ebook img

Computer Vision: Image Alignment PDF

125 Pages·2013·7.05 MB·English
by  
Save to my drive
Quick download
Download
Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.

Preview Computer Vision: Image Alignment

Computer Vision: Image Alignment Raquel Urtasun TTIChicago Jan 24, 2013 RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 1/44 Readings Chapter 2.1, 3.6, 4.3 and 6.1 of Szeliski’s book Chapter 1 of Forsyth & Ponce RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 2/44 What did we see in class last week? RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 3/44 What is the geometric relationship between these images? !" [Source: N. Snavely] RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 4/44 What is the geometric relationship between these images? Very important for creating mosaics! [Source: N. Snavely] RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 4/44 Image Warping Image filtering: change range of image g(x)=h(f(x)) !" %" $" #" #" Image warping: change domain of image g(x)=f(h(x)) !" %" $" #" #" [Source: R. Szeliski] RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 5/44 Parametric (global) warping !" !!"!#$%&'! !"!"!#$(%&('! Transformation T is a coordinate-changing machine: p(cid:48) =T(p) What does it mean that T is global? Is the same for any point p Can be described by just a few numbers (parameters) [Source: N. Snavely] RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 6/44 Forward and Inverse Warping Forward Warping: Send each pixel f(x) to its corresponding location (x(cid:48),y(cid:48))=T(x,y) in g(x(cid:48),y(cid:48)) Inverse Warping: Each pixel at the destination is sampled from the original image RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 7/44 All 2D Linear Transformations Linear transformations are combinations of Scale, Rotation Shear Mirror (cid:20)x(cid:48)(cid:21) (cid:20)a b(cid:21)(cid:20)x(cid:21) = y(cid:48) c d y [Source: N. Snavely] RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 8/44 Parallel lines remain parallel Ratios are preserved Closed under composition (cid:20)x(cid:48)(cid:21) (cid:20)a b(cid:21)(cid:20)e f(cid:21)(cid:20)i j(cid:21)(cid:20)x(cid:21) = y(cid:48) c d g h k l y What about the translation? [Source: N. Snavely] All 2D Linear Transformations Properties of linear transformations: Origin maps to origin Lines map to lines RaquelUrtasun (TTI-C) ComputerVision Jan24,2013 9/44

Description:
Computer Vision: Image Alignment. Raquel Urtasun. TTI Chicago. Jan 24, 2013. Raquel Urtasun (TTI-C). Computer Vision. Jan 24, 2013. 1 / 44
See more

The list of books you might like

Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.