1. Detecting image intensity changes

2. Detecting intensity changes
Smooth the image intensities
reduces effect of noise
sets resolution or scale of analysis
Differentiate the smoothed intensities
transforms image into a representation that facilitates detection of intensity changes
Detect and describe features in the transformed image
(e.g. peaks or zero-crossings)

3. Smoothing a 2D image G(x,y) * I(x,y)
To smooth a 2D image I(x,y), we convolve with a 2D Gaussian:
result of convolution
G(x,y) * I(x,y)
image

4. Differentiation in 2D
To differentiate the smoothed image, we will use the Laplacian operator:
We can again combine the smoothing and derivative operations:
(displayed with sign reversed)

5. Analyzing a 2D image image after smoothing and second derivative image
black = negative
white = positive
zero-crossings

6. Convolution in two dimensions1 8 1 3 8 1 3 8 *
convolution result
2D convolution operator 24 =
image

7. Image
Convolution operator
Laplacian
Convolution result

8. Detecting intensity changes at multiple scales
small σ
large σ
zero-crossings of convolutions of image with 2G operators

9. Computing the contrast of intensity changesL

10. Stereo viewing geometry
LEFT + -
RIGHT
positive disparity
 in front of fixation point
negative disparity
 behind fixation point
LEFT
RIGHT
1-10

11. Steps of the stereo process
left
right
extract features from the left and right images, whose stereo disparity will be measured
match the left and right image features and measure their disparity in position
“stereo correspondence problem”
use stereo disparity to compute depth
1-11
1-11

12. Constraints on stereo correspondence
Uniqueness
each feature in the left image matches with only one feature in the right (and vice versa…)
Similarity
matching features appear “similar” in the two images
Continuity
nearby image features have similar disparities
Epipolar constraint
simple version: matching features have similar vertical positions, but…
1-12

13. Solving the stereo correspondence problem
1-13