1 / 40

Announcements

Announcements. Kevin Matzen office hours Tuesday 4-5pm, Thursday 2-3pm, Upson 317 TA: Yin Lou Course lab: Upson 317 Card access will be setup soon Course webpage: http://www.cs.cornell.edu/courses/cs4670/2010fa/. Projects. Projects involving programming phones will be group projects

Download Presentation

Announcements

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Announcements • Kevin Matzen office hours • Tuesday 4-5pm, Thursday 2-3pm, Upson 317 • TA: Yin Lou • Course lab: Upson 317 • Card access will be setup soon • Course webpage: http://www.cs.cornell.edu/courses/cs4670/2010fa/

  2. Projects • Projects involving programming phones will be group projects • Groups will check out phones, specifics TBA

  3. Questions?

  4. Why is computer vision difficult? Viewpoint variation Scale Illumination

  5. Why is computer vision difficult? Motion (Source: S. Lazebnik) Intra-class variation Occlusion Background clutter

  6. Challenges: local ambiguity slide credit: Fei-Fei, Fergus & Torralba

  7. But there are lots of cues we can exploit… Source: S. Lazebnik

  8. Bottom line • Perception is an inherently ambiguous problem • Many different 3D scenes could have given rise to a particular 2D picture • We often need to use prior knowledge about the structure of the world Image source: F. Durand

  9. CS4670: Computer Vision Noah Snavely Lecture 1: Images and image filtering Hybrid Images, Oliva et al., http://cvcl.mit.edu/hybridimage.htm

  10. CS4670: Computer Vision Noah Snavely Lecture 1: Images and image filtering Hybrid Images, Oliva et al., http://cvcl.mit.edu/hybridimage.htm

  11. CS4670: Computer Vision Noah Snavely Lecture 1: Images and image filtering Hybrid Images, Oliva et al., http://cvcl.mit.edu/hybridimage.htm

  12. CS4670: Computer Vision Noah Snavely Lecture 1: Images and image filtering Hybrid Images, Oliva et al., http://cvcl.mit.edu/hybridimage.htm

  13. Reading • Szeliski, Chapter 3.1-3.2

  14. What is an image?

  15. What is an image? Digital Camera We’ll focus on these in this class (More on this process later) The Eye Source: A. Efros

  16. What is an image? • A grid (matrix) of intensity values (common to use one byte per value: 0 = black, 255 = white) =

  17. What is an image? • We can think of a (grayscale) image as a function, f, from R2 to R: • f (x,y) gives the intensity at position (x,y) • A digital image is a discrete (sampled, quantized) version of this function f (x, y) x y snoop 3D view

  18. Image transformations • As with any function, we can apply operators to an image • We’ll talk about a special kind of operator, convolution (linear filtering) • g (x,y) = f (-x,y) • g (x,y) = f (x,y) + 20

  19. Question: Noise reduction • Given a camera and a still scene, how can you reduce noise? Take lots of images and average them! What’s the next best thing? Source: S. Seitz

  20. 10 5 3 4 7 5 1 1 1 7 Image filtering • Modify the pixels in an image based on some function of a local neighborhood of each pixel Some function Local image data Modified image data Source: L. Zhang

  21. 0 0 0 0 0.5 0 0 1 0.5 10 5 3 4 8 6 1 1 1 8 Linear filtering • One simple version: linear filtering (cross-correlation, convolution) • Replace each pixel by a linear combination of its neighbors • The prescription for the linear combination is called the “kernel” (or “mask”, “filter”) Local image data kernel Modified image data Source: L. Zhang

  22. Cross-correlation Let be the image, be the kernel (of size 2k+1 x 2k+1), and be the output image This is called a cross-correlation operation:

  23. Convolution • Same as cross-correlation, except that the kernel is “flipped” (horizontally and vertically) • Convolution is commutative and associative This is called a convolution operation:

  24. 1D Demo

  25. Convolution Adapted from F. Durand

  26. Mean filtering * =

  27. 0 0 0 0 1 0 0 0 0 Linear filters: examples = * Original Identical image Source: D. Lowe

  28. 0 0 0 1 0 0 0 0 0 Linear filters: examples = * Original Shifted left By 1 pixel Source: D. Lowe

  29. 1 1 1 1 1 1 1 1 1 Linear filters: examples = * Original Blur (with a mean filter) Source: D. Lowe

  30. 0 1 0 1 1 0 1 0 1 2 0 1 0 1 1 0 0 1 Linear filters: examples - = * Sharpening filter (accentuates edges) Original Source: D. Lowe

  31. Sharpening Source: D. Lowe

  32. Smoothing with box filter revisited Source: D. Forsyth

  33. Gaussian Kernel Source: C. Rasmussen

  34. Mean vs. Gaussian filtering

  35. Gaussian filter • Removes “high-frequency” components from the image (low-pass filter) • Convolution with self is another Gaussian • Convolving two times with Gaussian kernel of width = convolving once with kernel of width = * Source: K. Grauman

  36. = detail smoothed (5x5) original Let’s add it back: = + α original detail sharpened Sharpening revisited • What does blurring take away? – Source: S. Lazebnik

  37. scaled impulse Gaussian Laplacian of Gaussian Sharpen filter blurredimage image unit impulse(identity)

  38. Sharpen filter unfiltered filtered

  39. Convolution in the real world Camera shake = * Source: Fergus, et al. “Removing Camera Shake from a Single Photograph”, SIGGRAPH 2006 Bokeh: Blur in out-of-focus regions of an image. Source: http://lullaby.homepage.dk/diy-camera/bokeh.html

  40. Questions? • For next time: • Read Szeliski, Chapter 3.1-3.2

More Related