Computer Vision
Course Information
Computer vision is a field that focuses on building machines that can see. In this course, we will cover the fundamentals of major tasks in computer vision, starting from the basics of image formation to modern computer vision methods based on deep learning. By the end of this course, students will have a solid foundation for conducting research in computer vision and the necessary technical background to understand and implement state-of-the-art vision papers.
Pre-requisites:
- CS 37300 Data Mining & Machine Learning
- MA 26500 Linear Algebra
- STAT 41600 Probability
Textbook:
- [FP] Computer Vision: A Modern Approach by David Forsyth and Jean Ponce (2nd ed.)
- [RS] Computer Vision: Algorithms and Applications by Richard Szeliski (2nd ed.)
- [DDL] Dive into deep learning by Zhang, Aston, et al.
Grading:
The final grade will be curved and no stricter than the cutoff:A+: 97-100, A: 93-96, A-: 90-92, B+: 87-89, ..., etc.
The percentage is computed following (without any rounding):
- Assignments: 50% (12.5% each assignment)
- Midterm: 25%
- Final Project: 25%
FAQ:
- Lecture slides will be posted on Brightspace. Some materials are from other Professors as referenced in the slides; Do not redistribute.
- The instructor & TAs can be best reached through Ed Discussion. Please post your questions there instead of emailing TAs.
- During office hours or on Ed Discussion, please avoid posting partial homework solutions or asking TAs to "review" your code/solution.
- Tutorial for learning Latex with Overleaf: [Link]
Instructor & TAs
Raymond A. Yeh
Instructor
Email: rayyeh [at] purdue.edu
Office Hour: Monday TBD
Location: Zoom
Chiao-An Yang
Teaching Assistant
Email: yang2300 [at] purdue.edu
Office Hour: TBD
Location: TBD
Time & Location
- Time: MWF (12:30PM - 01:20PM)
- Location: Max W & Maileen Brown Hall (BHEE 236)
Other Resource
Course Schedule
The following schedule is tentative and subject to change.
Date | Event | Description | Readings |
---|---|---|---|
Aug 19 | Lecture 1 | Introduction & Overview | DDL ch.3 |
Aug 21 | Lecture 2 | Applied Deep Learning - I | DDL 3 |
Aug 23 | Lecture 3 | Applied Deep Learning - II | DDL 2 |
Aug 26 | Info. | Assignment 1 Released Select from the following: | |
Aug 26 | Lecture 4 | Image Processing - I | |
Aug 28 | Lecture 5 | Image Processing - II | |
Aug 30 | Lecture 6 | Image Processing - III | |
Sept 2 | Info. | Labor Day Select from the following: | |
Sept 4 | Lecture 7 | Image filtering - I | F&P 4 |
Sept 6 | Lecture 8 | Image filtering - II | RS 3.4 |
Sept 9 | Lecture 9 | Image filtering - III | DDL 7 |
Sept 11 | Lecture 10 | Edge / Corner Detection - I | FP 5.1-5.2 |
Sept 13 | Lecture 11 | Edge / Corner Detection - II | FP 5.3 |
Sept 15 | Deadline | Assignment 1 Due at 11:59PM Select from the following: | |
Sept 16 | Info. | Assignment 2 Released Select from the following: | |
Sept 16 | Lecture 12 | Edge / Corner Detection - III | |
Sept 18 | Lecture 13 | SIFT - I | |
Sept 20 | Lecture 14 | SIFT - II | |
Sept 23 | Lecture 15 | SIFT - III | |
Sept 25 | Lecture 16 | Fitting & Alignment - I | FP 10.2-10.4, 22.1 |
Sept 27 | Lecture 17 | Fitting & Alignment - II | F&P 12.1 |
Sept 30 | Lecture 18 | Fitting & Alignment - III | |
Oct 2 | Lecture 19 | Fitting & Alignment - IV | |
Oct 4 | Lecture 20 | Cameras, Light, and Shading - I | FP 1 |
Oct 6 | Deadline | Assignment 2 Due at 11:59PM Select from the following: | |
Oct 7 | Info. | Assignment 3 Released Select from the following: | |
Oct 7 | Info | Fall Break Select from the following: | |
Oct 9 | Lecture 21 | Cameras, Light, and Shading - II | FP 2 |
Oct 11 | Lecture 22 | Cameras, Light, and Shading - III | |
Oct 13 | Deadline | Project Proposal Due at 11:59PM Select from the following: | |
Oct 14 | Lecture 23 | Midterm Review | |
Oct 16 | Deadline | Midterm Select from the following: | |
Oct 18 | Lecture 24 | Color | |
Oct 21 | Lecture 25 | Perspective projection - I | FP 1 |
Oct 23 | Lecture 26 | Perspective projection - II | |
Oct 25 | Lecture 27 | Camera calibration & Single-view modeling - I | FP 1 |
Oct 28 | Lecture 28 | Camera calibration & Single-view modeling - II | |
Oct 30 | Lecture 29 | Camera calibration & Single-view modeling - III | |
Nov 1 | Lecture 30 | Epipolar geometry & Structure from motion - I | FP 7.1 |
Nov 3 | Deadline | Assignment 3 Due at 11:59PM Select from the following: | |
Nov 4 | Info. | Assignment 4 Released Select from the following: | |
Nov 4 | Lecture 31 | Epipolar geometry & Structure from motion - II | FP 8 |
Nov 6 | Lecture 32 | Epipolar geometry & Structure from motion - III | |
Nov 8 | Lecture 33 | Two-view stereo - I | FP 7 |
Nov 11 | Lecture 34 | Two-view stereo - II | |
Nov 13 | Lecture 35 | Multi-view stereo | |
Nov 15 | Lecture 36 | Light field modeling - I | |
Nov 18 | Lecture 37 | Light field modeling - II | |
Nov 20 | Lecture 38 | Image Classification, segmentation, detection | DDL 4, 14 |
Nov 22 | Lecture 39 | Language and Vision | |
Nov 25 | Lecture 40 | Future of Vision? | |
Nov 24 | Deadline | Assignment 4 Due at 11:59PM Select from the following: | |
Nov 27 | Info | Thanksgiving Select from the following: | |
Nov 29 | Info | Thanksgiving Select from the following: | |
Dec 2 | Lecture 41 | Project Presentations | |
Dec 4 | Lecture 42 | Project Presentations | |
Dec 6 | Lecture 43 | Project Presentations | |
Dec 6 | Deadline | Final Project Report Due at 11:59PM Select from the following: |
Policies
Late & Absence Policy
We do not accept late assignments, i.e., late assignment by a second will be counted as 0%.For the consistency and fairness to all students, we follow the policy and absence request through the Office of the Dean of Students.
Academic Honesty
Please refer to Purdue's Student Guide for Academic Integrity. Academic dishonesty will result in an automatic zero on an assignment (not droppable) and the course grade will be reduced by one full letter grade. A second attempt will result in a failing grade for the course. It is one's responsibility to prevent others from copying your work.
Accessibility
Purdue University strives to make learning experiences as accessible as possible. If you anticipate or experience physical or academic barriers based on disability, please contact the Disability Resource Center at: drc@purdue.edu or by phone at 765-494-1247 and the course instructor to arrange for accommodations.
Classroom Guidance Regarding Protect Purdue
Any student who has substantial reason to believe that another person is threatening the safety of others by not complying with Protect Purdue protocols is encouraged to report the behavior to and discuss the next steps with their instructor. Students also have the option of reporting the behavior to the Office of the Student Rights and Responsibilities. See also Purdue University Bill of Student Rights and the Violent Behavior Policy under University Resources in Brightspace.
University Policies
Please refer to additional university policies in BrightSpace.