Presentation11 - Computer Vision Lecture #11 Hossam...

Info iconThis preview shows pages 1–25. Sign up to view the full content.

View Full Document Right Arrow Icon
Computer Vision Lecture #11 Hossam Abdelmunim 1 & Aly A. Farag 2 1 Computer & Systems Engineering Department, Ain Shams University, Cairo, Egypt 2 Electerical and Computer Engineering Department, University of Louisville, Louisville, KY, USA ECE619/645 – Spring 2011
Background image of page 1

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

View Full DocumentRight Arrow Icon
Invariant features
Background image of page 2
Background image of page 3

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

View Full DocumentRight Arrow Icon
Background image of page 4
We need better features, better representations, …
Background image of page 5

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

View Full DocumentRight Arrow Icon
Find a bottle: 6 Categories Instances Find these two objects Can’t do unless you do not care about few errors… Can nail it
Background image of page 6
Background image of page 7

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

View Full DocumentRight Arrow Icon
Building a Panorama M. Brown and D. G. Lowe. Recognising Panoramas. ICCV
Background image of page 8
How do we build a panorama? We need to match (align) images Global methods sensitive to occlusion, lighting, parallax effects. So look for local features that match well. How would you do it by eye?
Background image of page 9

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

View Full DocumentRight Arrow Icon
Matching with Features •Detect feature points in both images
Background image of page 10
Matching with Features •Detect feature points in both images •Find corresponding pairs
Background image of page 11

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

View Full DocumentRight Arrow Icon
Matching with Features •Detect feature points in both images •Find corresponding pairs •Use these pairs to align images
Background image of page 12
Matching with Features • Problem 1: – Detect the same point independently in both images no chance to match! We need a repeatable detector
Background image of page 13

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

View Full DocumentRight Arrow Icon
Matching with Features • Problem 2: – For each point correctly recognize the corresponding one ? We need a reliable and distinctive descriptor
Background image of page 14
More motivation… • Feature points are used also for: – Image alignment (homography, fundamental matrix) – 3D reconstruction – Motion tracking – Object recognition – Indexing and database retrieval – Robot navigation – … other
Background image of page 15

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

View Full DocumentRight Arrow Icon
Selecting Good Features • What’s a ―good feature‖? – Satisfies brightness constancy—looks the same in both images – Has sufficient texture variation – Does not have too much texture variation – Corresponds to a ―real‖ surface patch—see below: – Does not deform too much over time Left eye view Right eye view Bad feature Good feature
Background image of page 16
Contents Harris Corner Detector – Overview – Analysis Detectors – Rotation invariant – Scale invariant – Affine invariant Descriptors – Rotation invariant – Scale invariant – Affine invariant
Background image of page 17

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

View Full DocumentRight Arrow Icon
An introductory example: Harris corner detector C.Harris, M.Stephens. “A Combined Corner and Edge Detector”. 1988
Background image of page 18
The Basic Idea • We should easily localize the point by looking through a small window • Shifting a window in any direction should give a large change in intensity
Background image of page 19

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

View Full DocumentRight Arrow Icon
Harris Detector: Basic Idea “flat” region: no change as shift window in all directions “edge” : no change as shift window along the edge direction “corner” : significant change as shift window in all directions
Background image of page 20
Selecting Good Features l 1 and l 2 are large
Background image of page 21

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

View Full DocumentRight Arrow Icon
Selecting Good Features large l 1 , small l 2
Background image of page 22
Selecting Good Features small l 1 , small l 2
Background image of page 23

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

View Full DocumentRight Arrow Icon
Harris Detector: Mathematics l 1 l 2 “Corner” l 1 and l 2 are large, l 1 ~ l 2 ; E increases in all directions l 1 and l 2 are small; E is almost constant in all directions “Edge” l 1 >> l 2 “Edge” l 2 >> l 1 “Flat” region Classification of image points using eigenvalues of M :
Background image of page 24
Image of page 25
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/12/2012 for the course ECE 618 taught by Professor Amini during the Spring '08 term at University of Louisville.

Page1 / 96

Presentation11 - Computer Vision Lecture #11 Hossam...

This preview shows document pages 1 - 25. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online