Announcements
• Final: Thursday, December 15, 8am,
here.
• Review Session, Wednesday, Dec 14,
1pm, AV Williams 4424.
• Review sheet with practice problems
on-line.
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Guidelines and tips
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
Computer Vision Course Announcements and Topics - Prof. David Jacobs, Study notes of Computer Science
Announcements for a computer vision course, including exam and review session dates, hints for the final exam, and a list of topics covered in the course such as boundary detection, modeling and algorithms, stereo, optimization, learning, graphics, image editing, biomedical engineering, and big data sets. The document also mentions various researchers and their contributions to the field.
Typology: Study notes
Pre 2010
1 / 39
This page cannot be seen from the preview
Don't miss anything!
Related documents
Partial preview of the text
Download Computer Vision Course Announcements and Topics - Prof. David Jacobs and more Study notes Computer Science in PDF only on Docsity!
Announcements
• Final: Thursday, December 15, 8am,
here.
• Review Session, Wednesday, Dec 14,
1pm, AV Williams 4424.
• Review sheet with practice problems
on-line.
Hints for Final
• Focus on core techniques/ideas:
convolution, gradients, statisticalmodeling, 3D geometry, motionmatrices and optimization methods westudied, and their use in vision.
• Of course, other topics from course may
show up.
Boundary Detection
-^
Images don’t come color-coded withboundaries.^ – Filtering to combine evidence.– Define discontinuities in 2D.– Snakes to combine evidence further.– Good continuation, comes from knowledge of
shape.
- Texture understanding as modeling random
processes.
-^
Boundary detection involves combination ofdifferent kinds of knowledge.
Modeling + Algorithms
• Build a simple model of the world
(eg., flat, uniform intensity).
• Find provably good algorithms.• Experiment on real world.• Update model. Problem:
Too often models are simplistic
or intractable.
Where is Computer Vision
Going?
• More Data, Faster Machines =>• More Interaction with Other Fields.• Fundamental Problems Remain
Optimization
-^
Partly push of video meant biggeroptimization problems.
-^
Early 90s, SVD, Gradient Descent, Filtering.
-^
More recently, Graph Algorithms, ParticleFiltering, Mean-shift, Multi-grid….
-^
Techniques from theoretical CS, appliedmath, physics, learning, ….
State of the art method
Boykov et al., Fast Approximate Energy Minimization via Graph Cuts
,
International Conference on Computer Vision, September 1999.
Ground truth
(Seitz)
(Comaniciu and Meer)
Viola and Jones: Real time Face
Detection
Viola and Jones: Real time FaceDetection
input
depth image
novel view
Szeliski
Figure 1: 3D tracking software developed at Digital Domain was used onnearly every shot of the movie Titanic. (From
Vision in Film and
Special Effects
Doug Roble,
Digital Domain)
Image Editing: Snakes, Intelligent Scissors,Contour-based editing (
Vision-Assisted Image
Editing
Eric N. Mortensen
Brigham Young
University)
Biomedical Engineering
• Segmentation
- Identify organs to measure them.– Find tumors.
• Tracking
- Is a heart beating properly? Is there dead
tissue?
• Registration/Matching.
- Positions of Tumors in Surgery.