lecture 3.2.0 introduction to keypoint features€¦ · use of features in this course • this...

19
Lecture 3.2.0 Introduction to keypoint features Trym Vegard Haavardsholm

Upload: others

Post on 14-May-2020

2 views

Category:

Documents


0 download

TRANSCRIPT

Lecture 3.2.0Introduction to keypoint features

Trym Vegard Haavardsholm

Why extract features?

2

• Example: Panorama stitching– How do we combine two images?

Why extract features?

3

• Example: Panorama stitching– How do we combine two images?

Step 1: Extract features

Why extract features?

4

• Example: Panorama stitching– How do we combine two images?

Step 1: Extract featuresStep 2: Match features

Why extract features?

5

• Example: Panorama stitching– How do we combine two images?

Step 1: Extract featuresStep 2: Match featuresStep 3: Align images

6

7

Correspondences across views

8

Correspondences across views

9

Correspondences across views

10

Correspondences across views

11

Characteristics of good features

• Repeatability

12

Characteristics of good features

• Repeatability• Distinctiveness

13

Characteristics of good features

• Repeatability• Distinctiveness

• Efficiency

14

Characteristics of good features

• Repeatability• Distinctiveness

• Efficiency• Locality

15

Applications: Automatic Panoramas

16

Credit: Matt Brown

Application: Object Recognition

17

Application: 3D reconstruction and navigation

18

Use of features in this course

• This week:– Lecture 3.2.1: Corner features– Lecture 3.2.2: Blob features

• Next week:– Feature descriptors– Feature matching– Homography estimation from correspondences

• Weeks after that:– Part II: World geometry and 3D– Part III: Scene analysis

19