1 / 61

# Highlight extraction: Corners and blobs .

16 views
Category: Education / Career
Description
Feature extraction: Corners and blobs. Why extract features?. Motivation: panorama stitching We have two images – how do we combine them?. Step 2: match features. Why extract features?. Motivation: panorama stitching We have two images – how do we combine them?. Step 1: extract features.
Transcripts
Slide 1

﻿Include extraction: Corners and blobs

Slide 2

Why extricate highlights? Inspiration: display sewing We have two pictures – how would we consolidate them?

Slide 3

Step 2: coordinate elements Why extricate highlights? Inspiration: scene sewing We have two pictures – how would we join them? Step 1: remove highlights

Slide 4

Why separate components? Inspiration: scene sewing We have two pictures – how would we join them? Step 1: separate components Step 2: coordinate elements Step 3: adjust pictures

Slide 5

Characteristics of good elements Repeatability similar element can be found in a few pictures regardless of geometric and photometric changes Saliency Each element has a particular depiction Compactness and productivity Many less elements than picture pixels Locality An element involves a moderately little range of the picture; hearty to disorder and impediment

Slide 6

Applications Feature focuses are utilized for: Motion following Image arrangement 3D reproduction Object acknowledgment Indexing and database recovery Robot route

Slide 7

Finding Corners Key property: in the area around a corner, picture inclination has at least two overwhelming headings Corners are repeatable and unmistakable C.Harris and M.Stephens. "A Combined Corner and Edge Detector." Proceedings of the fourth Alvey Vision Conference : pages 147- - 151.

Slide 8

"level" locale: no adjustment every which way "edge" : no alter along the edge course "corner" : huge change every which way The Basic Idea We ought to effortlessly perceive the point by looking through a little window Shifting a window in any heading ought to give a huge change in power Source: A. Efros

Slide 9

Window work Shifted power Intensity Window work w(x,y) = or 1 in window, 0 outside Gaussian Harris Detector: Mathematics Change in appearance for the move [ u,v ]: Source: R. Szeliski

Slide 10

Harris Detector: Mathematics Change in appearance for the move [ u,v ]: Second-arrange Taylor development of E ( u , v ) around (0,0) (bilinear estimation for little moves):

Slide 11

M Harris Detector: Mathematics The bilinear guess disentangles to where M is a 2 2 framework processed from picture subsidiaries:

Slide 12

Interpreting the second minute grid The surface E ( u , v ) is privately approximated by a quadratic shape. We should attempt to comprehend its shape.

Slide 13

Interpreting the second minute grid First, consider the pivot adjusted case (angles are either even or vertical) If either λ is near 0, then this is not a corner, so search for areas where both are expansive.

Slide 14

bearing of the speediest alter course of the slowest change (  max ) - 1/2 (  min ) - 1/2 General Case Since M is symmetric, we have We can picture M as a circle with hub lengths controlled by the eigenvalues and introduction dictated by R Ellipse condition:

Slide 15

Visualization of second minute networks

Slide 16

Visualization of second minute lattices

Slide 17

Interpreting the eigenvalues Classification of picture focuses utilizing eigenvalues of M :  2 "Edge"  2 >>  1 "Corner"  1 and  2 are vast,  1 ~  2 ; E increments every which way  1 and  2 are little; E is practically steady every which way "Edge"  1 >>  2 "Level" district  1

Slide 18

Corner reaction work α : consistent (0.04 to 0.06) "Edge" R < 0 "Corner" R > 0 |R| little "Edge" R < 0 "Level" area

Slide 19

Harris identifier: Steps Compute Gaussian subsidiaries at every pixel Compute second minute grid M in a Gaussian window around every pixel Compute corner reaction work R Threshold R Find neighborhood maxima of reaction capacity (nonmaximum concealment)

Slide 20

Harris Detector: Steps

Slide 21

Harris Detector: Steps Compute corner reaction R

Slide 22

Harris Detector: Steps Find focuses with huge corner reaction: R> edge

Slide 23

Harris Detector: Steps Take just the purposes of nearby maxima of R

Slide 24

Harris Detector: Steps

Slide 25

Invariance We need elements to be recognized regardless of geometric or photometric changes in the picture: in the event that we have two changed variants of similar picture, components ought to be distinguished in relating areas

Slide 26

Models of Image Change Geometric Rotation Scale Affine legitimate for: orthographic camera, locally planar question Photometric Affine power change ( I  an I + b )

Slide 27

Harris Detector: Invariance Properties Rotation Ellipse turns yet its shape (i.e. eigenvalues) continues as before Corner reaction R is invariant to picture pivot

Slide 28

Intensity scale: I  an I R limit x (picture arrange) x (picture organize) Harris Detector: Invariance Properties Affine force change Only subsidiaries are utilized => invariance to power move I  I + b Partially invariant to relative force change

Slide 29

Harris Detector: Invariance Properties Scaling Corner All focuses will be named edges Not invariant to scaling

Slide 30

Scale-invariant element identification Goal: freely identify comparing areas in scaled adaptations of similar picture Need scale choice component for discovering trademark locale measure that is covariant with the picture change

Slide 31

Scale-invariant elements: Blobs

Slide 32

Recall: Edge discovery Edge f Derivative of Gaussian Edge = most extreme of subsidiary Source: S. Seitz

Slide 33

Edge recognition, Take 2 Edge f Second subsidiary of Gaussian (Laplacian) Edge = zero intersection of second subordinate Source: S. Seitz

Slide 34

most extreme From edges to blobs Edge = swell Blob = superposition of two swells Spatial choice : the greatness of the Laplacian reaction will accomplish a most extreme at the focal point of the blob, gave the size of the Laplacian is "coordinated" to the size of the blob

Slide 35

unique flag (radius=8) expanding σ Scale choice We need to locate the trademark size of the blob by convolving it with Laplacians at a few scales and searching for the greatest reaction However, Laplacian reaction rots as scale builds: Why does this happen?

Slide 36

Scale standardization The reaction of a subordinate of Gaussian channel to an impeccable stride edge diminishes as σ increments

Slide 37

Scale standardization The reaction of a subsidiary of Gaussian channel to a flawless stride edge diminishes as σ increments To keep reaction the same (scale-invariant), should increase Gaussian subsidiary by σ Laplacian is the second Gaussian subordinate, so it must be duplicated by σ 2

Slide 38

Scale-standardized Laplacian reaction greatest Effect of scale standardization Original flag Unnormalized Laplacian reaction

Slide 39

Blob discovery in 2D Laplacian of Gaussian: Circularly symmetric administrator for blob location in 2D

Slide 40

Blob identification in 2D Laplacian of Gaussian: Circularly symmetric administrator for blob recognition in 2D Scale-standardized:

Slide 41

Scale determination At what scale does the Laplacian accomplish a most extreme reaction for a twofold hover of span r? r picture Laplacian

Slide 42

Scale choice The 2D Laplacian is given by Therefore, for a paired hover of span r, the Laplacian accomplishes a greatest at (up to scale) Laplacian reaction r scale ( σ ) picture

Slide 43

Characteristic scale We characterize the trademark scale as the scale that produces pinnacle of Laplacian reaction trademark scale T. Lindeberg (1998). "Feature recognition with programmed scale selection." International Journal of Computer Vision 30 (2): pp 77- - 116.

Slide 44

Scale-space blob identifier Convolve picture with scale-standardized Laplacian at a few scales Find maxima of squared Laplacian reaction in scale-space

Slide 45

Scale-space blob locator: Example

Slide 46

Scale-space blob indicator: Example

Slide 47

Scale-space blob finder: Example

Slide 48

Efficient execution Approximating the Laplacian with a distinction of Gaussians: (Laplacian) (Difference of Gaussians)

Slide 49

Efficient usage David G. Lowe. "Distinctive picture highlights from scale-invariant keypoints." IJCV 60 (2), pp. 91-110, 2004.

Slide 50

From scale invariance to relative invariance

Slide 51

heading of the speediest alter course of the slowest change (  max ) - 1/2 (  min ) - 1/2 Affine adjustment Recall: We can imagine M as an oval with hub lengths dictated by the eigenvalues and introduction controlled by R Ellipse condition:

Slide 52

Affine adjustment case Scale-invariant districts (blobs)

Slide 53

Slide 54

Affine standardization The second minute oval can be seen as the "trademark shape" of an area We can standardize the locale by changing the oval into a unit circle

Slide 55

Orientation vagueness There is no novel change from an oval to a unit circle We can pivot or flip a unit circle, regardless it remains a unit circle

Slide 56

p 2 0 Orientation uncertainty There is no one of a kind change from an oval to a unit circle We can turn or flip a unit circle, despite everything it remains a unit hover So, to allot a remarkable introduction to keypoints: Create histogram of neighborhood angle bearings in the fix Assign sanctioned introduction at pinnacle of smoothed histogram

Slide 57

Affine adjustment Problem: the second minute "window" dictated by weights w ( x , y ) must match the trademark state of the district Solution: iterative approach Use a round window to register second minute lattice Perform relative adjustment to discover an oval molded window Recompute second minute network utilizing new window and emphasize

Slide 58

Iterative relative adjustment K. Mikolajczyk and C. Schmid, Scale and Affine

Recommended
View more...