Course Description:
Provides an overview of computer vision, emphasizing the middle ground between image processing and artificial intelligence. Low-level image processing, computational photography, motion and depth estimation, object recognition, and case studies of current research
Office hours: There are no regularly scheduled office hours, but you can always arrange a meeting with either the TA or instructor. Just send an email.
Grading: The grade is based on four assignments. Each assignment will be a mix of coding and written answers.
Book (optional):
Computer Vision: A Modern Approach (2nd Edition), David A. Forsyth.
Computer Vision: Algorithms and Applications, Richard Szeliski.
Syllabus Overview:
Week 1: April 2
- Introduction
- Images and Filters Suggested Reading: Forsyth Section 7.1, Szeliski Section 3.2, 3.3.1
- Image Sampleing Suggested Reading: Forsyth Section 7.4, Szeliski Section 3.5.1, 3.5.2
Week 2: April 9
- Edge Detectoin Suggested Reading: Forsyth Section 8.2, 8.3, Szeliski Section: 4.2,4.3
- Geometric Transformations Suggested Reading: Forsyth Section 2.1 , Szeliski Section: 2.1, 3.6
- Interest Point Detection Suggested Reading: Szeliski Section: 4.1
Week 3: April 16
- Descriptors Suggested Reading: Forsyth Section 9.1 23.1.1, Szeliski Section: 4.1.
- Cameras and Image Formation Suggested Reading: Forsyth Section 1.1,1.2 , Szeliski Section: 3.4,3.5 .
- HW1: Filters Due (11:45pm) [Dropbox]
Week 4: April 23
- Image Stitching Suggested Reading: Szeliski Section: 9.1.1,9.1.3,9.2.1,9.3.4
- Structure From Motion Suggested Reading: Forsyth Section 12.3, 13.4 Szeliski Section:7.2,7.3,7.4
Week 5: April 30
- Structure from Motion (Cont'd)
- Stereo Suggested Reading: Szeliski Section 7, Forsyth Section 12
- HW2: Panorama Stitching Due (11:45pm) [Dropbox]
Week 6: May 7
- Reconstruction Suggested Reading: Szeliski Section:12
- Motion and Optical Flow Suggested Reading: Szeliski Section:8
Week 7: May 14
- Kinect, Visual Slam and Reconstruction Richard A. Newcombe (RSE and GRAIL labs)
- HW3: Stereo Due (11:45pm) [Dropbox]
Week 8: May 21
Week 9: May 28
Week 10: June 4
Homework Notes:
Please upload your assignment in a compressed file including codes, executables, writing assignments, and the data required for the program. Also, please include a brief readme describing any extra credit (bells and whistles) you accomplished. Note that there is a deadline for each assignment. Anything uploaded after the deadline will be marked late. Please be careful to not overwrite an in time assignment with a late assignment when uploading near the deadline. Each student has a TOTAL of 6 days late without penalty over the entire course (you may be one to two days late for every assignment, or 6 days late for one assignment, etc.) Please let the TA know if you cannot access any of the pages.