-scale approach increases number of low-level features Amit and Geman 98 Bouchard & Triggs 05 Some class-specific graphs Articulated motion People Animals Special parameterisations Limb angles Images from [Kumar, Torr and Zisserman 05, Felzenszwalb & Huttenlocher 05] Stochastic Grammar of Images S.C. Zhu et al. and D. Mumford animal head instantiated by tiger head animal head instantiated by bear head e.g. discontinuities, gradient e.g. linelets, curvelets, T- junctions e.g. contours, e....
View Full Document

Page1 / 101

lecture21 - EECS 442 Computer vision Object Recognition...

This preview shows document pages 1 - 18. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online