lec10 - Announcements HW2 is assigned Introduction to...

Info icon This preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon
1 CSE252a, Fall 2010 Computer Vision I Introduction to Computer Vision CSE 252a Lecture 10 CSE252a, Fall 2010 Computer Vision I Announcements HW2 is assigned CSE252A The Illumination Cone Theorem: : The set of images of any object in fixed posed, but under all lighting conditions, is a convex cone in the image space. (Belhumeur and Kriegman, IJCV, 98) Single light source images lie on cone boundary 2-light source image x 1 x 2 x n CSE252A Some natural ideas & questions Can the cones of two different objects intersect? Can two different objects have the same cone? How big is the cone? How can cone be used for recognition? x 1 x 2 x n CSE252A Do Ambiguities Exist? Can two objects of differing shapes produce the same illumination cone? Object 1 Object 2 YES CSE252A Generalized Bas-Relief Transformations Objects differing by a GBR have the same illumination cone.
Image of page 1

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

View Full Document Right Arrow Icon
2 CSE252A Uncalibrated photometric stereo 1. Take n images as input, perform SVD to compute B*. 2. Find some A such that B*A is close to integrable. 3. Integrate resulting gradient field to obtain height function f*(x,y). Comments: f*(x,y) differs from f(x,y) by a GBR. Can use specularities to resolve GBR for non- Lambertian surface. CSE252A GBR Preserves Shadows CSE252A Illumination Cones: Recognition Method x 1 x 2 x n Illumination cone for David Illumination cone for Lee Is this an image of Lee or David? •Distance to cone •Cost O(ne 2 ) where •n: # pixels •e: # extreme rays •Distance to subspace CSE252A Generating the Illumination Cone Original (Training) Images α ( x,y ) f x (x,y) f y (x,y) albedo (surface normals) Surface. f (x,y) (albedo textured mapped on surface) . 3D linear subspace [Georghiades, Belhumeur, Kriegman 01] Cone - Attached Cone - Cast CSE252A Yale Face Database B 64 Lighting Conditions 9 Poses => 576 Images per Person CSE252a, Fall 2010 Computer Vision I Color Cameras: Three kinds of pixels Lens Dichroic prism 3 Chip Camera Optically split incoming light onto three sensors, each responding to different wavelengths Single sensor with color mosaic overlaid.
Image of page 2
3 CSE252a, Fall 2010 Computer Vision I The appearance of colors Color appearance is strongly affected by (at least): – Spectrum of lighting striking the retina – other nearby colors (space) – adaptation to previous views (time) – “state of mind” CSE252a, Fall 2010 Computer Vision I
Image of page 3

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

View Full Document Right Arrow Icon
Image of page 4
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern