1. Detection of salient points

2. Feature matching vs. tracking
Image-to-image correspondences are key to passive triangulation-based 3D reconstruction
Extract features independently and then match by comparing descriptors
Extract features in first images and then try to find same feature back in next view
What is a good feature?

3. Comparing image regions
Compare intensities pixel-by-pixel
I(x,y)
I´(x,y)
Dissimilarity measures
Sum of Square Differences

4. Comparing image regions
Compare intensities pixel-by-pixel
I(x,y)
I´(x,y)
Similarity measures
Zero-mean Normalized Cross Correlation

5. Feature points Required properties: Well-defined Stable across views
(i.e. neigboring points should all be different)
Stable across views
(i.e. same 3D point should be extracted
as feature for neighboring viewpoints)

6. Feature point extraction
Find points that differ as much as possible from all neighboring points
homogeneous
edge
corner

7. Edge detectors tend to fail at corners
Intuition: right at corner, gradient is ill-defined
Near corner, intensity changes along any direction

8. Feature point extraction
Approximate SSD for small displacement Δ
Image difference, square difference for pixel
Its module:
SSD for window

9. Feature point extraction
homogeneous
edge
corner
Find points for which the following is maximum
i.e. maximize smallest eigenvalue of M

10. Harris corner detector
Use small local window:
Maximize „cornerness“:
Only use local maxima, subpixel accuracy through second order surface fitting
Select strongest features over whole image and over each tile (e.g. 1000/image, 2/tile)