Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8...
Transcript of Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8...
![Page 1: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/1.jpg)
10/9/2013
1
Lecture 5: Feature detection and matching
CS4670 / 5670: Computer Vision Noah Snavely
Reading
• Szeliski: 4.1
![Page 2: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/2.jpg)
10/9/2013
2
Feature extraction: Corners and blobs
Motivation: Automatic panoramas
Credit: Matt Brown
![Page 3: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/3.jpg)
10/9/2013
3
http://research.microsoft.com/en-us/um/redmond/groups/ivm/HDView/HDGigapixel.htm
HD View
Also see GigaPan: http://gigapan.org/
Motivation: Automatic panoramas
Why extract features?
• Motivation: panorama stitching
– We have two images – how do we combine them?
![Page 4: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/4.jpg)
10/9/2013
4
Why extract features?
• Motivation: panorama stitching
– We have two images – how do we combine them?
Step 1: extract features Step 2: match features
Why extract features?
• Motivation: panorama stitching
– We have two images – how do we combine them?
Step 1: extract features Step 2: match features Step 3: align images
![Page 5: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/5.jpg)
10/9/2013
5
Image matching
by Diva Sian
by swashford
TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.: AAAAAA
Harder case
by Diva Sian by scgbt
![Page 6: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/6.jpg)
10/9/2013
6
Harder still?
NASA Mars Rover images with SIFT feature matches
Answer below (look for tiny colored squares…)
![Page 7: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/7.jpg)
10/9/2013
7
Feature Matching
Feature Matching
![Page 8: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/8.jpg)
10/9/2013
8
Invariant local features
Find features that are invariant to transformations
– geometric invariance: translation, rotation, scale
– photometric invariance: brightness, exposure, …
Feature Descriptors
Advantages of local features
Locality
– features are local, so robust to occlusion and clutter
Quantity
– hundreds or thousands in a single image
Distinctiveness:
– can differentiate a large database of objects
Efficiency
– real-time performance achievable
![Page 9: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/9.jpg)
10/9/2013
9
More motivation…
Feature points are used for:
– Image alignment (e.g., mosaics)
– 3D reconstruction
– Motion tracking
– Object recognition
– Indexing and database retrieval
– Robot navigation
– … other
Snoop demo
What makes a good feature?
![Page 10: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/10.jpg)
10/9/2013
10
Want uniqueness
Look for image regions that are unusual
– Lead to unambiguous matches in other images
How to define “unusual”?
Local measures of uniqueness
Suppose we only consider a small window of pixels
– What defines whether a feature is a good or bad candidate?
Credit: S. Seitz, D. Frolova, D. Simakov
![Page 11: Lecture 1: Images and image filtering - Cornell University · 2013. 10. 9. · 10/9/2013 8 Invariant local features Find features that are invariant to transformations –geometric](https://reader033.fdocuments.in/reader033/viewer/2022060911/60a5fcd53dc495690951d414/html5/thumbnails/11.jpg)
10/9/2013
11
Local measure of feature uniqueness
“flat” region: no change in all directions
“edge”: no change along the edge direction
“corner”: significant change in all directions
• How does the window change when you shift it?
• Shifting the window in any direction causes a big change
Credit: S. Seitz, D. Frolova, D. Simakov